{"id":3339,"date":"2019-05-23T19:17:39","date_gmt":"2019-05-23T17:17:39","guid":{"rendered":"https:\/\/geekosas.com\/?p=3339"},"modified":"2026-05-23T19:18:37","modified_gmt":"2026-05-23T17:18:37","slug":"gender-pay-gap-in-technology","status":"publish","type":"post","link":"https:\/\/geekosas.com\/index.php\/2019\/05\/23\/gender-pay-gap-in-technology\/","title":{"rendered":"Gender Pay Gap in Technology"},"content":{"rendered":"\n

The Gender Pay Gap is the difference that exists on average in the salaries of Men vs. Women.<\/p>\n\n\n

Today there are people who attribute this to discrimination, while others say it is due to the decisions that men on average make versus those of women.<\/p>\n\n\n

Since both opinions have merit, I decided to conduct an analysis on some database that would allow me to reveal the reality. That’s when I came across the database from the survey that StackOverflow conducts every year. The interesting thing about it is that besides collecting gender and salary, it also collects many other attributes such as: favorite operating system, programming languages, years of experience, etc.<\/p>\n\n\n

The survey is answered by people in the technology field from all over the world and is conducted annually, but we will focus on the data from the year 2018 for the United States, where the individuals are employees (not independent), with annual salaries between USD 50,000 and USD 200,000. This is because it is where the most surveys were answered and where the majority of salaries are concentrated.<\/p>\n\n\n

In this analysis, I will only be guided by Advanced Analytics tools and interpret their results, but you, the readers, are free to debate the topic.<\/p>\n\n\n

Evidence of the Salary Gap<\/h2>\n\n\n

To begin, I will start by showing that there is indeed a difference in the average annual salaries of men and women:<\/p>\n\n

\naux = dataset %>%\n  group_by(Male) %>%\n  summarise(salario = mean(ConvertedSalary,na.rm=T),\n            number = n()) %>%\n  filter(!is.na(Male))\nggplot(aux,(aes(Male,salario))) + geom_bar(stat = 'identity', fill = 'dark orange') + ggtitle('Salario Promedio por Genero') + scale_fill_tableau() \n<\/pre><\/div>\n\n
\"\"<\/figure>\n\n\n
If we look at its distribution, we notice that women have a greater concentration in lower salaries:<\/p>\n\n
\nggplot(filter(dataset,!is.na(Male)),aes(ConvertedSalary,group = Male, fill = Male)) +\n  geom_density(alpha= 0.3,kernel = 'epanechnikov') +\n  ggtitle('Distribucion de Sueldo por Genero')  +\n  scale_fill_tableau() \n<\/pre><\/div>\n\n
\"\"<\/figure>\n\n\n
It is easier to see this effect if we look at the logarithm of salaries, where it is clear that women’s salaries are more to the left than men’s:<\/p>\n\n
\nggplot(filter(dataset,!is.na(Male)),aes(log10(ConvertedSalary),group = Male, fill = Male)) +\n  geom_density(alpha= 0.3,kernel='epanechnikov') +\n  ggtitle('Distribucion de Log Sueldo por Genero')  +\n  scale_fill_tableau() \n<\/pre><\/div>\n\n
\"\"<\/figure>\n\n\n
Finally, if we perform a one-tailed means test, it yields a p-value = 0, so it can be stated that the means are significantly different.<\/p>\n\n
\nt.test(ConvertedSalary ~ Male, filter(dataset,!is.na(Male)),alternative = 'less')\n<\/pre><\/div>\n\n
t.test(ConvertedSalary ~ Male, filter(dataset,!is.na(Male)),alternative = 'less')\n##\n##  Welch Two Sample t-test\n##\n## data:  ConvertedSalary by Male\n## t = -8.452, df = 917.2, p-value < 2.2e-16\n## alternative hypothesis: true difference in means is less than 0\n## 95 percent confidence interval:\n##       -Inf -7793.837\n## sample estimates:\n## mean in group FALSE  mean in group TRUE\n##            95684.52           105363.99<\/code><\/pre>\n\n\n
Analysis with Trees<\/h2>\n\n\n
To start, we will use Machine Learning to find the variables that best explain a programmer’s salary, to see if gender appears.<\/p>\n\n\n
We can see that the most important variables are:<\/p>\n\n\n