Overview
Setup
Part I
Part II
- All Departments in a Loop
- Your functions-demo.rmd File
Part III
Helpful Hints
Submission Instructions
Demo Report Sections

Overview

Your Objective

There have been growing concerns about gender pay equality in university settings.

Syracuse settles a class action lawsuit about pay equity

Syracuse University has settled a class-action lawsuit and will pay more than $3.7 million to resolve allegations from five female professors who claimed the school’s compensation and promotion policies and practices discriminated against women.

As a result, the Arizona Board of Regents has hired you to create a reporting system so that it can monitor the problem. You need to build a system to automate the process of generating reports when a new year of data becomes available. They have requested an initial report with data from 2016-2020.

Project Components

In order to build a reporting system you will need the following:

Custom functions for cleaning and visualizing the salary data (utils.R).
A template that contains the report instructions / sections (salary-report.rmd).
A batch script that will let you run all of the reports (batch.R).

You can download the draft (preliminary versions) of these files here:

In the subsequent steps you will:

Develop the rest of the custom functions for the full report and add them to the utils.R file.
Update the salary-report.rmd template by adding the new sections described below.
Include a loop that adds data from all departments, not just the one provided in the demo.
Gather the URLs for 2016, 2017, and 2018 data and add them to the batch processing file to generate three more years of reports.

A Focus on Workflow

You can always break a large project into discrete steps. The steps can be executed in order inside your project file (the salary-report.rmd in this case) to generate the desired results.

Pay attention to the project workflow in this reporting process. It will help you understand one of the fundamental concepts in data programming - dependencies. Each step depends upon information that was created in prior steps or custom functions that you have added to utils.R.

Data Dependencies

Recall that functions are just input-output machines. In order to leverage functions as part of a workflow the most important thing to pay attention to is making sure each function returns the output in a format that is the appropriate input into the next step:

As an example, the play_game() function in the Monty Hall Problem assignment is an example of a workflow function. All that the function does is call other functions that you have already created. But it allow us to play lots of games with a minimal amount of code:

results <- list()
for( i in 1:10000 )
{
  results[[i]] <- play_game( cars=3, goats=7 )
}

More importantly, wrapper functions require you to define explicit inputs (game size and number of cars in this case), and in doing so force consistency. Alternatively, if you have a loop that includes all of the steps then you need to update arguments in multiple places. This increases the likelihood of making an error. Similarly, if you find a bug in one of your functions then you need to update all of the places that function appears throughout your files. If you are using the wrapper function instead you only need to fix the bug in one place.

By building libraries of game playing functions we can then simplify the process in our primary project document - in this example the RMD file where we are conducting our experiments about optimal game playing strategies relative to game characteristics. When done correctly, a workflow approach makes code maintenance easier and it minimizes the likelihood of errors.

Function Dependencies

Some functions also depend upon other functions:

function_1 <- function(x) {
  y <- function_2(x)
  return(y)
}

To execute function_1() in this example, R needs to be able to find function_2(). We load functions used in a project by (1) including the code that creates the function directly in the RMD file, (2) loading the required packages with library() calls, or (3) sourcing them from a custom project script, often called utils.R, which is short for “project utility functions”.

To simplify projects you ultimately want to separate the process of writing your functions from the process of analyzing your data. The separation might look something like:

#   UTILS.R FILE; DEFINE fx's    #   RMD FILE; EXECUTE DATA RECIPES 
                                 #   
f_1 <- function()                #   
{ ... }                          #   d <- read.csv(...)
                                 #   
f_2 <- function()                #   d %>%  
{ ... }                          #     f_1() %>%
                                 #     f_2() %>% 
f_3 <- function()                #     f_3()
{ ... }                          #

Recall that functions operate as data verbs - actions performed with or upon our data. Our workflow becomes easier to manage when we are thoughtful about how we define and name functions so that the recipe is easy to understand.

URL %>%
  retrieve_data() %>%
  standardize_addresses() %>% 
  geocode_addresses() %>%
  map_xy_coordinates()

This often involves writing functions to solve problems (standardize your data, for example). Then combining several discrete tasks into a single wrapper function that makes the step more intuitive at a high level of abstraction.

unstring_salary <- function(x)
{ ... }

make_salary_fte <- function(d)
{ ... }


fix_salary <- function( d )
{
  d$salary <- unstring_salary( d$Salary )
  d <- make_salary_fte(d)
  return(d)
}

In this instance fix_salary() would group together the set of functions that are needed to standardize the raw salary data to prepare it for analysis. Note the workflow choices:

# VERSION 1
#  input: data frame
#  output: vector 
fix_salary <- function( d )
{
  d$salary <- unstring_salary( d$Salary )
  salary <- make_salary_fte( d )
  return(salary)
}

# VERSION 2
#  input:  data frame
#  output: data frame 
fix_salary <- function( d )
{
  d$salary <- unstring_salary( d$Salary )
  d <- make_salary_fte(d)
  return(d)
}

Version 2 fits naturally into a piped workflow. Version 1 does not, unless the last function only requires the salary variable and nothing else from the data frame:

# VERSION 1
d %>% 
  fix_salary() %>% 
  fx() # this function can only use salary

# VERSION 2 
d %>% 
  fix_salary() %>%
  fx() # this function can use all of d

File Dependencies

Batch processing reports is a new type of workflow that involves organizing your code using multiple files. The custom functions you write will be stored in your code library utils.R file. The data recipe that produces the report (loading data, wrangling it, summarizing it in tables, and graphing it) lives in the RMD template file. And the batch.R file let’s you execute all of the steps from one place. The workflow then looks like this:

batch.R knits the template.rmd through the render() function
render() sends document arguments (the URL) to template.rmd
template.rmd loads the data from an external source with the URL passed from render()
template.rmd loads functions from utils.R by ‘sourcing’ it
template.rmd executes the data recipe using functions from utils.R

template.rmd = salary-report.rmd in this example.

A workflow diagrammed (the workflow version of pseudocode) might look something like this:

batch.R
├─ rmarkdown::render()           >> 
│  ├─ use template.rmd           >>
│  ├─ send URL to template.rmd   >>
├─ execute template.rmd          >>
│  ├─ import utils.R library     >>
│  ├─ load data from URL         >>
│  ├─ execute data recipe

Note that YOU WILL NOT KNIT THE RMD FILE DIRECTLY on this assignment. You are knitting the RMD file by calling the rmarkdown::render() function so that you can control/change the data that is sent the report template (the URL argument), and thus can create many reports with a single template file.

Breaking the Project Into Tasks

As you work on more complex projects you will have to manage more raw data files, more nuanced data cleaning steps, more packages, and more custom functions.

Traditional analysts typically focus narrowly on analytical tasks - creating descriptive statistics, running regression models, generating tables of results. Data scientists will think more generally about the full project life-cycle, improving the data engineering processes, and making their team more efficient over time.

What needs to happen separately to acquire data, clean and refine it, execute the analysis, and package the results in a format useful to a specific audience?
How can we break the project into smaller steps so that each step is easier to manage?
How does data move through the workflow and how does it change throughout the process?
What custom functions will I need for the project?
Which input and output data types are needed at each step to manage the workflow with custom functions?
And more broadly, can components created for this project can be reused on future projects?

This type of project management mindset is also why many employers prefer employees with data science training over analysts that have strong statistical skills but a tenuous understanding of how all of the project steps fit together.

Setup

Required Packages

Install the gender and genderdata packages:

install.packages("remotes") 
remotes::install_github("lmullen/gender")
remotes::install_github("lmullen/genderdata")

If you are getting errors while installing genderdata you might need to download the tarball (zipped package) from the link and install it using the local (instead of CRAN or GitHub option):

Download the tarball (zipped package file): https://api.github.com/repos/lmullen/genderdata/tarball/HEAD
From the R menu select: Package >> Install packages from local files

You may need to install pandoc if it is not already on your machine (it is typically installed when R Studio is installed).

Remember to never include install commands in an RMD doc unless you include the chunk argument eval=F because it will create errors while knitting.

You will create helper functions to clean and process data using instructions below.They will be stored in a “utilities” file called utils.R and loaded into your report template using the source command. Source commands typically go in the same chunk as your commands to load packages:

library( dplyr )
library( pander )
library( knitr )
library( gender )
source( "utils.R" )  # needs to be in the same folder as salary-report.rmd

Note that a library in R refers to a collection of functions. The utils.R script is another type of library - custom functions that you wrote for the project.

Project Files

If you have not already, download the files into a local project folder:

As a result of changes to GitHub the download feature may strip the YAML header during download on some operating systems. Open salary-report.rmd and make sure it has the following YAML header (if not add it):

---
title: "Batch Report Demo"
output:
  html_document:
    theme: readable
    highlight: zenburn
    toc: true
params:
  url:
    value: x  
---

Testing Your Setup

Before advancing it is a good idea to test out the demo files to ensure that your machine and R environment are configured properly and all of the necessary packages are installed.

Open batch.R in a regular R console and try rendering the reports to create the HTML files.

setwd( "location/of/project/files" )

url.2020 <- "https://docs.google.com/spreadsheets/d/1RoiO9bfpbXowprWdZrgtYXG9_WuK3NFemwlvDGdym7E/export?gid=1335284952&format=csv"
rmarkdown::render( input='salary-report.rmd', 
                   output_file = "ASU-2020-Salary-Report.HTML",
                   params = list( url = url.2020 ) )

You should generate HTML files like these:

If you succeeded you should see similar HTML files in your project directory:

Note that you would probably not include code in a report for a general audience. You will change the knit options to echo=FALSE so code is hidden in the final report, but it is visible here for demo purposes.

dir()  # list files
[1] "ASU-2019-Salary-Report.HTML" "ASU-2020-Salary-Report.HTML" 
[3] "batch.R"                     "salary-report.rmd"          
[5] "utils.R"

Note, you can open a file from R to inspect it using the shell() command (this may not work on all operating systems):

shell( "ASU-2020-Salary-Report.HTML" )

If that works you are ready to get started!

Part I

Step 1: Data

We will be using the ASU salaries database distributed by the The State Press, and Arizona newspaper:

https://www.statepress.com/article/2017/04/spinvestigative-salary-database

Since ASU is a public university salary data is in the public domain, though the university doesn’t release it directly to the public. The State Press likely does a Freedom of Information request each year, cleans the data, and adds it to their online database of salaries (a google spreadsheet with several tabs):

https://docs.google.com/spreadsheets/d/1RoiO9bfpbXowprWdZrgtYXG9_WuK3NFemwlvDGdym7E/edit#gid=1335284952

We can use information embedded in this web link to create a convenient import command in R:

# WE NEED THE FORMAT: 
# https://docs.google.com/spreadsheets/d/<KEY>/export?gid=<GID>&format=csv
#
# where <KEY> and <GID> can be obtained from the base URL:
# https://docs.google.com/spreadsheets/d/<KEY>/edit#gid=<GID>

URL <- 'https://docs.google.com/spreadsheets/d/1RoiO9bfpbXowprWdZrgtYXG9_WuK3NFemwlvDGdym7E/export?gid=1335284952&format=csv'
d <- read.csv( URL )
head( d ) %>% pander()

Table continues below
Calendar.Year	Full.Name	Job.Description
2020	ABBASI, Mohammad	Research/Lab Assistant
2020	ARQUIZA, Jose Maria Reynaldo Apollo	Lecturer
2020	Aaberg, Kelsea	Student Support Specialist
2020	Abadjivor, Enyah	Project Manager
2020	Abayesu, Precious	Management Intern
2020	Abbas, James	Assoc Professor

Department.Description	Salary	FTE
Sch Biological & Hlth Sys Engr	$35,090.00	100
Sch Biological & Hlth Sys Engr	$71,400.00	100
Admission Services	$36,000.00	100
CASGE Tempe	$64,000.00	100
Health & Clinical Partnerships	$20,800.00	50
Sch Biological & Hlth Sys Engr	$107,195.00	100

Step 2: Parse First Name

Write a name parsing function called get_first_name() that will take a Full.Name as the argument and return only the first name.

Note that the Full.Name variable has the format: LAST_NAME, FIRST_NAME MIDDLE_NAME

# Example of a working get_first_name() function:
top.25 <- head( d$Full.Name,25 )
first.25 <- get_first_name( name=top.25 )

data.frame( top.25, first.25 ) %>% pander()

top.25	first.25
ABBASI, Mohammad	Mohammad
ARQUIZA, Jose Maria Reynaldo Apollo	Jose
Aaberg, Kelsea	Kelsea
Abadjivor, Enyah	Enyah
Abayesu, Precious	Precious
Abbas, James	James
Abbaszadegan, Morteza	Morteza
Abbe, Scott	Scott
Abbl, Norma	Norma
Abbott, Joshua	Joshua
Abbott, Joshua	Joshua
Abdollahi, Amir	Amir
Abdou, Olgeanna	Olgeanna
Abdurhman, Abdurazak	Abdurazak
Abel, John	John
Abele, Kelsey	Kelsey
Aberle, James	James
Abhyankar, Aditya	Aditya
Abi Karam, Karam	Karam
AbiNader, Millan	Millan
Aboalam, Safaa	Safaa
Abraha, Naomi	Naomi
Abramchuk, Mykola	Mykola
Abrams, Cristen	Cristen
Abrams, Kristen	Kristen

Note, the name format changes slightly between years. Specifically, some years use a comma+space as the delimiter between last name and the rest of the string. Other years use only a comma.

Make sure your name parser can handle both cases. If you use the comma as a split value, for example, you can always drop the extra space later using the trim white space function trimws().

### 2019 DATA
 [65] "Adelman,Madelaine"        "Adler,Patricia"          
 [67] "Adrian,Ronald"            "Adusumilli,Sesha Chandra"
 [69] "Afanador Pujol,Angelica"  "Affolter,Jacob"          
 [71] "Afsari Mamaghani,Sepideh" "Aganaba,Timiebi"     

### 2020 DATA
[1] "ABBASI, Mohammad"                    "ARQUIZA, Jose Maria Reynaldo Apollo"
[3] "Aaberg, Kelsea"                      "Abadjivor, Enyah"                   
[5] "Abayesu, Precious"

Here is some test data that includes both formats if you want to see if your function works for all years of data:

x <- 
c("ABBASI, Mohammad", "ARQUIZA,Jose Maria Reynaldo Apollo", 
"Aaberg,Kelsea", "Abadjivor, Enyah", "Abayesu,Precious", "Abbas, James", 
"Abbaszadegan, Morteza", "Abbe,Scott", "Abbl,Norma", "Abbott, Joshua" )

# Note the difference here: 

x.list <- strsplit( x, ", " )               # split on last name
COMMA.SPACE <- sapply( x.list, function(x){x[2]} )   # return second element

x.list <- strsplit( x, "," )                # split on last name
COMMA.ONLY <- sapply( x.list, function(x){x[2]} )   # return second element

cbind( COMMA.SPACE, COMMA.ONLY )

##       COMMA.SPACE COMMA.ONLY                  
##  [1,] "Mohammad"  " Mohammad"                 
##  [2,] NA          "Jose Maria Reynaldo Apollo"
##  [3,] NA          "Kelsea"                    
##  [4,] "Enyah"     " Enyah"                    
##  [5,] NA          "Precious"                  
##  [6,] "James"     " James"                    
##  [7,] "Morteza"   " Morteza"                  
##  [8,] NA          "Scott"                     
##  [9,] NA          "Norma"                     
## [10,] "Joshua"    " Joshua"

Pay attention to what happens if we ignore spaces. Which names are ignored by the gender package?

# library( gender )

# COMMA.ONLY
#  [1] " Mohammad"  "Jose Maria Reynaldo Apollo"                    
#  [3] " Enyah"     "Precious"   " James"    "Kelsea"      
#  [7] " Morteza"   "Scott"      "Norma"     " Joshua"

gender( COMMA.ONLY  )

What happened to Jose? Note how the gender package deals with compound first names:

gender( c( "jose", "jose maria", "josemaria" ) )

Since we can’t tell the difference between a compound first name (two first names) and a first name + middle name in this dataset we can use the first name only since it will provide the same information about the gender of the individual.

get_first_name( "Adusumilli, Sesha Chandra" ) --> "Sesha"

Step 3: Add Gender to the Dataset

The database does not provide the gender of the employees, but that’s alright because we can code these ourselves once we have first names isolated.

The gender package allows us to query a database of US birth certificates to see the most likely gender of someone with a specific first name.

library( gender )

# need to save first names for the merge 
d$first.name <- get_first_name( name=d$Full.Name )

# create a list of unique first names in the data 
unique.first.names <- unique( d$first.name )

# get gender data from US Social Security Admin 
gen <- gender( unique.first.names )
head( gen ) %>% pander()

name	proportion_male	proportion_female	gender	year_min	year_max
Aaron	0.9918	0.0082	male	1932	2012
Abba	1	0	male	1932	2012
Abbey	0.0017	0.9983	female	1932	2012
Abbie	0.0088	0.9912	female	1932	2012
Abby	0.003	0.997	female	1932	2012
Abdel	1	0	male	1932	2012

You then need to add gender to the salary dataset by merging the gender data frame with the salary data using first names as the unique key. Make sure you do not drop observations from the salary database.

Notes on Data Joins

If the name was not found in the US names database the gender will be coded as NA. After you complete the data join, replace all of the missing cases with the label “uncoded” so that we don’t end up with NAs in tables.

# d <- merge( d, gen, ... )
d$gender[ is.na(d$gender) ] <- "uncoded"
d$gender <- factor( d$gender, levels=c("male","female","uncoded") )

Create a function called add_gender() that calls the get_first_name() function, filters the vector of first names into a vector of unique first names, builds a gender table for the names, adds the gender fields to the data frame through a merge, then recodes NA values as “uncoded”.

Step 4: Standardize Job Titles

We are interested in five categories of job titles but the job description field is not standardized across the university. Here is a quick crosswalk, likely missing some cases and with some errors but good enough for a first pass.

Convert these steps into a add_titles() function that adds the new variable title to the existing data frame.

title <- rep( "", nrow(d) )
title[ grepl( "^Asst Professor$", d$Job.Description ) ]  <- "Assistant Professor"
title[ grepl( "^Assoc Professor$", d$Job.Description ) ] <- "Associate Professor"

title[ grepl( "^Professor$", d$Job.Description ) ]            <- "Full Professor"
title[ grepl( "Regents Professor", d$Job.Description ) ]      <- "Full Professor"
title[ grepl( "President's Professor", d$Job.Description ) ]  <- "Full Professor"

title[ grepl( "^Postdoctoral Research Scholar$", d$Job.Description ) ]   <- "Researcher"
title[ grepl( "Research Specialist", d$Job.Description ) ]               <- "Researcher"
title[ grepl( "Research Analyst", d$Job.Description ) ]                  <- "Researcher"
title[ grepl( "Postdoctoral Scholar", d$Job.Description ) ]              <- "Researcher"
title[ grepl( "Research Scientist", d$Job.Description ) ]                <- "Researcher"
title[ grepl( "Research Professional", d$Job.Description ) ]             <- "Researcher"
title[ grepl( "Research Professor", d$Job.Description ) ]                <- "Researcher"

title[ grepl( "^Instructor$", d$Job.Description ) ]           <- "Teaching Faculty"
title[ grepl( "Clinical .+ Professor", d$Job.Description ) ]  <- "Teaching Faculty"
title[ grepl( "Lecturer$", d$Job.Description ) ]              <- "Teaching Faculty"
title[ grepl( "^Lecturer Sr$", d$Job.Description ) ]          <- "Teaching Faculty"
title[ grepl( "^Principal Lecturer$", d$Job.Description ) ]   <- "Teaching Faculty"
title[ grepl( "Professor of Practice", d$Job.Description ) ]  <- "Teaching Faculty"

d$title <- factor( title, 
                   levels=c("Full Professor","Associate Professor",
                            "Assistant Professor","Teaching Faculty",
                            "Researcher" ) )

Step 5: Convert Salary to Numeric

Note the format of Salaries in the database. Since it has a dollar sign and comma it is understood to be a text field. As a result, we cannot compute basic statistics like the median salary, and we also cannot recast it easily.

head( d$Salary )

## [1] "$111,133.00" "$46,275.00"  "$37,717.00"  "$53,710.00"  "$91,000.00" 
## [6] "$107,160.00"

head( d$Salary ) %>% as.numeric()

## [1] NA NA NA NA NA NA

Write a function to remove the dollar sign and comma from the strings and return a numeric salary vector. Use it to create a new variable called “salary” (no uppercase S):

d$salary <- convert_currency( d$Salary )

Step 6: Convert All Salaries to Full-Time

For the purposes of comparing apples to apples want FTE salaries, or what the salary each person would earn if they are working full-time (FTE=100).

For example, if someone is working half-time (FTE=50) and is paid $40,000 a year their full-time salary would be $80,000:

40000 / (50/100)

## [1] 80000

Normalize the new salary variable so that it represents everyone’s FTE salary:

salary <- d$salary / (d$FTE / 100)

Note that the format of FTE varies by year. In the 2020 data it ranges from 1 to 100. Other years it ranges from 0 to 1.

To make your function robust include some conditionally:

if( max(d$FTE) == 100 )
{  salary <- d$salary / (d$FTE/100) }

if( max(d$FTE) == 1 )
{ salary <- d$salary / d$FTE }

Convert this step into a function called get_fte().

Step 7: Select Sample

Many university units are administrative and not academic, so we need to select a set of academic units for the report. A list is provided for you below.

Also drop employees that don’t fit into the defined title categories:

academic.units <- 
c("CISA-Intrdisp Hum & Comm", "CISA-Science & Mathmatics", 
"College of Health Solutions MS", "College of Health Solutions NT", 
"College of Health Solutions SH", "College Of Law", "English", "Hugh Downs School Of Comm", 
"Humanities Arts & Cultural", "Journalism & Mass Comm", "Ldrshp and Integrative Studies", 
"Math & Natural Sciences Div", "MDT Music", "Physics Department", 
"Psychology", "Sch Biological & Hlth Sys Engr", "Sch Compt Infor & Dec Sys Engr", 
"Sch Elect Comptr & Energy Engr", "Sch Engr Matter Trnsprt Energy", 
"Sch Future of Innov in Society", "Sch Sustain Engr & Built Envrn", 
"School Of Art", "School of Criminology & Crim J", "School Of Earth & Space Explor", 
"School of Geog Sci & Urban Pln", "School of Math & Stat Sciences", 
"School of Molecular Sciences", "School of Politics & Global St", 
"School Of Public Affairs", "School of Social Transform", "School Of Social Work", 
"SHPRS History Faculty", "Social & Behavioral Sciences", "Sols Administration & Faculty", 
"SOS Faculty & Researchers", "The Design School", "The Sanford School", 
"WPC Accountancy", "WPC Economics", "WPC Information Systems", 
"WPC Management", "WPC Supply Chain Management")

d <- 
  d %>% 
  filter( title != "" & ! is.na(title) ) %>% 
  filter( Department.Description %in% academic.units ) %>% 
  arrange( Department.Description, title )

nrow( d )

## [1] 2459

head( d ) %>% pander()

Table continues below
first.name	Calendar.Year	Full.Name	Job.Description
Barry	2020	Maid, Barry	Professor
Brooks	2020	Simpson, Brooks	Professor
Eva	2020	Brumberger, Eva	Professor
Ian	2020	Moulton, Ian	Professor
Jewell	2020	Rhodes, Jewell	Professor
Claire	2020	Lauer, Claire	Assoc Professor

Table continues below
Department.Description	Salary	FTE	gender	proportion_female
CISA-Intrdisp Hum & Comm	$54,050.00	50	male	0.0045
CISA-Intrdisp Hum & Comm	$145,610.00	100	male	0.0647
CISA-Intrdisp Hum & Comm	$106,350.00	100	female	0.9963
CISA-Intrdisp Hum & Comm	$100,000.00	100	male	0.0038
CISA-Intrdisp Hum & Comm	$297,000.00	100	female	0.8463
CISA-Intrdisp Hum & Comm	$90,150.00	100	female	0.9939

title	salary
Full Professor	54050
Full Professor	145610
Full Professor	106350
Full Professor	1e+05
Full Professor	297000
Associate Professor	90150

Create a function called get_study_sample() that takes the full salary dataset and returns a subset of employees that belong to the academic units listed above and belong to one of the five title categories we created.

Step 8: Summarize Salaries by Rank and Gender

Create a table of salary iq-range (25th quantile to 75th quantile) that is broken out by the rank of professors (title) and their gender:

The p variable represents the proportion of total employees within each group.

Turn this into a create_salary_table() function.

t.salary <- 
  d %>% 
  filter( ! is.na( title ) & title != "" ) %>% 
  group_by( title, gender ) %>% 
  summarize( q25=quantile(salary,0.25),
             q50=quantile(salary,0.50),
             q75=quantile(salary,0.75),
             n=n() ) %>% 
  ungroup() %>% 
  mutate( p= round( n/sum(n), 2) )

pander( t.salary )

title	gender	q25	q50	q75	n	p
Full Professor	male	115798	139198	173329	338	0.14
Full Professor	female	108500	129300	160255	141	0.06
Full Professor	uncoded	127614	147418	185207	56	0.02
Associate Professor	male	95000	105800	121300	229	0.09
Associate Professor	female	88928	98421	112949	180	0.07
Associate Professor	uncoded	101200	111022	121064	52	0.02
Assistant Professor	male	82294	94200	101950	147	0.06
Assistant Professor	female	81493	87000	94300	141	0.06
Assistant Professor	uncoded	86775	96500	100500	66	0.03
Teaching Faculty	male	48575	54000	82350	319	0.13
Teaching Faculty	female	47852	52844	65000	378	0.15
Teaching Faculty	uncoded	48350	55000	80221	57	0.02
Researcher	male	50000	55000	70000	169	0.07
Researcher	female	50000	53797	65000	114	0.05
Researcher	uncoded	46883	51500	60000	72	0.03

Step 9: Graph Results

I have provided you with functions to create graph of salaries of instructors, assistants, associate, and full professors in each unit reporting results by gender.

Note the chunk arguments:

{r, fig.height=7, fig.width=10}

add_position <- function( t, position, y, xmax, scale.f=8 )
{
  
  t.original <- t
  t <- filter( t.original, title==position )
  dot.size <- 2 + scale.f*sum(t$p)
  offset.n <- 1 + sum(t$p)*2
  
  male.median <- NA
  n.male <- NA
  t <- filter( t.original, title==position & gender == "male" )
  if( nrow(t) > 0 )
  { 
    male.median <- t$q50 
    n.male <- t$n
  }

  
  female.median <- NA
  n.female <- NA
  t <- filter( t.original, title==position & gender == "female" )
  if( nrow(t) > 0 )
  { 
    female.median <- t$q50 
    n.female <- t$n
  }

  
  # dumbell plots 
  segments( x0=female.median, x1=male.median, y0=y,
          col=gray(0.3,0.5), lwd=7 )
  points( male.median, y,
          col=adjustcolor( "darkblue", alpha.f = 0.5), 
          pch=19, cex=dot.size  )
  points( female.median, y,
          col=adjustcolor( "firebrick", alpha.f = 0.5), 
          pch=19, cex=dot.size  )
  
  pos.f <- 2
  pos.m <- 4
  if( ! ( is.na(female.median) | is.na(male.median) ) )
  {
    pos.f <- ifelse( female.median > male.median, 4, 2 )
    pos.m <- ifelse( female.median > male.median, 2, 4 )
  }
  
  # add salaries to right and left 
  text( female.median, y, paste0("$",round(female.median/1000,0),"k"),
        col=adjustcolor( "firebrick", alpha.f = 0.7), 
        cex=1.2, pos=pos.f, offset=offset.n )
  text( male.median, y, paste0("$",round(male.median/1000,0),"k"),
        col=adjustcolor( "darkblue", alpha.f = 0.7), 
        cex=1.2, pos=pos.m, offset=offset.n ) 
  
  # add faculty counts
  n.female <- ifelse( is.na(n.female), 0, n.female )
  n.female <- ifelse( nchar(n.female)==1, 
                      paste0( " ", n.female), n.female )
  n.male <- ifelse( is.na(n.male), 0, n.male )
  n.male <- ifelse( nchar(n.male)==1, 
                      paste0( " ", n.male), n.male )
  text( xmax-0.1*xmax, y+0.14, paste0( "f   = ", n.female),
        col="gray50", cex=1.1, pos=4  )
  text( xmax-0.1*xmax, y-0.14, paste0( "m = ", n.male),
        col="gray50", cex=1.1, pos=4  )


  axis( side=2, at=y, labels=position, 
        las=2, tick=F, cex.axis=1.5, col.axis="gray50" )
}


build_graph <- function( t.salary, unit )
{
  unique.titles <- unique( t.salary$title )
  ymax <- length(unique.titles)
  xmax <- round( max(t.salary$q50), -3 ) + 50000
  color.key.pos <- 40000 + ( xmax - 40000 ) / 2
  color.key.inc <- ( xmax - 40000 ) / 10
  
  t.mf <- filter( t.salary, gender %in% c("male","female") )
  N <- sum( t.mf$n )
  
  par( mar=c(6,15,4.1,0) )
  plot.new()
  plot.window( xlim=c(40000-10000,xmax), ylim=c(0,ymax+1) )
  
  abline( v=seq(40000,xmax-40000,20000), lwd=1.5, lty=2, col=gray(0.5,0.5) )
  axis( side=1, 
        at=seq(40000,xmax-40000,20000), 
        labels=paste0("$",seq(40,(xmax-40000)/1000,20),"k"),
        cex.axis=1.1, col.axis="gray40", tick=FALSE )
  
  y <- ymax
  
  if( "Full Professor" %in% unique.titles )
  {
    add_position( t.salary, position="Full Professor", y, xmax )
    y <- y-1
  }
  if( "Associate Professor" %in% unique.titles )
  {
    add_position( t.salary, position="Associate Professor", y, xmax )
    y <- y-1
  }
  if( "Assistant Professor" %in% unique.titles )
  {
    add_position( t.salary, position="Assistant Professor", y, xmax )
    y <- y-1
  }
  if( "Teaching Faculty" %in% unique.titles )
  {
    add_position( t.salary, position="Teaching Faculty", y, xmax )
    y <- y-1
  }
  if( "Researcher" %in% unique.titles )
  {
    add_position( t.salary, position="Researcher", y, xmax )
    y <- y-1
  }

  
  text( color.key.pos + 3*color.key.inc, 0, "MALE", 
        col=adjustcolor( "darkblue", alpha.f = 0.7), cex=1.2 )
  text( color.key.pos + 1.8*color.key.inc, 0, "FEMALE", 
        col="firebrick",  cex=1.2 )
  text( xmax - 0.1*xmax, 0, paste0("N = ",N), col="gray40",  cex=1.2, pos=4 )

  
  title( main="Median Salary by Rank and Gender", cex.main=1.5, col.main="gray30" )
  title( xlab=unit, col.lab="gray50", cex.lab=1.5, line=5 )
  title( xlab="dot size represents proportion of faculty at that rank",
         col.lab="gray50", cex.lab=0.9 )
  
  return(NULL)
}



### TEST: 
#   t.salary is the salary table from the previous step
#   unit is a category from Department.Description
#
#     build_graph( t.salary, unit="Psychology" )
#


d %>%  
  filter( Department.Description == "Psychology" ) %>% 
  create_salary_table( ) %>% 
  build_graph( unit="Psychology" )

NULL

Step 10 - Top Five Salaries

Create function that generates a table of the top 5 salaries and reports the name, gender, position, and salary of each person on the list.

You might find the following formatting function helpful:

dollarize <- function(x)
{ paste0("$", format( round( x, 0 ), big.mark="," ) ) }

dollarize( x=150000 )

## [1] "$150,000"

Full.Name	gender	Job.Description	salary
LePine, Jeffery	male	Professor	$402,257
Panchanathan, Sethuraman	uncoded	Professor	$365,000
Gomez-Mejia, Luis	male	Regents Professor	$361,393
Hero, Rodney	male	Professor	$341,750
Prescott, Edward	male	Regents Professor	$340,159

The utils.R File

Once all of your functions are working properly copy them all into the utils.R script.

This script will be “sourced” to load all of the functions in your report template (see Part III below).

Part II

All Departments in a Loop

Automate the process using a loop to isolate data from each unit, create the two tables and the graph, then add them to the document.

for( i in academic.units )
{
  
  d2 <- filter( d, Department.Description == i )
  # create the salary summary by rank & gender table 
  # create the top 5 salaries table 
  # build the graph 

  # print the tables:  
  # cat( paste('<h3>',"TOP FIVE SALARIES",'</h3>' ) )
  # cat( t.rank %>% knitr::kable(format="html") )   

  # cat( '<br><hr><br>' )
  
}

Some academic units may not exist in every year of the data so add a control structure that checks if the unit is available and skips trying to add it to the report if that department did not exist yet:

for( i in academic.units )
{
  
  d2 <- filter( d, Department.Description == i )
  if( nrow(d2) == 0 ) { next }  
  # skips the rest of the code in the loop 
  # and start over with the next department
  ...
  
}

You need to include the chunk argument results=‘asis’ and in order to return the raw text from inside a loop you need to use cat() instead of print():

{r, fig.height=7, fig.width=10, results="asis"}

Note, the knitr package has a function called kable that will output nice HTML tables.You can add HTML tables to the RMD through the chunk, then render them to produce nicely-formatted results.

cat( t.rank %>% knitr::kable(format="html") )

Your functions-demo.rmd File

Name your current file “functions-demo.rmd”.

The rendered HTML file will serve as the documentation of your process.

It should load the 2020 data and will also include all of the custom functions you created.
Organize your file with sections for each Step above (step 1, step 2, etc).
Do NOT hide your code in this file and demo each function with some test data to show they are working.

In the next step you will create a generic report template (salary-report.rmd) which sources the functions from utils.R and has a generic data load step so you can re-use the template with different years of data (see Part III below).

Part III

Big Picture

You are creating a generic report template that will allow you to run a salary report with any year of data.

The salary-report.rmd template will serve the same purpose as the Resume.rmd template on Lab 6:

It sources your custom scripts (parsin_functions.R in the resume example)
loads the data (positions.csv)
then calls the custom functions to add content to each section.

https://github.com/DS4PS/cv/blob/master/resume.Rmd

source('parsing_functions.R')

position_data <- read_csv('positions.csv')


## Education {data-icon=graduation-cap data-concise=true}

'''{r}
position_data %>% print_section('education')
'''


## Selected Writing {data-icon=newspaper}

'''{r}
position_data %>% print_section('writings')
'''

Your template will have a similar structure:

source( 'utils.R' )   # load custom functions 
 
URL <- params$url     # load data 
d <- read.csv( URL )  

... data cleaning steps ... 


# PSYCHOLOGY

'''{r}
d %>%  
  filter( Department.Description == "Psychology" ) %>% 
  create_salary_table(  ) %>% 
  build_graph( unit="Psychology" )
'''
  
## PAY RANGE BY RANK AND GENDER

'''{r}
d %>% 
  filter( Department.Description == "Psychology" ) %>% 
  create_salary_table(  )
'''

## TOP 5 SALARIES 

etc...

Except you will loop through all academic units:

source( 'utils.R' )

URL <- params$url
d <- read.csv( URL )

... data cleaning steps ...



for( i in academic.units )
{
  
  cat( paste('<h1>', i ,'</h1>' ) )
  
  d %>%  
    filter( Department.Description == i ) %>% 
    create_salary_table() %>% 
    build_graph( unit=i )  

  cat( paste('<h3>', 'PAY RANGE BY RANK AND GENDER' ,'</h3>' ) )

  t.salary <- 
    d %>% 
    filter( Department.Description == i ) %>% 
    create_salary_table()
    
  cat( t.salary %>% knitr::kable(format="html") )

  # etc...

  cat( '<br><hr><br>' )
  
}

Step 1: Create a Generic Salary Report Template

Once you have completed all of these steps you are ready to create your salary report template. It is generic because it will create the same report using different years of data.

Create an RMD template called salary-report.rmd.

Copy all of your new functions into a utils.R file (in R Studio you can use the top menu bar):

select File >> New File >> R Script >> save as utils.R

In the chunk where you load packages add a command to source utils.R to load your custom functions.

library( dplyr )
library... load the rest 

source( 'utils.R' )

Make the data load step generic so you can change the input data at the rmarkdown::render stage (see Step 3 for more details):

Add params to the YAML header:

---
title: 'ASU Salary Report'
output:
  html_document:
    theme: readable
    highlight: zenburn
    toc: true
params:
  url:
    value: x   
---

And change the data load step to:

URL <- params$url
d <- read.csv( URL )

Include each step needed to clean, augment, and analyze the data. Include a loop at the end that generates a report section for each academic unit.

You will build a report using the render function in the rmarkdown package (this is what is called when you “knit” your RMD doc in R Studio):

rmarkdown::render( input='salary-report.rmd', 
                   output_file = "ASU-2020-Salary-Report.HTML",
                   params = # 2020 data url )

Step 2: Customize Your CSS

Customize your salary-report.rmd by adding a CSS section at the end. Change the color of your headers and add some spacing to the tables.

# pretty tables 

td {
    padding: 3px 15px 3px 15px;
    text-align: center !important;
}

th {
    padding: 3px 15px 3px 15px;
    text-align: center !important;
    font-weight: bold;
    color: SlateGray !important;
}

Step 3: Create a Batch Processing Script

We are going to batch process multiple years of reports using functionality in the rmarkdown package.

We will knit reports using the render() function instead of the knit button in R Studio because it allows us to pass parameters to an RMD template the same way we pass arguments to a function. Specifically, we will pass new

BATCH PROCESS SCRIPT:

Create a new R script called ““batch.R”.

This script will render a new report using salary-report.rmd, one for each year. The batch.R file calls the RMD template file, and the RMD template file in-turn sources the custom functions and loads the data.

So your files are chained together as follows:

batch.R 
├── render( url.2020 )
│   ├── salary-template.rmd
│       ├── source( 'utils.R' )
│       ├── read.csv( params$url ) # 2020
├── render( url.2019 )
│   ├── salary-template.rmd
│       ├── source( 'utils.R' )
│       ├── read.csv( params$url ) # 2019
├── render( url.2018 )
│   ├── salary-template.rmd
│       ├── source( 'utils.R' )
│       ├── read.csv( params$url ) # 2018

Note that the same salary-template.rmd and utils.R will be re-used for each report. The only thing that is changing is the data load step.

We can pass url.year to the RMD document THROUGH the render() function, which then changes which year of data is loaded at the read.csv() step in the document.

This means we can reuse the report template over and over, and we have a convenient way to send it the proper data to use.

CREATE A GENERIC DATA LOAD STEP:

We want to change the data load step from a specific year of data:

URL <- 'https://docs.google.com/spreadsheets/d/1RoiO9bfpbXowprWdZrgtYXG9_WuK3NFemwlvDGdym7E/export?gid=1335284952&format=csv'
d <- read.csv( URL )

To a generic URL placeholder that changes each time we create a new report.

URL <- params$url
d <- read.csv( URL )

To make it possible to send the correct URL to the RMD template at the render stage we need to add a new params field in your YAML header that looks like this:

---
title: 'ASU Salary Report'
output:
  html_document:
    theme: readable
    highlight: zenburn
    toc: true
params:
  url:
    value: x   
---

PASSING NEW DATA TO THE REPORT TEMPLATE:

The YAML fields in the RMD doc are like arguments in a function.

The YAML header provides the defaults, but they can be overwritten using the rmarkdown::render() function. We call this inside the batch.R file.

#####  BATCH.R FILE      

## 2020 REPORT
url.2020 <- "https://docs.google.com/spreadsheets/d/1RoiO9bfpbXowprWdZrgtYXG9_WuK3NFemwlvDGdym7E/export?gid=1335284952&format=csv"
rmarkdown::render( input='salary-report.rmd', 
                   output_file = "ASU-2020-Salary-Report.HTML",
                   params = list( url = url.2020 ) )

## 2019 REPORT 
url.2019 <- "https://docs.google.com/spreadsheets/d/1RoiO9bfpbXowprWdZrgtYXG9_WuK3NFemwlvDGdym7E/export?gid=1948400967&format=csv"
rmarkdown::render( input='salary-report.rmd', 
                   output_file = "ASU-2019-Salary-Report.HTML",
                   params = list( url = url.2019 ) )

Here params = list( url = url.2020 ) will populate params$url in the data load chunk of the RMD file:

URL <- params$url
d <- read.csv( URL )

Whichever URL we use in the batch.r file at the render() stage will be the data used to generate the report.

GET THE URL FOR EACH YEAR:

Note that so far we have been working with the 2020 salary data that was loaded directly in the RMD doc:

URL <- 'https://docs.google.com/spreadsheets/d/1RoiO9bfpbXowprWdZrgtYXG9_WuK3NFemwlvDGdym7E/export?gid=1335284952&format=csv'
d <- read.csv( URL )

The State Press google spreadsheet has multiple years of data organized by tabs. Each tab has a unique URL:

ASU Salaries Spreadsheet

# https://docs.google.com/spreadsheets/d/  <KEY>  /export?gid=  <GID>  &format=csv
# where <KEY> and <GID> can be obtained from the default spreadsheet URL

# Note that the default URL is in EDIT mode, not EXPORT
# https://docs.google.com/spreadsheets/d/<KEY>/edit#gid=<GID>

# IF YOU NEED A LITTLE HELP CREATING THE EXPORT MODE: 

KEY <- "1RoiO9bfpbXowprWdZrgtYXG9_WuK3NFemwlvDGdym7E"   # same for all
GID.2020 <- "1335284952"
url.2020 <- paste0( "https://docs.google.com/spreadsheets/d/", KEY, "/export?gid=", GID.2020, "&format=csv" )


# GET THE GOOGLE ID <GID> FOR EACH SHEET
# 2019 sheet:  https://docs.google.com/spreadsheets/d/1RoiO9bfpbXowprWdZrgtYXG9_WuK3NFemwlvDGdym7E/edit#gid=1948400967
# 2018 sheet:  https://docs.google.com/spreadsheets/d/1RoiO9bfpbXowprWdZrgtYXG9_WuK3NFemwlvDGdym7E/edit#gid=169937930

# GID.2019 <- "1948400967"
# url.2019 <- paste0( "https://docs.google.com/spreadsheets/d/", KEY, "/export?gid=", GID.2019, "&format=csv" )
#
# GID.2018 <- "169937930"
# url.2018 <- paste0( "https://docs.google.com/spreadsheets/d/", KEY, "/export?gid=", GID.2018, "&format=csv" )

# etc

Or you can generalize the process:

build_url <- function( GID )
{
  KEY <- "1RoiO9bfpbXowprWdZrgtYXG9_WuK3NFemwlvDGdym7E"
  url <- paste0( "https://docs.google.com/spreadsheets/d/", KEY, "/export?gid=", GID, "&format=csv" )
  return( url )
}

url.2020 <- build_url( GID="1335284952" )

THE BATCH.R FILE:

Find the proper URLs for years 2016-2020 (same keys, unique Google IDs) and add them to the file.
Use the render function to create a separate report for each year.
Make sure to change the output filename and the input URL for each year.

Now run your batch.R script and generate reports for all years.

Helpful Hints

Data Types

Keeping track of data types and your work flow are small details but also one of the most important skills as your projects grow in size and complexity.

A reminder that it is a very good habit to use consistent object names so that you are paying attention to data types.

Some suggestions:

# data frames 
d
df
dat

# subset of a data frame
d2
d.male
dat.top5

# vectors (argument names) 
x, y
v
x.string <- as.character(x)
x.num <- as.numeric(x)

# logical vectors (defining groups)
these
these.female <- gender == "female"

# tables 
t <- table( x, y )
t.salary.by.gender <- d %>% group_by( gender ) %>% summarize( ave=mean(salary) )

# regression models 
m
m1
m2

Once you are working with a larger project you will see the importance of good housekeeping and organizational skills.

Data types are not trivial! Creating a habit of naming objects by data type will force you to be aware of your objects as well as pay attention to proper argument types and return values when creating functions.

Functions

Functions are input-output machines. They take inputs and transform them into something else.

Notes on Functions

Recall that a function is just a recipe. For the recipe to work properly all of the ingredients need to be provided to the function as arguments.

Pay attention to three main types of functions in this project - those that refine vectors, those that augment data frames, and those that transform a data frame into a table.

# VECTORS
refine_vector <- function(x)
{
  x <- do_something(x)
  return(x)
}

# USE:
# d$x <- refine_vector( d$x )



# DATA FRAMES
augment_df <- function(d)
{
  
  # add variable to d
  x2 <- augment(d$x)
  d$x2 <- x2
  
  # filter rows
  d <- filter( d, y > 10 )
  
  # select columns 
  d <- select( d, x, y, z )
  
  return(d)
  
}

# USE: 
# d <- augment_df( d )



# TABLES
build_table <- function(d)
{
  
  t <- 
    d %>%
    group_by( f1, f2 ) %>% 
    summarize( ave.x=mean(x) )
  
  return(t)
  
}

# USE: 
# t <- build_table( d )

Pay attention to what you are trying to accomplish with the task.

For example, Step 4 asks you to create a function to recode titles to build a new title variable from the current Job.Description variable.

There are different ways we can accomplish this. Here’s an approach that uses the data frame as the input-output object type (adds new variable to the data frame, returns new augmented data frame):

add_titles <- function(d)
{
  # code abstraction 
  title <- some_process( d$Job.Description )
  d$title <- title
  return(d)
}

# USE: 
# d <- add_titles( d )

Alternatively, if we look at the code we can see that the only information we need for the task is the Job.Description variable, so we could structure the function around the vector of job descriptions:

recode_job_description <- function( job.desc )
{
  # code abstraction 
  title <- some_process( job.desc )
  return(title)
}

# USE: 
# d$title <- recode_job_description( d$Job.Description )

Both approaches are reasonable in this case. Whichever you choose, though, the very important detail to pay attention to is the journey of your data through the load and wrangling steps as it is refined, augmented, and reshaped to prepare it for whatever analysis is presented in the report.

# DATA FRAME APPROACH 
d <- add_titles( d )

# VECTOR APPROACH 
d$title <- recode_job_description( d$Job.Description )

One of the reasons the first approach is preferable is that functions that use data frames as both the input and the output can be added to data recipes using pipes:

d %>% 
  add_gender() %>% 
  add_titles() %>% 
  fix_salary()

If we use a vectorized function we can’t use that approach since recode_job_description() will expect a vector as the input information and it will also output a vector as the return object:

# error: 
d %>% 
  add_gender() %>% 
  recode_job_description() %>%     # expecting a vector
  fix_salary()                     # expecting a df 


# without pipes:  
d <- add_gender( d )
d$title <- recode_job_description( d$Job.Description )
d <- fix_salary( d )

Date Joins (Merging dfs)

If it’s been awhile since you have had to conduct a merge.

Data Joins

Full.Name	first.name	Salary
Bae, Aaron	Aaron	$52,750.00
Baker, Aaron	Aaron	$107,160.00
Ball, Aaron	Aaron	$127,690.00

Why do we use unique names and always check data frame dimensions before and after merges?

Note that you will query only a list of unique first names:

unique.names <- unique( d$first.name )

What happens if we send name duplicates to the gender package? It will send back one match per name and it won’t check to make sure there are no duplicates.

g <- gender( df.aaron$first.name ) 
g %>% pander()

name	proportion_male	proportion_female	gender	year_min	year_max
Aaron	0.9918	0.0082	male	1932	2012
Aaron	0.9918	0.0082	male	1932	2012
Aaron	0.9918	0.0082	male	1932	2012

Let’s see what happens if we merge these two data frames. I’ll number the observations in the gender table so it’s easier to see what happens:

g <- 
  g %>%
  select( name, gender ) %>% 
  mutate( gender = paste0( gender, 1:3 ) ) 
  

merge( df.aaron, g, by.x="first.name", by.y="name" ) %>% pander()

first.name	Full.Name	Salary	gender
Aaron	Bae, Aaron	$52,750.00	male1
Aaron	Bae, Aaron	$52,750.00	male2
Aaron	Bae, Aaron	$52,750.00	male3
Aaron	Baker, Aaron	$107,160.00	male1
Aaron	Baker, Aaron	$107,160.00	male2
Aaron	Baker, Aaron	$107,160.00	male3
Aaron	Ball, Aaron	$127,690.00	male1
Aaron	Ball, Aaron	$127,690.00	male2
Aaron	Ball, Aaron	$127,690.00	male3

We started with 3 Aarons in df.aaron and 3 Aarons in the gender data frame g.

Starting with Aaron Bae, the merge() function looks to g to find which columns to append to Bae’s data. Since we are merging on first names only, though, we can’t differentiate between any of the Aarons and as a result merge will append all Aarons from g to each Aaron in df.aaron.

Since we have 3 Aarons in this dataset that means we would have 3 separate Aaron cases in the gender data frame if we do not send a list of unique names only. That means we append 3 observations per Aaron for a total of 3x3 = 9 rows in the final dataset.

In the full dataset we have 36 Aarons, so this mistake would result in 36x36 = 1,296 rows of Aarons. And Aaron is not even the most common name. There are 191 Michaels, so this error would generate 36,481 rows of Michaels in the final dataset!

Pay attention to your data joins. It’s one of the cases where arguments and duplicates matter a great deal and the merge will likely work with the wrong arguments or if duplicates are present but will corrupt your dataset.

Sorting Salaries

Will the Salary variable sort correctly? What’s happening here?

x <-
c("$35,090.00", "$71,400.00", "$36,000.00", "$64,000.00", "$20,800.00", 
"$107,195.00", "$147,225.00", "$98,426.00", "$89,406.00", "$95,095.00" )

sort( x, decreasing=TRUE )

##  [1] "$98,426.00"  "$95,095.00"  "$89,406.00"  "$71,400.00"  "$64,000.00" 
##  [6] "$36,000.00"  "$35,090.00"  "$20,800.00"  "$147,225.00" "$107,195.00"

Recall the difference between sorting numbers (arrange by magnitude) and alphabetizing strings. Since Salary contains dollar signs and commas it will be a string. You can sort it, but sorting strings uses alphabetization rules, not magnitude.

Sort the numeric version of salary, then format (dollarize) to make it look nice in a table.

Submission Instructions

Deliverables

You have the following files:

utils.R - contains all of your helper functions
function-demo.rmd, function-demo.html - show each helper function in action
salary-report.rmd - report template
batch.R - generates reports for all years
five rendered HTML reports:
- “ASU-2020-Salary-Report.HTML”
- “ASU-2019-Salary-Report.HTML”
- “ASU-2018-Salary-Report.HTML”
- “ASU-2017-Salary-Report.HTML”
- “ASU-2016-Salary-Report.HTML”

The relationship between files:

function-demo.rmd 
├── output: function-demo.html

batch.R 
├── render( salary-template.rmd ) # 2020 data
│       ├── source( 'utils.R' )
│       ├── output: ASU-2020-Salary-Report.HTML

├── render( salary-template.rmd ) # 2019 data
│       ├── source( 'utils.R' )
│       ├── output: ASU-2019-Salary-Report.HTML

├── render( salary-template.rmd ) # 2018 data
│       ├── source( 'utils.R' )
│       ├── output: ASU-2018-Salary-Report.HTML

In the function-demo.rmd file include all of your code and demo each function from Steps 1-10 above so I can see they are working properly.

The salary-report.rmd file, on the other hand, will hide the code so that it generates a clean report. Make sure to suppress warnings and messages as well. The knitr options argument is helpful:

knitr::opts_chunk$set( echo=F, message=F, warning=F )

Grade Break-Down

This assignment is worth 15 points and is broken into 3 main parts with points assigned as follows:

Part I: Working Functions (5 Points)

I will source the utils.R file and test your functions.

Part II: Working Report (5 Points)

Does your function-demo.rmd file knit and does it produce proper report sections for the 2020 data (the two tables and one graph)?

Note that this is your documentation file, so include all of the data wrangling steps and show all of your code.

Part III: Batch Process (5 Points)

Does salary-report.rmd produce a report?

Can I run your batch.R script and generate fresh reports for all 5 years without getting errors?

Partial Credit

Start from the top and work your way through the assignment. Complete what you can. If you can’t get a step to work then submit your files and explain where they get stuck. I can at least give partial credit for a section if I can see what you are doing.

Submission

Zip the nine files above into a project directory and upload to canvas.

Name your files: PAF-514-FINAL-LastName.zip

Demo Report Sections

Your final reports should look something like this:

CISA-Intrdisp Hum & Comm

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Rhodes, Jewell	female	Professor	$297,000
Simpson, Brooks	male	Professor	$145,610
Brumberger, Eva	female	Professor	$106,350
Moulton, Ian	male	Professor	$100,000
Nystrom, Eric	male	Assoc Professor	$ 94,612

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$ 77,025	$100,000	$122,805	3	0.07
Full Professor	female	$154,012	$201,675	$249,338	2	0.04
Associate Professor	male	$ 94,612	$ 94,612	$ 94,612	1	0.02
Associate Professor	female	$ 88,762	$ 89,225	$ 89,688	2	0.04
Assistant Professor	male	$ 73,512	$ 74,025	$ 74,512	3	0.07
Assistant Professor	female	$ 72,100	$ 72,200	$ 74,375	3	0.07
Assistant Professor	uncoded	$ 65,000	$ 65,000	$ 65,000	1	0.02
Teaching Faculty	male	$ 24,389	$ 46,400	$ 48,897	9	0.20
Teaching Faculty	female	$ 46,512	$ 48,590	$ 51,706	20	0.44
Teaching Faculty	uncoded	$ 24,490	$ 24,490	$ 24,490	1	0.02

CISA-Science & Mathmatics

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Sagers, Cynthia	female	Professor	$123,750
Zandieh, Michelle	female	Professor	$113,288
Shovkovy, Igor	male	Professor	$107,675
Kang, Yun	female	Professor	$103,330
Sukharev, Maxim	male	Professor	$103,096

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$104,241	$105,386	$106,530	2	0.05
Full Professor	female	$108,309	$113,288	$118,519	3	0.08
Associate Professor	male	$ 89,752	$ 95,208	$ 95,847	3	0.08
Associate Professor	female	$ 93,698	$ 94,882	$ 96,066	2	0.05
Associate Professor	uncoded	$ 90,333	$ 90,333	$ 90,333	1	0.03
Assistant Professor	male	$ 82,780	$ 83,628	$ 84,814	3	0.08
Assistant Professor	female	$ 81,357	$ 82,714	$ 84,070	2	0.05
Assistant Professor	uncoded	$ 84,536	$ 85,024	$ 85,512	2	0.05
Teaching Faculty	male	$ 48,925	$ 50,000	$ 58,082	9	0.24
Teaching Faculty	female	$ 48,686	$ 48,925	$ 56,949	7	0.18
Teaching Faculty	uncoded	$ 48,106	$ 48,350	$ 49,275	3	0.08
Researcher	female	$ 58,000	$ 58,000	$ 58,000	1	0.03

College of Health Solutions MS

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Gaesser, Glenn	male	Professor	$162,943
Adams, Marc	male	Assoc Professor	$120,280
Siegler, Jason	male	Assoc Professor	$115,000
Huberty, Jennifer	female	Assoc Professor	$103,650
Der Ananian, Cheryl	female	Assoc Professor	$ 93,600

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$162,943	$162,943	$162,943	1	0.03
Associate Professor	male	$ 97,398	$115,000	$117,640	3	0.09
Associate Professor	female	$ 92,248	$ 93,299	$ 96,112	4	0.12
Assistant Professor	male	$ 59,438	$ 69,625	$ 79,812	2	0.06
Assistant Professor	female	$ 88,000	$ 88,000	$ 88,000	1	0.03
Teaching Faculty	male	$ 53,062	$ 59,000	$ 63,550	7	0.22
Teaching Faculty	female	$ 54,500	$ 55,215	$ 57,482	11	0.34
Researcher	female	$ 48,789	$ 50,000	$ 51,352	3	0.09

College of Health Solutions NT

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Ohri-Vachaspati, Punam	female	Professor	$165,543
Wang, Shu	male	Professor	$160,000
Banks, Dorothy	female	Professor	$140,000
Bruening, Meredith	female	Assoc Professor	$120,280
Vega-Lopez, Sonia	female	Assoc Professor	$113,460

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$160,000	$160,000	$160,000	1	0.03
Full Professor	female	$146,386	$152,772	$159,157	2	0.06
Associate Professor	female	$105,589	$106,665	$113,460	5	0.16
Assistant Professor	female	$ 89,000	$ 89,000	$ 89,000	1	0.03
Assistant Professor	uncoded	$ 94,700	$ 94,700	$ 94,700	1	0.03
Teaching Faculty	female	$ 53,625	$ 56,600	$ 63,725	17	0.55
Researcher	male	$ 48,113	$ 48,742	$ 49,371	2	0.06
Researcher	female	$ 63,650	$ 66,100	$ 68,550	2	0.06

College of Health Solutions SH

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Scherer, Nancy	female	Professor	$156,634
Gray, Shelley	female	Professor	$147,400
Berisha, Visar	uncoded	Assoc Professor	$118,400
Schatzki, MariaRita	uncoded	Clinical Assoc Professor (FSC)	$106,308
Reddy, Corianne	female	Assoc Professor	$102,000

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	female	$149,708	$152,017	$154,326	2	0.06
Associate Professor	male	$101,397	$101,397	$101,397	1	0.03
Associate Professor	female	$100,354	$101,709	$101,854	3	0.10
Associate Professor	uncoded	$118,400	$118,400	$118,400	1	0.03
Assistant Professor	male	$ 98,000	$ 98,000	$ 98,000	1	0.03
Assistant Professor	female	$ 98,050	$ 98,200	$ 98,350	2	0.06
Teaching Faculty	female	$ 77,500	$ 80,000	$ 84,780	13	0.42
Teaching Faculty	uncoded	$106,308	$106,308	$106,308	1	0.03
Researcher	male	$ 29,120	$ 37,440	$ 66,192	3	0.10
Researcher	female	$ 26,239	$ 27,642	$ 37,438	4	0.13

College Of Law

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Bodansky, Daniel	male	Regents Professor	$274,000
Banks, Angela	female	Professor	$255,250
Roberts, Lawrence	male	Professor of Practice	$250,000
Selmi, Michael	male	Professor	$225,000
Williamson, John	male	Professor of Practice	$220,000

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$165,294	$169,050	$170,696	14	0.30
Full Professor	female	$160,841	$162,996	$174,498	6	0.13
Associate Professor	male	$135,750	$138,000	$151,869	6	0.13
Associate Professor	female	$149,830	$156,460	$156,476	3	0.06
Associate Professor	uncoded	$ 93,876	$ 93,876	$ 93,876	1	0.02
Teaching Faculty	male	$ 60,000	$ 68,000	$192,600	9	0.19
Teaching Faculty	female	$ 67,250	$ 68,000	$ 87,500	6	0.13
Teaching Faculty	uncoded	$ 75,000	$ 75,000	$ 75,000	1	0.02
Researcher	male	$ 45,000	$ 45,000	$ 45,000	1	0.02

English

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Bate, Andrew	male	Professor	$250,000
Diaz, Natalie	female	Assoc Professor	$210,200
Justice, George	male	Professor	$186,000
Bjork, Robert	male	Professor	$163,750
Looser, Devoney	female	Professor	$160,387

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$105,893	$116,259	$138,985	19	0.13
Full Professor	female	$111,050	$122,425	$130,020	13	0.09
Associate Professor	male	$ 92,994	$ 93,820	$ 95,142	11	0.07
Associate Professor	female	$ 88,408	$ 95,862	$ 97,316	9	0.06
Assistant Professor	male	$ 78,900	$ 79,500	$ 80,000	5	0.03
Assistant Professor	female	$ 80,046	$ 81,246	$ 82,131	8	0.05
Assistant Professor	uncoded	$102,000	$102,000	$102,000	1	0.01
Teaching Faculty	male	$ 49,000	$ 52,100	$ 52,600	32	0.21
Teaching Faculty	female	$ 49,000	$ 52,600	$ 52,600	46	0.31
Teaching Faculty	uncoded	$ 49,000	$ 51,600	$ 52,600	5	0.03

Hugh Downs School Of Comm

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Lederman, Linda	female	Professor	$220,000
Tracy, Sarah	female	Professor	$135,670
Corman, Steven	male	Professor	$130,500
Alberts, Janet	female	President’s Professor	$129,300
Roberto, Anthony	male	Professor	$119,450

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$115,870	$119,450	$124,975	3	0.06
Full Professor	female	$111,118	$120,955	$134,078	6	0.11
Associate Professor	male	$ 95,050	$ 97,700	$ 98,185	3	0.06
Associate Professor	female	$100,600	$100,600	$100,600	1	0.02
Associate Professor	uncoded	$ 89,907	$ 89,978	$ 90,048	2	0.04
Assistant Professor	male	$ 74,500	$ 74,500	$ 74,500	1	0.02
Assistant Professor	female	$ 75,350	$ 76,700	$ 78,350	3	0.06
Assistant Professor	uncoded	$ 77,300	$ 77,300	$ 77,300	1	0.02
Teaching Faculty	male	$ 45,000	$ 47,050	$ 47,190	13	0.24
Teaching Faculty	female	$ 37,730	$ 45,600	$ 47,190	20	0.37
Teaching Faculty	uncoded	$ 46,200	$ 46,200	$ 46,200	1	0.02

Humanities Arts & Cultural

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Pagan, Eduardo	male	Assoc Professor	$114,900
Hanlon, Christopher	male	Professor	$105,275
Guzzetti, Barbara	female	Professor	$101,607
Kim, Marianne	female	Professor	$100,276
Fahs, Breanne	female	Professor	$ 99,962

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$65,161	$83,974	$100,417	4	0.08
Full Professor	female	$97,540	$99,556	$100,198	6	0.12
Associate Professor	male	$88,016	$88,335	$ 91,288	8	0.15
Associate Professor	female	$85,325	$86,620	$ 88,704	10	0.19
Assistant Professor	male	$75,830	$75,830	$ 75,830	1	0.02
Assistant Professor	female	$75,750	$75,750	$ 75,750	1	0.02
Teaching Faculty	male	$48,300	$48,470	$ 58,200	5	0.10
Teaching Faculty	female	$46,150	$47,750	$ 48,685	15	0.29
Teaching Faculty	uncoded	$48,338	$50,546	$ 52,753	2	0.04

Journalism & Mass Comm

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Misner, John	male	Professor of Practice (FSC)	$196,223
Beelman, Maud	female	Professor of Practice (FSC)	$185,000
Cohen, Sarah	female	Professor	$157,579
Wallace, Julia	female	Professor of Practice	$156,259
Downie, Leonard	male	Professor of Practice	$155,448

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$ 65,760	$ 68,050	$ 79,391	3	0.07
Full Professor	female	$157,579	$157,579	$157,579	1	0.02
Associate Professor	male	$ 70,154	$ 70,963	$ 75,479	3	0.07
Associate Professor	female	$ 74,789	$ 80,611	$ 88,440	6	0.14
Associate Professor	uncoded	$ 89,635	$ 89,635	$ 89,635	1	0.02
Assistant Professor	male	$ 69,216	$ 70,122	$ 71,027	2	0.05
Assistant Professor	female	$ 67,591	$ 67,591	$ 67,591	1	0.02
Teaching Faculty	male	$ 92,362	$105,816	$139,440	12	0.27
Teaching Faculty	female	$104,105	$115,591	$143,440	15	0.34

Ldrshp and Integrative Studies

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Akpan, Patience	female	Assoc Professor	$89,000
Bates, Denise	female	Asst Professor	$73,429
Giron, Angela	female	Clinical Asst Professor (FSC)	$71,722
Castillo, Elizabeth	female	Asst Professor	$70,749
Trinh, Mai	female	Asst Professor	$70,740

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Associate Professor	male	$43,985	$43,985	$43,985	1	0.03
Associate Professor	female	$89,000	$89,000	$89,000	1	0.03
Assistant Professor	male	$70,653	$70,653	$70,653	1	0.03
Assistant Professor	female	$70,744	$70,749	$72,089	3	0.08
Teaching Faculty	male	$48,524	$49,623	$53,370	16	0.42
Teaching Faculty	female	$48,839	$50,796	$54,494	14	0.37
Teaching Faculty	uncoded	$47,080	$47,159	$47,238	2	0.05

Math & Natural Sciences Div

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Dietrich, Suzanne	female	Professor	$127,995
Camacho, Erika	female	Professor	$121,440
Kanthaswamy, Sreetharan	uncoded	Professor	$117,645
Sullivan, Brian	male	Professor	$111,420
Marshall, Pamela	female	Professor	$107,234

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$ 91,243	$104,397	$105,975	5	0.08
Full Professor	female	$114,337	$121,440	$124,718	3	0.05
Full Professor	uncoded	$100,774	$106,398	$112,022	2	0.03
Associate Professor	male	$ 89,577	$ 90,402	$ 91,915	5	0.08
Associate Professor	female	$ 95,773	$ 97,358	$ 98,546	4	0.06
Associate Professor	uncoded	$100,166	$100,166	$100,166	1	0.02
Assistant Professor	male	$ 86,750	$ 87,000	$ 88,077	4	0.06
Assistant Professor	female	$ 88,000	$ 90,000	$ 91,599	5	0.08
Assistant Professor	uncoded	$ 89,062	$ 91,125	$ 93,188	2	0.03
Teaching Faculty	male	$ 45,000	$ 47,275	$ 55,250	12	0.19
Teaching Faculty	female	$ 45,000	$ 47,450	$ 53,322	16	0.26
Teaching Faculty	uncoded	$ 57,684	$ 57,684	$ 57,684	1	0.02
Researcher	male	$ 62,600	$ 62,600	$ 62,600	1	0.02
Researcher	uncoded	$ 60,000	$ 60,000	$ 60,000	1	0.02

MDT Music

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Marshall, Kimberly	female	Professor	$121,288
Roumain, Daniel	male	Professor of Practice, MY	$121,185
Spring, Robert	male	Professor	$115,305
Meyer, Jeffery	male	Assoc Professor	$112,325
DeMaris, Brian	male	Assoc Professor	$109,184

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$87,016	$92,271	$ 94,935	13	0.20
Full Professor	female	$87,690	$92,661	$ 94,540	7	0.11
Full Professor	uncoded	$91,886	$91,886	$ 91,886	1	0.02
Associate Professor	male	$84,210	$91,956	$102,092	7	0.11
Associate Professor	female	$73,313	$76,250	$ 77,679	6	0.09
Assistant Professor	male	$63,254	$65,072	$ 72,190	11	0.17
Assistant Professor	female	$63,145	$64,666	$ 70,575	6	0.09
Teaching Faculty	male	$33,476	$46,718	$ 71,092	10	0.15
Teaching Faculty	female	$44,742	$57,362	$ 69,239	4	0.06

Physics Department

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Ritchie, Barry	male	Professor	$233,201
Nemanich, Robert	male	Regents Professor	$210,580
Smith, David	male	Regents Professor	$184,222
Spence, John	male	Regents Professor	$184,200
Liu, Jingyue	uncoded	Professor	$180,825

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$116,544	$134,000	$175,535	18	0.26
Full Professor	female	$112,269	$112,880	$113,490	2	0.03
Full Professor	uncoded	$104,376	$118,932	$149,878	3	0.04
Associate Professor	male	$108,413	$111,662	$114,505	8	0.11
Associate Professor	female	$105,700	$105,700	$105,700	1	0.01
Assistant Professor	male	$ 92,000	$ 92,500	$ 92,800	5	0.07
Assistant Professor	female	$ 93,500	$ 93,500	$ 93,650	3	0.04
Teaching Faculty	male	$ 28,000	$ 28,000	$ 28,000	1	0.01
Teaching Faculty	female	$ 58,200	$ 58,200	$ 58,200	1	0.01
Researcher	male	$ 49,607	$ 51,670	$ 66,650	14	0.20
Researcher	female	$ 47,957	$ 50,450	$ 51,563	6	0.09
Researcher	uncoded	$ 47,476	$ 49,700	$ 51,498	8	0.11

Psychology

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
McNamara, Danielle	female	Professor	$227,000
Chassin, Laurie	female	Regents Professor	$226,418
Mackinnon, David	male	Professor	$177,750
Kenrick, Douglas	male	President’s Professor	$176,765
Goldinger, Stephen	male	Professor	$175,575

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$121,920	$133,778	$164,629	14	0.18
Full Professor	female	$122,167	$151,298	$184,948	8	0.10
Full Professor	uncoded	$116,114	$118,250	$120,386	2	0.03
Associate Professor	male	$ 98,000	$106,250	$112,619	9	0.12
Associate Professor	female	$108,367	$113,215	$121,520	5	0.06
Associate Professor	uncoded	$111,780	$111,780	$111,780	1	0.01
Assistant Professor	female	$ 92,000	$ 92,750	$ 93,875	6	0.08
Assistant Professor	uncoded	$ 92,000	$ 92,000	$ 92,000	1	0.01
Teaching Faculty	male	$ 80,702	$ 85,175	$ 88,888	4	0.05
Teaching Faculty	female	$ 39,131	$ 52,000	$ 61,322	4	0.05
Teaching Faculty	uncoded	$ 35,971	$ 43,648	$ 51,324	2	0.03
Researcher	male	$ 56,352	$ 60,000	$ 78,998	3	0.04
Researcher	female	$ 50,004	$ 50,760	$ 62,000	17	0.22
Researcher	uncoded	$ 90,534	$108,289	$126,044	2	0.03

Sch Biological & Hlth Sys Engr

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Kleim, Jeffrey	male	Assoc Professor	$159,301
Tyler, William	male	Assoc Professor	$148,600
Lockhart, Thurmon	male	Professor	$135,000
Stabenfeldt, Sarah	female	Assoc Professor	$125,833
Sadleir, Rosalind	female	Assoc Professor	$124,428

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$135,000	$135,000	$135,000	1	0.02
Associate Professor	male	$107,706	$117,972	$121,982	11	0.26
Associate Professor	female	$124,058	$124,428	$125,130	3	0.07
Associate Professor	uncoded	$111,557	$111,557	$111,557	1	0.02
Assistant Professor	male	$ 97,250	$ 98,000	$103,692	4	0.10
Assistant Professor	female	$100,365	$102,126	$103,617	4	0.10
Assistant Professor	uncoded	$ 97,000	$ 98,000	$ 98,000	3	0.07
Teaching Faculty	male	$ 72,878	$ 74,357	$ 75,836	2	0.05
Teaching Faculty	female	$ 73,185	$ 73,185	$ 73,185	1	0.02
Researcher	male	$ 49,885	$ 50,000	$ 52,500	5	0.12
Researcher	female	$ 54,500	$ 55,000	$ 68,700	3	0.07
Researcher	uncoded	$ 50,003	$ 50,502	$ 51,770	4	0.10

Sch Compt Infor & Dec Sys Engr

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Panchanathan, Sethuraman	uncoded	Professor	$365,000
VanLehn, Kurt	male	Professor	$240,565
Kambhampati, Subbarao	uncoded	Professor	$224,719
Liu, Huan	male	Professor	$211,536
Mirchandani, Pitu	uncoded	Professor	$206,710

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$146,668	$176,501	$195,980	10	0.11
Full Professor	female	$144,750	$147,500	$150,250	2	0.02
Full Professor	uncoded	$156,918	$177,231	$200,075	11	0.12
Associate Professor	male	$108,716	$126,500	$130,815	8	0.09
Associate Professor	female	$104,035	$111,735	$114,165	3	0.03
Associate Professor	uncoded	$106,760	$115,127	$121,603	6	0.07
Assistant Professor	male	$101,450	$104,400	$109,750	11	0.12
Assistant Professor	female	$102,750	$105,500	$107,750	3	0.03
Assistant Professor	uncoded	$106,875	$112,500	$113,625	6	0.07
Teaching Faculty	male	$ 79,552	$ 85,000	$ 89,446	9	0.10
Teaching Faculty	female	$ 54,375	$ 82,500	$ 90,699	7	0.08
Teaching Faculty	uncoded	$ 94,966	$ 98,506	$ 99,805	4	0.05
Researcher	male	$ 80,107	$ 97,587	$121,669	6	0.07
Researcher	female	$ 70,886	$ 71,771	$ 72,656	2	0.02

Sch Elect Comptr & Energy Engr

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Vittal, Vijay	male	Regents Professor	$298,000
Lai, Ying-Cheng	uncoded	Professor	$270,200
Kiaei, Sayfe	uncoded	Professor	$264,880
Meldrum, Deirdre	female	Professor	$235,250
Balanis, Constantine	male	Regents Professor	$221,879

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$125,870	$160,888	$172,700	17	0.17
Full Professor	female	$154,620	$160,298	$177,500	8	0.08
Full Professor	uncoded	$143,667	$171,328	$202,000	10	0.10
Associate Professor	male	$116,660	$119,340	$126,580	9	0.09
Associate Professor	female	$116,378	$118,065	$120,885	4	0.04
Associate Professor	uncoded	$107,900	$107,959	$112,570	3	0.03
Assistant Professor	male	$ 98,000	$103,000	$105,000	11	0.11
Assistant Professor	female	$108,500	$108,500	$108,500	1	0.01
Assistant Professor	uncoded	$ 99,375	$102,750	$105,375	6	0.06
Teaching Faculty	male	$ 75,500	$ 77,000	$ 78,750	3	0.03
Teaching Faculty	female	$ 80,000	$ 80,000	$ 80,000	1	0.01
Researcher	male	$ 50,750	$ 65,000	$ 70,000	20	0.20
Researcher	uncoded	$ 53,500	$ 55,000	$ 62,960	7	0.07

Sch Engr Matter Trnsprt Energy

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Chattopadhyay, Aditi	female	Regents Professor	$292,157
Dahm, Werner	male	Professor	$248,748
Lin, Jerry	male	Regents Professor	$218,200
Jannesari Ladani, Leila	female	Professor	$185,000
Rege, Kaushal	male	Professor	$165,000

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$143,412	$151,324	$160,003	18	0.16
Full Professor	female	$211,789	$238,578	$265,368	2	0.02
Full Professor	uncoded	$134,802	$147,042	$156,154	4	0.04
Associate Professor	male	$111,040	$116,990	$124,088	11	0.10
Associate Professor	female	$112,709	$116,429	$119,550	5	0.04
Associate Professor	uncoded	$104,658	$116,033	$121,064	8	0.07
Assistant Professor	male	$ 97,500	$ 99,500	$100,500	9	0.08
Assistant Professor	female	$102,190	$103,380	$104,190	3	0.03
Assistant Professor	uncoded	$ 96,625	$ 98,000	$101,250	10	0.09
Teaching Faculty	male	$ 22,000	$ 80,000	$ 84,000	9	0.08
Teaching Faculty	uncoded	$ 74,750	$ 76,000	$ 77,250	2	0.02
Researcher	male	$ 45,000	$ 48,925	$ 52,500	17	0.15
Researcher	female	$ 50,172	$ 51,443	$ 55,722	3	0.03
Researcher	uncoded	$ 35,607	$ 45,000	$ 48,107	12	0.11

Sch Future of Innov in Society

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Cook-Deegan, Robert	male	Professor	$204,480
Barab, Sasha	female	Professor	$199,896
Michael, Katina	female	Professor	$179,725
Martin, Paul	male	Research Professional FSC	$169,538
Mayes, Kristin	female	Professor of Practice (FSC)	$162,742

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$155,287	$155,969	$180,224	3	0.07
Full Professor	female	$184,768	$189,810	$194,853	2	0.04
Associate Professor	male	$ 95,728	$102,467	$108,301	3	0.07
Associate Professor	female	$ 86,142	$ 96,800	$100,920	3	0.07
Associate Professor	uncoded	$113,874	$113,874	$113,874	1	0.02
Assistant Professor	male	$ 94,015	$ 94,264	$ 94,512	2	0.04
Assistant Professor	female	$ 75,655	$ 86,355	$ 92,880	8	0.18
Assistant Professor	uncoded	$ 92,700	$ 92,700	$ 92,700	1	0.02
Teaching Faculty	male	$ 52,148	$ 58,878	$ 82,310	4	0.09
Teaching Faculty	female	$ 71,708	$103,138	$158,386	7	0.16
Researcher	male	$ 46,150	$ 50,000	$ 94,889	7	0.16
Researcher	female	$ 49,325	$ 58,242	$ 70,998	4	0.09

Sch Sustain Engr & Built Envrn

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Kavazanjian, Edward	male	Regents Professor	$260,500
Westerhoff, Paul	male	Regents Professor	$255,300
Hjelmstad, Keith	male	President’s Professor	$253,100
Allenby, Braden	male	President’s Professor	$243,400
Lackner, Klaus	male	Professor	$228,900

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$138,620	$195,798	$245,825	12	0.16
Full Professor	uncoded	$140,527	$144,645	$147,469	4	0.05
Associate Professor	male	$107,332	$112,300	$125,400	11	0.15
Associate Professor	female	$108,925	$111,650	$116,075	3	0.04
Associate Professor	uncoded	$110,375	$111,350	$112,145	4	0.05
Assistant Professor	male	$ 96,600	$ 99,100	$101,500	5	0.07
Assistant Professor	female	$ 97,900	$ 97,900	$ 99,350	3	0.04
Assistant Professor	uncoded	$ 97,000	$ 97,400	$ 99,350	4	0.05
Teaching Faculty	male	$ 76,425	$ 80,750	$ 87,100	4	0.05
Teaching Faculty	female	$ 39,500	$ 39,500	$ 39,500	1	0.01
Teaching Faculty	uncoded	$ 79,400	$ 79,400	$ 79,400	1	0.01
Researcher	male	$ 41,130	$ 60,000	$ 70,395	10	0.14
Researcher	female	$ 55,000	$ 66,250	$ 76,534	4	0.05
Researcher	uncoded	$ 48,750	$ 60,300	$ 63,250	8	0.11

School Of Art

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Klett, Mark	male	Regents Professor	$146,336
Weiser, Kurt	male	Regents Professor	$140,243
Lawson, Shawn	male	Assoc Professor	$118,000
Codell, Julie	female	Professor	$113,462
Neubauer, Mary	female	President’s Professor	$110,523

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$87,681	$90,912	$106,227	9	0.18
Full Professor	female	$89,168	$91,731	$ 99,997	11	0.22
Associate Professor	male	$76,732	$77,820	$ 97,910	3	0.06
Associate Professor	female	$74,898	$81,018	$ 85,000	9	0.18
Assistant Professor	male	$64,000	$64,000	$ 64,000	1	0.02
Assistant Professor	female	$64,150	$65,133	$ 66,155	5	0.10
Assistant Professor	uncoded	$64,500	$64,500	$ 64,500	1	0.02
Teaching Faculty	male	$46,925	$47,950	$ 48,975	2	0.04
Teaching Faculty	female	$44,850	$45,900	$ 59,842	10	0.20

School of Criminology & Crim J

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Spohn, Cassia	female	Regents Professor	$226,000
White, Michael	male	Professor	$173,538
Maguire, Edward	male	Professor	$163,500
Hepburn, John	male	Professor	$143,213
Reisig, Michael	male	Professor	$142,300

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$142,985	$153,356	$166,010	4	0.11
Full Professor	female	$145,251	$172,168	$199,084	2	0.05
Associate Professor	male	$100,688	$101,938	$103,753	4	0.11
Associate Professor	female	$100,148	$101,000	$101,250	5	0.13
Associate Professor	uncoded	$110,000	$110,000	$110,000	1	0.03
Assistant Professor	male	$ 84,050	$ 84,100	$ 84,150	2	0.05
Assistant Professor	female	$ 83,750	$ 84,100	$ 84,400	4	0.11
Teaching Faculty	male	$ 48,000	$ 51,000	$ 58,250	11	0.29
Teaching Faculty	female	$ 53,000	$ 53,000	$ 54,000	5	0.13

School Of Earth & Space Explor

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Bell, James	male	Professor	$222,400
Christensen, Philip	male	Regents Professor	$216,050
Windhorst, Rogier	uncoded	Regents Professor	$189,950
Anbar, Ariel	female	President’s Professor	$189,800
Timmes, Francis	male	Professor	$188,705

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$136,306	$146,531	$168,300	19	0.19
Full Professor	female	$189,800	$189,800	$189,800	1	0.01
Full Professor	uncoded	$155,527	$167,002	$178,476	2	0.02
Associate Professor	male	$112,612	$113,100	$120,050	3	0.03
Associate Professor	female	$114,156	$119,050	$121,250	5	0.05
Associate Professor	uncoded	$127,966	$129,183	$130,400	2	0.02
Assistant Professor	male	$ 92,000	$ 96,000	$ 98,200	5	0.05
Assistant Professor	female	$ 92,000	$ 93,500	$ 95,750	4	0.04
Assistant Professor	uncoded	$ 96,000	$ 96,000	$ 97,000	3	0.03
Teaching Faculty	female	$ 45,000	$ 45,000	$ 45,000	1	0.01
Researcher	male	$ 54,096	$ 63,500	$ 73,225	34	0.34
Researcher	female	$ 56,324	$ 65,000	$ 70,232	15	0.15
Researcher	uncoded	$ 60,000	$ 60,000	$ 75,196	5	0.05

School of Geog Sci & Urban Pln

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Fotheringham, Stewart	male	Regents Professor	$333,200
Turner, Billie	female	Regents Professor	$221,647
Sailor, David	male	Professor	$141,453
Cerveny, Randall	male	President’s Professor	$132,462
Dorn, Ronald	male	Professor	$124,288

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$115,722	$119,964	$130,418	10	0.22
Full Professor	female	$100,572	$140,930	$181,288	2	0.04
Associate Professor	male	$ 98,246	$101,605	$106,640	3	0.07
Associate Professor	female	$ 97,998	$101,527	$112,264	3	0.07
Associate Professor	uncoded	$102,156	$102,938	$103,720	2	0.04
Assistant Professor	male	$ 84,500	$ 85,308	$ 86,211	4	0.09
Assistant Professor	female	$ 85,526	$ 86,000	$ 87,750	3	0.07
Assistant Professor	uncoded	$ 85,000	$ 85,000	$ 85,000	1	0.02
Teaching Faculty	male	$ 55,000	$ 55,000	$ 57,752	3	0.07
Teaching Faculty	female	$ 60,547	$ 60,547	$ 60,547	1	0.02
Teaching Faculty	uncoded	$ 49,479	$ 49,479	$ 49,479	1	0.02
Researcher	male	$ 45,019	$ 52,500	$ 60,000	4	0.09
Researcher	female	$ 37,017	$ 40,128	$ 45,540	4	0.09
Researcher	uncoded	$ 50,000	$ 50,000	$ 50,000	5	0.11

School of Math & Stat Sciences

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Mahalov, Alex	male	Professor	$224,020
McCulloch, Robert	male	Professor	$212,170
Renaut, Rosemary	female	Professor	$174,005
Gumel, Abba	male	Professor	$167,945
Carlson, Marilyn	female	Professor	$164,207

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$125,180	$136,726	$153,320	19	0.19
Full Professor	female	$144,838	$164,207	$169,106	3	0.03
Full Professor	uncoded	$132,695	$132,695	$132,695	1	0.01
Associate Professor	male	$ 96,670	$104,980	$110,148	15	0.15
Associate Professor	female	$ 93,844	$ 97,091	$ 98,876	4	0.04
Associate Professor	uncoded	$ 99,722	$104,744	$108,216	3	0.03
Assistant Professor	male	$ 92,781	$101,600	$105,000	5	0.05
Assistant Professor	female	$105,000	$105,000	$105,000	1	0.01
Assistant Professor	uncoded	$ 92,500	$ 95,000	$ 97,500	3	0.03
Teaching Faculty	male	$ 50,470	$ 59,955	$ 60,444	17	0.17
Teaching Faculty	female	$ 55,000	$ 57,390	$ 61,038	9	0.09
Teaching Faculty	uncoded	$ 55,000	$ 57,658	$ 65,626	8	0.08
Researcher	male	$ 53,250	$ 54,000	$ 55,114	7	0.07
Researcher	female	$ 66,882	$ 80,064	$ 93,245	2	0.02
Researcher	uncoded	$ 54,000	$ 54,000	$ 54,000	1	0.01

School of Molecular Sciences

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Navrotsky, Alexandra	female	Professor	$240,000
Fromme, Petra	female	Regents Professor	$226,197
Angell, Charles	male	Regents Professor	$191,976
Moore, Thomas	male	Regents Professor	$184,096
Yarger, Jeffery	male	Professor	$176,161

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$125,521	$135,675	$149,260	17	0.19
Full Professor	female	$142,128	$159,551	$226,197	5	0.05
Full Professor	uncoded	$127,221	$128,007	$134,869	3	0.03
Associate Professor	male	$103,056	$103,495	$105,099	5	0.05
Associate Professor	female	$101,409	$101,409	$101,409	1	0.01
Assistant Professor	male	$ 94,569	$ 95,524	$ 96,478	6	0.07
Assistant Professor	female	$ 93,000	$ 94,000	$ 94,856	3	0.03
Assistant Professor	uncoded	$ 96,478	$ 96,478	$ 96,478	1	0.01
Teaching Faculty	male	$ 46,430	$ 47,918	$ 48,700	6	0.07
Teaching Faculty	female	$ 47,425	$ 48,723	$ 56,010	11	0.12
Teaching Faculty	uncoded	$ 46,500	$ 47,999	$ 48,246	3	0.03
Researcher	male	$ 50,201	$ 55,977	$ 88,750	12	0.13
Researcher	female	$ 47,607	$ 50,680	$ 67,000	10	0.11
Researcher	uncoded	$ 39,244	$ 48,960	$ 54,428	8	0.09

School of Politics & Global St

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Hero, Rodney	male	Professor	$341,750
Polt, Michael	male	Professor of Practice (FSC)	$226,600
Thies, Cameron	male	Professor	$175,000
Hechter, Michael	male	Professor	$171,750
Bergen, Peter	male	Professor of Practice (FSC)	$157,500

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$112,700	$171,750	$175,000	5	0.14
Full Professor	female	$131,875	$139,000	$146,125	2	0.05
Associate Professor	male	$100,500	$101,750	$102,000	5	0.14
Associate Professor	female	$ 85,750	$ 96,000	$ 99,772	6	0.16
Assistant Professor	male	$ 85,000	$ 86,750	$ 99,125	4	0.11
Assistant Professor	female	$ 88,750	$ 92,000	$ 95,250	2	0.05
Assistant Professor	uncoded	$ 85,000	$ 85,000	$ 85,000	1	0.03
Teaching Faculty	male	$ 56,500	$119,500	$154,500	8	0.22
Teaching Faculty	female	$ 56,625	$ 58,250	$ 81,875	3	0.08
Researcher	female	$ 60,000	$ 60,000	$ 60,000	1	0.03

School Of Public Affairs

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Bozeman, Barry	male	Regents Professor	$236,900
Kapstein, Ethan	male	Professor	$227,500
Reilly, Thomas	male	Professor	$186,375
Corley, Elizabeth	female	Professor	$150,070
Feeney, Mary	female	Professor	$144,000

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$ 92,261	$186,375	$227,500	5	0.20
Full Professor	female	$145,518	$147,035	$148,552	2	0.08
Associate Professor	male	$102,820	$104,725	$113,488	4	0.16
Associate Professor	uncoded	$106,496	$106,496	$106,496	1	0.04
Assistant Professor	male	$ 92,150	$ 94,200	$ 94,600	3	0.12
Assistant Professor	female	$ 90,125	$ 92,250	$ 94,375	2	0.08
Assistant Professor	uncoded	$ 88,500	$ 88,500	$ 88,500	1	0.04
Teaching Faculty	male	$ 30,950	$ 40,300	$ 49,700	4	0.16
Teaching Faculty	female	$ 40,195	$ 49,000	$ 62,000	3	0.12

School of Social Transform

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Brayboy, Bryan	male	President’s Professor	$219,429
Scott, Kimberly	female	Professor	$180,000
Lomawaima, K	uncoded	Professor	$161,685
Moore, Elsie	female	Professor	$148,250
Gonzales, Angela	female	Assoc Professor	$143,200

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$154,309	$176,016	$197,722	2	0.04
Full Professor	female	$ 98,345	$109,370	$119,745	8	0.16
Full Professor	uncoded	$161,685	$161,685	$161,685	1	0.02
Associate Professor	male	$ 85,536	$ 90,000	$100,738	9	0.18
Associate Professor	female	$ 83,312	$ 92,394	$ 99,673	14	0.27
Associate Professor	uncoded	$100,673	$100,673	$100,673	1	0.02
Assistant Professor	male	$ 58,750	$ 67,500	$ 76,250	2	0.04
Assistant Professor	female	$ 85,000	$ 85,000	$ 85,000	5	0.10
Assistant Professor	uncoded	$ 85,000	$ 85,000	$ 85,000	1	0.02
Teaching Faculty	male	$ 53,460	$ 54,171	$ 54,882	2	0.04
Teaching Faculty	female	$ 39,538	$ 45,000	$ 52,422	3	0.06
Teaching Faculty	uncoded	$ 45,000	$ 45,000	$ 45,000	1	0.02
Researcher	female	$ 70,343	$ 70,343	$ 70,343	1	0.02
Researcher	uncoded	$ 42,500	$ 42,500	$ 42,500	1	0.02

School Of Social Work

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Messing, Jill	female	Professor	$160,000
Shafer, Michael	male	Professor	$137,401
Ashford, Jose	male	Professor	$131,845
Segal, Elizabeth	female	Professor	$130,390
Lecroy, Craig	male	Professor	$129,970

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$127,502	$130,908	$133,234	4	0.06
Full Professor	female	$123,725	$130,390	$145,195	3	0.05
Associate Professor	male	$ 91,649	$ 92,864	$ 94,078	2	0.03
Associate Professor	female	$ 90,194	$ 90,267	$ 91,528	5	0.08
Assistant Professor	male	$ 82,250	$ 83,500	$ 84,750	2	0.03
Assistant Professor	female	$ 83,000	$ 83,550	$ 83,750	10	0.16
Assistant Professor	uncoded	$ 82,425	$ 83,000	$ 84,700	4	0.06
Teaching Faculty	male	$ 35,725	$ 48,450	$ 49,800	3	0.05
Teaching Faculty	female	$ 48,200	$ 50,750	$ 53,710	26	0.41
Researcher	male	$ 60,000	$ 60,000	$ 60,000	1	0.02
Researcher	female	$ 51,885	$ 64,000	$ 66,250	4	0.06

SHPRS History Faculty

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Fixico, Donald	male	Regents Professor	$271,527
Austin, Curtis	male	Assoc Professor	$190,000
Alexander, Leslie	female	Assoc Professor	$190,000
Saikia, Yasmin	female	Professor	$181,750
Critchlow, Donald	male	Professor	$158,446

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$101,565	$130,000	$158,446	5	0.12
Full Professor	female	$130,808	$147,789	$164,770	2	0.05
Full Professor	uncoded	$135,206	$135,206	$135,206	1	0.02
Associate Professor	male	$108,000	$108,707	$122,268	5	0.12
Associate Professor	female	$ 75,612	$ 91,369	$104,841	7	0.17
Assistant Professor	male	$ 75,741	$ 76,732	$ 78,241	3	0.07
Assistant Professor	female	$ 77,506	$ 79,750	$ 79,875	3	0.07
Assistant Professor	uncoded	$ 82,494	$ 82,494	$ 82,494	1	0.02
Teaching Faculty	male	$ 50,575	$ 51,000	$ 67,667	9	0.21
Teaching Faculty	female	$ 49,429	$ 58,334	$ 67,959	4	0.10
Teaching Faculty	uncoded	$ 47,992	$ 47,992	$ 47,992	1	0.02
Researcher	female	$ 60,000	$ 60,000	$ 60,000	1	0.02

Social & Behavioral Sciences

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Mickelson, Kristin	female	Professor	$125,464
Kassing, Jeffrey	male	Professor	$118,412
Kirby, Andrew	male	Professor	$117,816
Nadesan, Majia	uncoded	Professor	$114,104
Waldron, Vincent	male	Professor	$108,184

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$103,368	$106,592	$115,408	6	0.09
Full Professor	female	$125,464	$125,464	$125,464	1	0.01
Full Professor	uncoded	$114,104	$114,104	$114,104	1	0.01
Associate Professor	male	$ 93,394	$ 97,660	$ 99,152	5	0.07
Associate Professor	female	$ 91,490	$ 93,801	$ 98,000	9	0.13
Assistant Professor	male	$ 83,562	$ 85,625	$ 87,438	4	0.06
Assistant Professor	female	$ 81,000	$ 82,987	$ 85,000	8	0.12
Assistant Professor	uncoded	$ 82,500	$ 82,500	$ 82,500	1	0.01
Teaching Faculty	male	$ 48,224	$ 54,000	$ 54,000	9	0.13
Teaching Faculty	female	$ 52,000	$ 54,000	$ 55,000	19	0.28
Teaching Faculty	uncoded	$ 54,000	$ 54,000	$ 54,000	1	0.01
Researcher	female	$ 48,750	$ 52,810	$ 56,715	4	0.06

Sols Administration & Faculty

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Grimm, Nancy	female	Regents Professor	$253,500
Compton, Carolyn	female	Professor	$241,600
Jacobs, Bertram	male	Professor	$202,800
Perrings, Charles	male	Professor	$188,538
Collins, James	male	Professor	$186,576

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$119,282	$131,002	$158,089	21	0.18
Full Professor	female	$123,004	$146,298	$158,500	11	0.09
Full Professor	uncoded	$ 97,221	$114,018	$130,814	2	0.02
Associate Professor	male	$ 98,827	$105,545	$123,339	10	0.09
Associate Professor	female	$102,720	$110,150	$118,748	4	0.03
Associate Professor	uncoded	$ 99,294	$102,819	$106,344	2	0.02
Assistant Professor	male	$ 90,550	$ 93,700	$ 96,850	2	0.02
Assistant Professor	female	$ 92,000	$ 94,000	$ 94,150	7	0.06
Assistant Professor	uncoded	$ 99,000	$ 99,000	$ 99,000	1	0.01
Teaching Faculty	male	$ 48,000	$ 48,000	$ 56,875	7	0.06
Teaching Faculty	female	$ 48,000	$ 48,000	$ 53,150	8	0.07
Researcher	male	$ 50,123	$ 52,000	$ 58,260	17	0.15
Researcher	female	$ 49,500	$ 51,638	$ 64,250	16	0.14
Researcher	uncoded	$ 47,494	$ 50,678	$ 55,414	8	0.07

SOS Faculty & Researchers

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Pfirman, Stephanie	female	Professor	$255,000
Melnick, Robert	male	Research Scientist	$249,765
Basile, George	male	Professor of Practice (FSC)	$168,913
Childers, Daniel	male	Professor	$145,466
Aggarwal, Rimjhim	uncoded	Assoc Professor	$143,500

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$ 88,528	$110,980	$131,516	4	0.08
Full Professor	female	$123,124	$126,249	$190,624	3	0.06
Full Professor	uncoded	$118,827	$118,827	$118,827	1	0.02
Associate Professor	male	$ 97,101	$ 97,515	$ 97,929	2	0.04
Associate Professor	female	$ 98,982	$ 99,813	$100,644	2	0.04
Associate Professor	uncoded	$143,500	$143,500	$143,500	1	0.02
Assistant Professor	male	$ 78,184	$ 89,251	$101,164	4	0.08
Assistant Professor	female	$ 87,116	$ 87,125	$102,562	3	0.06
Assistant Professor	uncoded	$ 87,333	$ 87,966	$ 88,600	2	0.04
Teaching Faculty	male	$ 46,250	$ 51,129	$ 59,771	10	0.20
Teaching Faculty	female	$ 38,655	$ 45,000	$ 45,000	11	0.22
Teaching Faculty	uncoded	$ 27,000	$ 50,000	$ 52,632	5	0.10
Researcher	male	$103,691	$152,382	$201,074	2	0.04

The Design School

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Jackson, Maria	female	Professor	$142,011
Underhill, Michael	male	Professor	$135,995
Brooks, Kenneth	male	Professor	$133,800
Petrucci, Darren	male	Professor	$132,762
Reddy, T Agami	uncoded	Professor	$128,056

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$106,867	$122,233	$133,281	7	0.14
Full Professor	female	$142,011	$142,011	$142,011	1	0.02
Full Professor	uncoded	$128,056	$128,056	$128,056	1	0.02
Associate Professor	male	$ 80,020	$ 81,763	$ 83,445	9	0.18
Associate Professor	female	$ 80,173	$ 91,695	$103,351	5	0.10
Associate Professor	uncoded	$ 82,032	$ 82,032	$ 82,032	1	0.02
Assistant Professor	male	$ 70,250	$ 70,500	$ 70,750	3	0.06
Assistant Professor	female	$ 70,700	$ 70,700	$ 70,700	1	0.02
Assistant Professor	uncoded	$ 70,500	$ 71,000	$ 71,375	3	0.06
Teaching Faculty	male	$ 43,212	$ 48,100	$ 61,722	8	0.16
Teaching Faculty	female	$ 32,236	$ 50,900	$ 66,225	10	0.20

The Sanford School

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Elliott, Stephen	male	Professor	$281,860
Sandefur, Rebecca	female	Professor	$220,000
Fabes, Richard	male	Professor	$190,000
Meek, Shantel	female	Professor of Practice (FSC)	$168,093
Ladd, Gary	male	Professor	$165,726

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$124,358	$158,364	$183,932	6	0.13
Full Professor	female	$122,326	$127,953	$132,502	7	0.15
Associate Professor	male	$ 98,500	$ 98,500	$ 98,500	1	0.02
Associate Professor	female	$ 99,132	$100,255	$116,712	8	0.17
Assistant Professor	male	$ 86,212	$ 86,775	$ 87,338	2	0.04
Assistant Professor	female	$ 85,529	$ 87,358	$ 88,800	6	0.13
Teaching Faculty	male	$ 24,814	$ 24,814	$ 24,814	1	0.02
Teaching Faculty	female	$ 82,609	$ 82,609	$ 88,433	5	0.11
Teaching Faculty	uncoded	$ 49,300	$ 49,300	$ 49,300	1	0.02
Researcher	male	$113,603	$113,603	$113,603	1	0.02
Researcher	female	$ 52,500	$ 52,500	$ 59,282	7	0.15
Researcher	uncoded	$ 53,375	$ 54,250	$ 55,125	2	0.04

WPC Accountancy

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Lamoreaux, Phillip	male	Assoc Professor	$323,113
Li, Yinghua	uncoded	Professor	$322,573
Matejka, Michal	female	Professor	$309,350
Reckers, Philip	male	Professor	$300,975
Kaplan, Steven	male	Professor	$297,109

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$248,620	$297,109	$299,042	3	0.08
Full Professor	female	$309,350	$309,350	$309,350	1	0.03
Full Professor	uncoded	$174,393	$223,786	$273,180	2	0.05
Associate Professor	male	$224,344	$262,454	$280,428	4	0.10
Associate Professor	female	$267,244	$274,394	$278,578	4	0.10
Associate Professor	uncoded	$265,220	$265,220	$265,220	1	0.03
Assistant Professor	male	$217,494	$219,475	$221,306	6	0.15
Assistant Professor	female	$215,475	$215,475	$215,475	1	0.03
Assistant Professor	uncoded	$225,000	$225,000	$225,000	1	0.03
Teaching Faculty	male	$ 88,676	$ 98,550	$129,500	8	0.21
Teaching Faculty	female	$ 96,612	$120,650	$143,750	8	0.21

WPC Economics

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Prescott, Edward	male	Regents Professor	$340,159
Manelli, Alejandro	male	Professor	$320,449
Silverman, Daniel	male	Professor	$310,840
Chade, Hector	male	Professor	$302,410
Mehra, Rajnish	uncoded	Professor	$296,743

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$178,508	$246,564	$302,410	13	0.30
Full Professor	female	$180,091	$180,091	$180,091	1	0.02
Full Professor	uncoded	$296,743	$296,743	$296,743	1	0.02
Associate Professor	male	$172,974	$183,753	$184,974	6	0.14
Associate Professor	female	$149,103	$153,830	$158,558	2	0.05
Associate Professor	uncoded	$107,984	$107,984	$107,984	1	0.02
Assistant Professor	male	$147,288	$154,000	$157,750	4	0.09
Assistant Professor	female	$147,433	$152,288	$157,144	2	0.05
Teaching Faculty	male	$ 93,993	$101,038	$104,520	8	0.19
Teaching Faculty	female	$102,700	$104,300	$105,800	4	0.09
Researcher	male	$111,706	$111,706	$111,706	1	0.02

WPC Information Systems

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Chen, Pei-yu	uncoded	Professor	$230,917
Zhang, Zhongju	uncoded	Professor	$224,029
Shao, Benjamin	male	Professor	$209,807
Shi, Zhan	uncoded	Assoc Professor	$200,867
Han, Sang Pil	male	Assoc Professor	$195,019

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$130,719	$157,082	$183,444	2	0.06
Full Professor	uncoded	$225,751	$227,473	$229,195	2	0.06
Associate Professor	male	$177,755	$183,510	$189,264	2	0.06
Associate Professor	uncoded	$178,106	$185,693	$193,280	2	0.06
Assistant Professor	male	$168,039	$168,039	$168,039	1	0.03
Assistant Professor	female	$168,151	$172,100	$176,050	2	0.06
Assistant Professor	uncoded	$180,000	$180,000	$180,000	1	0.03
Teaching Faculty	male	$ 84,549	$ 95,000	$120,000	13	0.36
Teaching Faculty	female	$ 75,056	$ 93,905	$124,146	4	0.11
Teaching Faculty	uncoded	$ 86,008	$100,000	$103,666	7	0.19

WPC Management

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
LePine, Jeffery	male	Professor	$402,257
Gomez-Mejia, Luis	male	Regents Professor	$361,393
Ashforth, Blake	male	Regents Professor	$338,580
Corley, Kevin	male	Professor	$282,000
Semadeni, Matthew	male	Professor	$273,267

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$219,152	$282,000	$349,986	7	0.17
Associate Professor	male	$195,430	$228,780	$232,799	8	0.20
Associate Professor	female	$144,591	$155,322	$168,114	4	0.10
Assistant Professor	female	$215,000	$215,000	$215,000	1	0.02
Assistant Professor	uncoded	$163,151	$163,151	$163,151	1	0.02
Teaching Faculty	male	$ 85,680	$ 97,549	$119,294	13	0.32
Teaching Faculty	female	$ 97,174	$103,807	$106,524	5	0.12
Teaching Faculty	uncoded	$122,520	$122,520	$122,520	1	0.02
Researcher	male	$ 47,208	$ 47,208	$ 47,208	1	0.02

WPC Supply Chain Management

TOP FIVE SALARIES

Full.Name	gender	Job.Description	salary
Choi, Thomas	male	Professor	$288,818
Carter, Craig	male	Professor	$263,000
Fowler, John	male	Professor	$256,139
Rabinovich, Elliot	male	Professor	$252,685
Li, Hongmin	uncoded	Professor	$250,000

PAY RANGE BY RANK AND GENDER

title	gender	q25	q50	q75	n	p
Full Professor	male	$217,774	$244,224	$256,139	9	0.30
Full Professor	uncoded	$250,000	$250,000	$250,000	1	0.03
Associate Professor	male	$183,522	$185,682	$187,841	2	0.07
Associate Professor	uncoded	$167,055	$178,720	$180,270	3	0.10
Assistant Professor	male	$154,050	$160,000	$165,000	3	0.10
Assistant Professor	female	$148,601	$148,601	$148,601	1	0.03
Teaching Faculty	male	$ 91,750	$ 98,512	$117,578	7	0.23
Teaching Faculty	female	$ 89,478	$ 90,457	$ 91,436	2	0.07
Teaching Faculty	uncoded	$103,104	$106,207	$109,310	2	0.07

Data Science for
Public Service

Labs designed by Jesse D. Lecy
Source code is available on GitHub

Creative Common License:
(CC BY-NC-SA 4.0)

CPP 527 Foundations of Data Science II
Part of the MS in Evaluation and Analytics
@ Arizona State University

DSII: Final Project Instructions

Overview

Your Objective

Project Components

A Focus on Workflow

Data Dependencies

Function Dependencies

File Dependencies

Breaking the Project Into Tasks

Setup

Required Packages

Project Files

Testing Your Setup

Part I

Step 1: Data

Step 2: Parse First Name

Step 3: Add Gender to the Dataset

Step 4: Standardize Job Titles

Step 5: Convert Salary to Numeric

Step 6: Convert All Salaries to Full-Time

Step 7: Select Sample

Step 8: Summarize Salaries by Rank and Gender

Step 9: Graph Results

Step 10 - Top Five Salaries

The utils.R File

Part II

All Departments in a Loop

Your functions-demo.rmd File

Part III

Big Picture

Step 1: Create a Generic Salary Report Template

Step 2: Customize Your CSS

Step 3: Create a Batch Processing Script

Helpful Hints

Data Types

Functions

Date Joins (Merging dfs)

Sorting Salaries

Submission Instructions

Deliverables

Grade Break-Down

Submission

Demo Report Sections

CISA-Intrdisp Hum & Comm

TOP FIVE SALARIES

PAY RANGE BY RANK AND GENDER

CISA-Science & Mathmatics

TOP FIVE SALARIES

PAY RANGE BY RANK AND GENDER

College of Health Solutions MS

TOP FIVE SALARIES

PAY RANGE BY RANK AND GENDER

College of Health Solutions NT

TOP FIVE SALARIES

PAY RANGE BY RANK AND GENDER

College of Health Solutions SH

TOP FIVE SALARIES

PAY RANGE BY RANK AND GENDER

College Of Law

TOP FIVE SALARIES

PAY RANGE BY RANK AND GENDER

English

TOP FIVE SALARIES

PAY RANGE BY RANK AND GENDER

Hugh Downs School Of Comm

TOP FIVE SALARIES

PAY RANGE BY RANK AND GENDER

Humanities Arts & Cultural

TOP FIVE SALARIES

PAY RANGE BY RANK AND GENDER

Journalism & Mass Comm

TOP FIVE SALARIES

PAY RANGE BY RANK AND GENDER

Ldrshp and Integrative Studies

TOP FIVE SALARIES

PAY RANGE BY RANK AND GENDER

Math & Natural Sciences Div

TOP FIVE SALARIES

PAY RANGE BY RANK AND GENDER

MDT Music