Apply: 5 CEO Departures
Olivia Pendergast
2024-03-25
Goal is to predict CEO departure
Import Data
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.3 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(correlationfunnel)## Warning: package 'correlationfunnel' was built under R version 4.3.2## ══ correlationfunnel Tip #2 ════════════════════════════════════════════════════
## Clean your NA's prior to using `binarize()`.
## Missing values and cleaning data are critical to getting great correlations. :)departures <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-04-27/departures.csv')## Rows: 9423 Columns: 19
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (8): coname, exec_fullname, interim_coceo, still_there, notes, sources...
## dbl (10): dismissal_dataset_id, gvkey, fyear, co_per_rol, departure_code, c...
## dttm (1): leftofc
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.Clean Data
skimr::skim(departures)| 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( departure_code, tenure_no_ceodb, max_tenure_ceodb, ceo_dismissal) %>% names()
data_clean <- departures %>%
select(-interim_coceo, -still_there, -eight_ks, -notes, -sources, -leftofc) %>%
# remove NA's
na.omit() %>%
# address factors imported as numeric
mutate(across(all_of(factors_vec), as.factor)) %>%
# drop zero variance variable name
select(-c(`_merge`))Explore Data
data_clean %>% count(ceo_dismissal)## # A tibble: 2 × 2
## ceo_dismissal n
## <fct> <int>
## 1 0 5822
## 2 1 1439data_clean %>%
ggplot(aes(ceo_dismissal)) +
geom_bar()
fyear vs interim_coceo
data_clean %>%
ggplot(aes(ceo_dismissal, )) +
geom_boxplot()correlation plot
# step 1: binarize
data_binarized <- data_clean %>%
binarize()
data_binarized %>% glimpse()## Rows: 7,261
## Columns: 43
## $ `dismissal_dataset_id__-Inf_2159` <dbl> 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ dismissal_dataset_id__2159_4330 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ dismissal_dataset_id__4330_6564 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ dismissal_dataset_id__6564_Inf <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ coname__BARRICK_GOLD_CORP <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `coname__-OTHER` <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ `gvkey__-Inf_6867` <dbl> 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ gvkey__6867_13283 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ gvkey__13283_30025 <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ gvkey__30025_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `fyear__-Inf_1999` <dbl> 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 0, 0, …
## $ fyear__1999_2006 <dbl> 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, …
## $ fyear__2006_2012 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ fyear__2012_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `co_per_rol__-Inf_6968` <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ co_per_rol__6968_18252 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ co_per_rol__18252_33294 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ co_per_rol__33294_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ exec_fullname__John_W._Rowe <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `exec_fullname__-OTHER` <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ departure_code__1 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ departure_code__2 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ departure_code__3 <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, …
## $ departure_code__4 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ departure_code__5 <dbl> 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, …
## $ departure_code__6 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ departure_code__7 <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, …
## $ `cik__-Inf_101063` <dbl> 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, …
## $ cik__101063_832428 <dbl> 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, …
## $ cik__832428_1024302 <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ cik__1024302_Inf <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, …# step 2: correlation
data_correlation <- data_binarized %>%
correlate(ceo_dismissal__1)
data_correlation## # A tibble: 43 × 3
## feature bin correlation
## <fct> <chr> <dbl>
## 1 ceo_dismissal 0 -1
## 2 ceo_dismissal 1 1
## 3 departure_code 3 0.929
## 4 departure_code 5 -0.482
## 5 departure_code 7 -0.298
## 6 departure_code 4 0.274
## 7 fyear -Inf_1999 -0.0785
## 8 departure_code 6 -0.0784
## 9 co_per_rol -Inf_6968 -0.0598
## 10 fyear_gone -Inf_2000 -0.0589
## # ℹ 33 more rows# step 3: plot
data_correlation %>%
correlationfunnel::plot_correlation_funnel()