Wage Gender Gap
1. Histogram of Wage
The distribution of wages is right-skewed. Most individuals earn lower wages, while a small number earn very high wages, creating a long right tail.
2. Boxplot of Wage by Gender
The boxplot shows that men have a higher median wage than women. The spread of wages is also larger for men, with more high-value outliers.
3. Summary Statistics
Men mean: 125.13
Women mean: 97.33
The raw wage gap is 27.81 dollars.
4. Log Transformation
After applying the logarithm, the distribution becomes more symmetric and closer to a normal distribution. This reduces skewness.
5. Boxplot of Log Wage
The difference between men and women is still visible after the transformation, but the distributions are more balanced.
6. Percentage Gap
The approximate percentage wage gap is about 25%.
7. Education
Education levels are relatively similar between men and women, although small differences exist. These differences may partially explain the wage gap.
8. Part-time Work
Women have a higher proportion of part-time work. Since part-time jobs usually pay less, this contributes to the wage gap.
9. Age
The average and median ages of men and women are similar. Therefore, age does not fully explain the wage gap.
10. Why use log(wage)?
Log(wage) is used because it reduces skewness and allows wage differences to be interpreted in percentage terms.
11. Discrimination
The raw wage gap is not entirely due to discrimination. Factors such as education and part-time work explain part of the difference.
AI Use Log
I used ChatGPT to assist with writing R code, interpreting the results, and structuring the assignment. All analysis was performed and verified by me.