Gender Pay Gap Analysis

Motivation

Problem

Since long ago there has been a difference in the wages man and women receive even in the same deparment or position. It is imperative to know how big this gap is right now and if beside once gender their age, job title or level of education have a significant impact in the disparity.

Solution

Glassdoor is the second largest job site in the U.S., following Indeed. It's a free digital platform that gathers information and reviews from employees or former employees about companies, salaries, and even job openings. Meaning that they have wide range of information in the dataset and it is updated in a yearly manner. The goal of this project is to identify which are the factors that with realation to gender have the greatest impact in the wage disparity and in what manner is it affected.

Impact

If we are able to create an accurate analysis of the disperities encounter in each job title. It will posible to identify and asses this issue in a different manner focusing on the new insight gain.

Dataset

Detail

We will use a Kaggle Dataset of Gender Pay Gap to odserve how does the following feuteres affect the gender pay gap:

• Job title
• Gender
• Age
• Performance Evaluation Score(PerfEval)
• Level of Education
• Department(Dept)
• No of years worked(Seniority)
• Annual Basic Pay(BasePay)
• Annual Bonus Pay

JobTitle	Gender	Age	PerfEval	Education	Dept	Seniority	BasePay	Bonus
Graphic Designer	Female	18	5	College	Operations	2	42363	9938
Software Engineer	Male	21	5	College	Management	5	108476	11128
Warehouse Associate	Female	19	4	PhD	Administration	5	90208	9268
Software Engineer	Male	20	5	Masters	Sales	4	108080	10154
Graphic Designer	Male	26	5	Masters	Engineering	5	99464	9319

import pandas as pd
df = pd.read_csv('glassdoor_gender_pay _gap.csv')
df

	JobTitle	Gender	Age	PerfEval	Education	Dept	Seniority	BasePay	Bonus
0	Graphic Designer	Female	18	5	College	Operations	2	42363	9938
1	Software Engineer	Male	21	5	College	Management	5	108476	11128
2	Warehouse Associate	Female	19	4	PhD	Administration	5	90208	9268
3	Software Engineer	Male	20	5	Masters	Sales	4	108080	10154
4	Graphic Designer	Male	26	5	Masters	Engineering	5	99464	9319
...	...	...	...	...	...	...	...	...	...
995	Marketing Associate	Female	61	1	High School	Administration	1	62644	3270
996	Data Scientist	Male	57	1	Masters	Sales	2	108977	3567
997	Financial Analyst	Male	48	1	High School	Operations	1	92347	2724
998	Financial Analyst	Male	65	2	High School	Administration	1	97376	2225
999	Financial Analyst	Male	60	1	PhD	Sales	2	123108	2244

1000 rows × 9 columns

Potential Problems

As this data comes from employees and employeers we may encounter some outliers when it comes to the basic pay. These outliers could just by one individual affect the size of the gap in a significant manner when it comes to certain job titles or departments.

Method:

We will first clean the data to get rid of the performance evaluation and bonus pay colums. Then look at the gender wage gap as a whole.Also, identify the top 5 jod titles and deparment in which the gap is bigger and smaller, and create a bar chart to visualize the gap. Utilize a scatter plot to show if there is any relation between education level and salary.