Solutions: Exercises 1–2

library(tidyverse)

students <- 42
weeks <- 12
course_name <- "Research Project Design"
mean(c(22, 25, 24, 29, 20))

[1] 24

employees <- read_csv("data/employee_survey.csv", show_col_types = FALSE)
dim(employees)

[1] 480  26

glimpse(employees)

Rows: 480
Columns: 26
$ employee_id            <chr> "E000001", "E000002", "E000003", "E000004", "E0…
$ age                    <dbl> 37, 32, 22, 44, 42, 41, 48, 23, 32, 25, 51, 39,…
$ gender                 <chr> "Man", "Man", "Man", "Woman", "Woman", "Woman",…
$ department             <chr> "Operations", "Operations", "Operations", "Tech…
$ remote_days            <dbl> 3, 3, 1, 1, 3, 0, 3, 0, 3, 4, 2, 0, 4, 1, 2, 2,…
$ tenure_years           <dbl> 9.2, 7.0, 0.7, 4.2, 7.4, 1.6, 1.6, 2.9, 10.0, 6…
$ manager                <chr> "No", "No", "No", "No", "No", "Yes", "No", "Yes…
$ training_group         <chr> "Training", "Training", "Control", "Training", …
$ leadership_1           <dbl> 1, 3, 5, 3, 3, 2, 3, 3, 5, 2, 4, 5, 1, 2, 1, 2,…
$ leadership_2           <dbl> 1, 1, 5, 2, 4, 3, 3, 4, 5, 1, 5, 5, 1, 1, 1, 2,…
$ leadership_3           <dbl> 1, 1, 5, 3, 5, 4, 4, 2, 5, 2, 5, 5, 1, 1, 2, 2,…
$ leadership_4_reverse   <dbl> 5, 5, 1, 4, 1, 3, 3, 4, 1, 5, 2, 1, 3, 4, 4, 3,…
$ engagement_1           <dbl> 2, 3, 5, 4, 5, 3, 5, 2, 5, 3, 4, 5, 3, 2, 4, 5,…
$ engagement_2           <dbl> 2, 1, 3, 5, 4, 4, 5, 1, 5, 2, 4, 5, 4, 2, 3, 1,…
$ engagement_3           <dbl> 1, 1, 4, 4, 4, 4, 5, 2, 5, 2, 5, 5, 4, 1, 3, 3,…
$ engagement_4_reverse   <dbl> 3, 4, 1, 2, 2, 4, 1, 3, 1, 5, 1, 1, 3, 5, 2, 2,…
$ role_clarity_1         <dbl> 1, 1, 4, 4, 5, 4, 3, 2, 3, 3, 5, 3, 2, 1, 1, 2,…
$ role_clarity_2         <dbl> 1, 3, 3, 5, 4, 4, 5, 3, 4, 2, 5, 5, 1, 1, 1, 1,…
$ role_clarity_3         <dbl> 1, 2, 3, 4, 4, 3, 4, 3, 5, 4, 5, 2, 2, 1, 1, 2,…
$ role_clarity_4         <dbl> 1, 4, 3, 3, 3, 2, 5, 5, 5, 3, 4, 4, 2, 1, 1, 3,…
$ workload               <dbl> 3.44, 4.68, 4.68, 4.09, 4.26, 2.25, 2.79, 4.16,…
$ organizational_support <dbl> 2.50, 3.92, 5.09, 3.72, 3.63, 3.97, 5.58, 4.25,…
$ job_satisfaction       <dbl> 2.52, 4.17, NA, 4.87, 3.17, 5.68, 4.86, 3.77, 5…
$ performance            <dbl> 45.1, 43.8, 52.2, 60.3, 59.9, NA, 64.3, 48.1, 6…
$ burnout                <dbl> 49.8, 48.5, 47.4, 47.1, 51.8, 36.3, 32.1, 46.6,…
$ turnover_intention     <dbl> 4.84, 4.18, 3.66, 4.12, 4.62, 2.83, 3.16, 5.26,…

employees |>
  count(department, sort = TRUE)

# A tibble: 5 × 2
  department     n
  <chr>      <int>
1 Operations   125
2 Technology   104
3 Marketing    100
4 Finance       97
5 HR            54

employees |>
  summarise(
    across(
      c(age, tenure_years, workload, performance),
      ~ mean(.x, na.rm = TRUE)
    )
  )

# A tibble: 1 × 4
    age tenure_years workload performance
  <dbl>        <dbl>    <dbl>       <dbl>
1  38.2         4.79     4.09        53.9

employees |>
  summarise(across(everything(), ~ sum(is.na(.x)))) |>
  pivot_longer(everything(), names_to = "variable", values_to = "missing")

# A tibble: 26 × 2
   variable       missing
   <chr>            <int>
 1 employee_id          0
 2 age                  0
 3 gender               0
 4 department           0
 5 remote_days          0
 6 tenure_years         0
 7 manager              0
 8 training_group       0
 9 leadership_1         0
10 leadership_2         8
# ℹ 16 more rows

employees_clean <- employees |>
  mutate(
    remote_mode = case_when(
      remote_days == 0 ~ "On-site",
      remote_days <= 3 ~ "Hybrid",
      TRUE ~ "Mostly remote"
    )
  )

employees_clean |>
  group_by(training_group) |>
  summarise(
    n = sum(!is.na(performance)),
    mean_performance = mean(performance, na.rm = TRUE),
    sd_performance = sd(performance, na.rm = TRUE)
  )

# A tibble: 2 × 4
  training_group     n mean_performance sd_performance
  <chr>          <int>            <dbl>          <dbl>
1 Control          217             52.0           8.78
2 Training         255             55.6           9.18

employees_clean |>
  ggplot(aes(x = performance)) +
  geom_histogram(bins = 25)

employees_clean |>
  ggplot(aes(x = training_group, y = performance)) +
  geom_boxplot()