Import data

# excel file
data <- read_excel("../00_data/Salaries.xlsx")
data
## # A tibble: 397 × 6
##    rank      discipline yrs.since.phd yrs.service sex    salary
##    <chr>     <chr>              <dbl>       <dbl> <chr>   <dbl>
##  1 Prof      B                     19          18 Male   139750
##  2 Prof      B                     20          16 Male   173200
##  3 AsstProf  B                      4           3 Male    79750
##  4 Prof      B                     45          39 Male   115000
##  5 Prof      B                     40          41 Male   141500
##  6 AssocProf B                      6           6 Male    97000
##  7 Prof      B                     30          23 Male   175000
##  8 Prof      B                     45          45 Male   147765
##  9 Prof      B                     21          20 Male   119250
## 10 Prof      B                     18          18 Female 129000
## # ℹ 387 more rows

State one question

Do male or female professors make more than one another

Plot data

names(data)
## [1] "rank"          "discipline"    "yrs.since.phd" "yrs.service"  
## [5] "sex"           "salary"
# Summarize average salary by sex
salary_summary <- data |>
  group_by(sex) |>
  summarise(
    mean_salary = mean(salary, na.rm = TRUE),
    sd_salary   = sd(salary, na.rm = TRUE),
    n           = n()
  )
salary_summary
## # A tibble: 2 × 4
##   sex    mean_salary sd_salary     n
##   <chr>        <dbl>     <dbl> <int>
## 1 Female     101002.    25952.    39
## 2 Male       115090.    30437.   358
# Boxplot comparing salary distributions
ggplot(data, aes(x = sex, y = salary, fill = sex)) +
  geom_boxplot(alpha = 0.7, outlier.color = "red") +
  labs(
    title = "Salary Comparison by Sex",
    x = "Sex",
    y = "Salary",
    caption = "Each box shows salary distribution for male vs female professors"
  ) +
  theme_minimal() +
  theme(legend.position = "none")

Interpret

basing from the data shown male teachers have a bit higher of a salary than female teachers.