Subscribe to DSC Newsletter

Contributed by Wendy Yu. Wendy took NYC Data Science Academy 12 weeks boot camp program between Jan 11th to Apr 1st, 2016. The post was based on her second class project(due at 4th week of the program). 


This project utilizes publicly available data to visualize temporal trends of gender pay gap. According to the data from United States Census, full-time women workers’ earnings are only about 78 percent of their male counterparts’ earnings. Pay discrimination is a real and persistent problem that continues to shortchange American women and their families.

Immediately below, you will view a series of questions with each followed by several data visualizations.  Details on data and methodology are located at this blog post.  All data loading, manipulation, and visualization is performed using the R statistical software and the code is located at the end of this blog. 


Saleforce closing gender pay gap (nov. 2015):

- See more at:

Data exploration

Use the App below to explore changes of income and gender pay gap over the past 30 years, and see how different factors influence the pay gap.

How to use the App:

Select a factor you would like to explore, and click “Update View”.

Move mouse over to the bubbles to identify each group.

Click play button to view changes over time.

View bar chart/line chart by selecting tabs at upper right corner

Switch y-axis to “Difference_Income_Norm” to see different effects

All data are collected from United States Census Bureau.

Click on the image below to go to the published Shiny App.


From exploring the data above, here are some of my observations:

Over the years, the absolute differences in average income between men and women have increased. However, percent differences in average income between men and women have decreased. (To see these effects, select “Difference_Income” and “Difference_Income_Norm” at y-axis.)

In the 1970s, men made about 80% to 100% more than women. In 2014, men made about 20% more than women.

Gender pay gap has reduced for the past few decades but remain largely unchanged for the past five years.

Education Factor: pay gap for people with a master or doctoral degree is the lowest and remain unchanged for the past decades. There is a trend for reduction in pay gap for other education levels.

Race: We see a general decreasing trend for all races. In 2014, the pay gap was the largest for white and lowest for black. Men were paid about 52% and 28% more than women respectively.

Region: no difference in pay gap among different regions is observed.

Marital Status: pay gap is considerably larger for married ones than divorced or single. This could be explained by the traditional gender roles. In a marriage, a husband is expected to be the financial provider while a wife is expected to stay at home and provide domestic needs. Therefore, it makes sense to see a large gender pay gap for married couples.

Work Time: there is a reduction in pay gap for full-time employees. Interestingly, for part-time employees, female were paid about 0-20% more than male between 1980 to 2010. In 2014, gender pay gap was almost gone for part-time employees. This phenomenon can also be due to stereotypical gender roles. Part-time jobs offer more flexibility in the schedule so women can balance work and family more easily. On the other hand, very few full-time jobs offer the flexibility that women require to take care of her family, for example, to pick up kids or to go to doctor’s appointments. Women are penalized for taking time off and therefore hindering their career development.

Job Type: gender pay gap remains largely unchanged for all job types except for sales and armed forces. We see a decrease in pay gap for both sales and armed forces. Gender pay gap reached zero in 2000 for armed forces.

Overall, the good news is that gender pay gap has shrunk for the past few decades. However, the decrease in the pay gap has stopped for at least five years. To date, women are still making about 20% less then men. Gender pay gap is a continuous problem in the United States, we should first seek an understanding of stereotypical gender roles, we will then be in a better position to fix gender pay gap.

All data are collected from United States Census Bureau.

## Note: the specification for S3 class "AsIs" in package 'RJSONIO' seems equivalent to one from package 'jsonlite': not turning on duplicate class definitions for this class.

## ## Welcome to googleVis version 0.5.10##
## Please read the Google API Terms of Use
## before you start using the package:
## Note, the plot method of googleVis will by default use
## the standard browser to display its output.
## See the googleVis package vignettes for more details,
## or visit
## To suppress this message use:
## suppressPackageStartupMessages(library(googleVis))

Views: 1091


You need to be a member of Data Science Central to add comments!

Join Data Science Central

Comment by Bob Vanderheyden on April 17, 2016 at 4:38pm

I would like to see the analysis for STEM related professions vs non-STEM. For example, it's well documented that Engineering is still a very male dominated profession. It is also well documented that salaries for engineers are significantly higher than for other professions (except other STEM professions like computer programming, another male dominate profession).

I don't refute the existence of a gender pay gap, but it's impossible to fix the gap if you can't accurately measure it.

© 2019   Data Science Central ®   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service