departures <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-04-27/departures.csv')
skimr::skim(departures)
Data summary
Name departures
Number of rows 9423
Number of columns 19
_______________________
Column type frequency:
character 8
numeric 10
POSIXct 1
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
coname 0 1.00 2 30 0 3860 0
exec_fullname 0 1.00 5 790 0 8701 0
interim_coceo 9105 0.03 6 7 0 6 0
still_there 7311 0.22 3 10 0 77 0
notes 1644 0.83 5 3117 0 7755 0
sources 1475 0.84 18 1843 0 7915 0
eight_ks 4499 0.52 69 3884 0 4914 0
_merge 0 1.00 11 11 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
dismissal_dataset_id 0 1.00 5684.10 25005.46 1 2305.5 4593 6812.5 559044 ▇▁▁▁▁
gvkey 0 1.00 40132.48 53921.34 1004 7337.0 14385 60900.5 328795 ▇▁▁▁▁
fyear 0 1.00 2007.74 8.19 1987 2000.0 2008 2016.0 2020 ▁▆▅▅▇
co_per_rol 0 1.00 25580.22 18202.38 -1 8555.5 22980 39275.5 64602 ▇▆▅▃▃
departure_code 1667 0.82 5.20 1.53 1 5.0 5 7.0 9 ▁▃▇▅▁
ceo_dismissal 1813 0.81 0.20 0.40 0 0.0 0 0.0 1 ▇▁▁▁▂
tenure_no_ceodb 0 1.00 1.03 0.17 0 1.0 1 1.0 3 ▁▇▁▁▁
max_tenure_ceodb 0 1.00 1.05 0.24 1 1.0 1 1.0 4 ▇▁▁▁▁
fyear_gone 1802 0.81 2006.64 13.63 1980 2000.0 2007 2013.0 2997 ▇▁▁▁▁
cik 245 0.97 741469.17 486551.43 1750 106413.0 857323 1050375.8 1808065 ▆▁▇▂▁

Variable type: POSIXct

skim_variable n_missing complete_rate min max median n_unique
leftofc 1802 0.81 1981-01-01 2998-04-27 2006-12-31 3627 
factors_vec <- departures %>% select(leftofc, departure_code, co_per_rol, fyear, coname, tenure_no_ceodb, max_tenure_ceodb, fyear_gone) %>% names()

data_clean <- departures %>%
    select(-c(interim_coceo, still_there, eight_ks, gvkey, co_per_rol, leftofc, cik, fyear)) %>%
    filter(fyear_gone != "2997") %>%
    filter(!is.na(ceo_dismissal))

Explore data

skimr::skim(departures)
Data summary
Name departures
Number of rows 9423
Number of columns 19
_______________________
Column type frequency:
character 8
numeric 10
POSIXct 1
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
coname 0 1.00 2 30 0 3860 0
exec_fullname 0 1.00 5 790 0 8701 0
interim_coceo 9105 0.03 6 7 0 6 0
still_there 7311 0.22 3 10 0 77 0
notes 1644 0.83 5 3117 0 7755 0
sources 1475 0.84 18 1843 0 7915 0
eight_ks 4499 0.52 69 3884 0 4914 0
_merge 0 1.00 11 11 0 1 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
dismissal_dataset_id 0 1.00 5684.10 25005.46 1 2305.5 4593 6812.5 559044 ▇▁▁▁▁
gvkey 0 1.00 40132.48 53921.34 1004 7337.0 14385 60900.5 328795 ▇▁▁▁▁
fyear 0 1.00 2007.74 8.19 1987 2000.0 2008 2016.0 2020 ▁▆▅▅▇
co_per_rol 0 1.00 25580.22 18202.38 -1 8555.5 22980 39275.5 64602 ▇▆▅▃▃
departure_code 1667 0.82 5.20 1.53 1 5.0 5 7.0 9 ▁▃▇▅▁
ceo_dismissal 1813 0.81 0.20 0.40 0 0.0 0 0.0 1 ▇▁▁▁▂
tenure_no_ceodb 0 1.00 1.03 0.17 0 1.0 1 1.0 3 ▁▇▁▁▁
max_tenure_ceodb 0 1.00 1.05 0.24 1 1.0 1 1.0 4 ▇▁▁▁▁
fyear_gone 1802 0.81 2006.64 13.63 1980 2000.0 2007 2013.0 2997 ▇▁▁▁▁
cik 245 0.97 741469.17 486551.43 1750 106413.0 857323 1050375.8 1808065 ▆▁▇▂▁

Variable type: POSIXct

skim_variable n_missing complete_rate min max median n_unique
leftofc 1802 0.81 1981-01-01 2998-04-27 2006-12-31 3627 
data_clean %>% count(ceo_dismissal)
## # A tibble: 2 × 2
##   ceo_dismissal     n
##           <dbl> <int>
## 1             0  5993
## 2             1  1484
data_clean %>%
    ggplot(aes(ceo_dismissal)) +
    geom_bar()

ceo_dismissal vs. departure_code

data_clean %>%
    ggplot(aes(departure_code)) +
    geom_boxplot()

correlation plot

# Step 1: binarize
data_binarized <- data_clean %>%
    select(-notes, -sources, -exec_fullname, -coname) %>%
    binarize()

data_binarized %>% glimpse
## Rows: 7,477
## Columns: 18
## $ `dismissal_dataset_id__-Inf_2176` <dbl> 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ dismissal_dataset_id__2176_4326   <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ dismissal_dataset_id__4326_6580   <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ dismissal_dataset_id__6580_Inf    <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `departure_code__-Inf_5`          <dbl> 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, …
## $ departure_code__5_Inf             <dbl> 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ ceo_dismissal__0                  <dbl> 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, …
## $ ceo_dismissal__1                  <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, …
## $ tenure_no_ceodb__1                <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ tenure_no_ceodb__2                <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `tenure_no_ceodb__-OTHER`         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ max_tenure_ceodb__1               <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ max_tenure_ceodb__2               <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `max_tenure_ceodb__-OTHER`        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `fyear_gone__-Inf_2000`           <dbl> 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 0, 0, …
## $ fyear_gone__2000_2006             <dbl> 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, …
## $ fyear_gone__2006_2013             <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ fyear_gone__2013_Inf              <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
# Step 2: correlation
data_correlation <- data_binarized %>%
    correlate(`departure_code__-Inf_5` )

data_correlation
## # A tibble: 18 × 3
##    feature              bin       correlation
##    <fct>                <chr>           <dbl>
##  1 departure_code       -Inf_5       1       
##  2 departure_code       5_Inf       -1       
##  3 ceo_dismissal        1            0.322   
##  4 ceo_dismissal        0           -0.322   
##  5 dismissal_dataset_id 4326_6580   -0.0496  
##  6 dismissal_dataset_id -Inf_2176    0.0460  
##  7 max_tenure_ceodb     2            0.0371  
##  8 max_tenure_ceodb     1           -0.0366  
##  9 fyear_gone           2000_2006    0.0300  
## 10 dismissal_dataset_id 2176_4326    0.0221  
## 11 dismissal_dataset_id 6580_Inf    -0.0185  
## 12 fyear_gone           2013_Inf    -0.0184  
## 13 fyear_gone           -Inf_2000   -0.0135  
## 14 tenure_no_ceodb      2           -0.00339 
## 15 tenure_no_ceodb      1            0.00320 
## 16 fyear_gone           2006_2013    0.00297 
## 17 max_tenure_ceodb     -OTHER       0.00193 
## 18 tenure_no_ceodb      -OTHER       0.000670
# Step 3: plot
data_correlation %>%
    correlationfunnel::plot_correlation_funnel()

There is a moderate correlation between departure codes and ceo dismissals so some departures codes are more indicative of ceo dismissals than others.