Download the Data

I downloaded the raw data from my GitHub repository.

tmp<-tempfile(fileext=".xlsx")
download.file(
  "https://github.com/MEF-BDA503/pj18-mkerimacar/blob/master/egm_example_data.xlsx?raw=true",
  destfile=tmp,mode="wb")
raw_data<-readxl::read_excel(tmp,col_names=TRUE)
file.remove(tmp)
## [1] TRUE
head(raw_data)
## # A tibble: 6 x 15
##   date  pension_fund_co~ n_of_participan~ fund_size_parti~ gov_contribution
##   <chr> <chr>                       <dbl>            <dbl>            <dbl>
## 1 06.0~ Aegon Emeklilik~            42826        139193651         14409322
## 2 06.0~ Allianz Hayat v~           118867       1840701596        231156574
## 3 06.0~ Allianz Yaşam v~           726684       7387398235        815356276
## 4 06.0~ Anadolu Hayat E~          1119572       9975066501       1484745501
## 5 06.0~ Asya Emeklilik ~           129389        337754079         77689275
## 6 06.0~ Avivasa Emeklil~           876894      10550032358       1355045933
## # ... with 10 more variables: contribution <dbl>, n_of_pensioners <chr>,
## #   n_of_ind_contracts <dbl>, n_of_group_ind_contracts <chr>,
## #   n_of_employer_group_certificates <chr>, n_total <dbl>,
## #   size_of_ind_contracts <dbl>, size_of_group_ind_contracts <dbl>,
## #   size_of_employer_group_certificates <dbl>, size_total <dbl>
tail(raw_data)
## # A tibble: 6 x 15
##   date  pension_fund_co~ n_of_participan~ fund_size_parti~ gov_contribution
##   <chr> <chr>                       <dbl>            <dbl>            <dbl>
## 1 30.0~ Halk Hayat ve E~           511848       2845016752        527923905
## 2 30.0~ Katılım Emeklil~           205994        907989162        182110867
## 3 30.0~ Metlife Emeklil~           187483       1368676067        233517732
## 4 30.0~ NN Hayat ve Eme~           265725       2607702561        382046370
## 5 30.0~ Vakıf Emeklilik~           502994       5375415236        757466988
## 6 30.0~ Ziraat Hayat ve~           598703       3105479818        590220958
## # ... with 10 more variables: contribution <dbl>, n_of_pensioners <chr>,
## #   n_of_ind_contracts <dbl>, n_of_group_ind_contracts <chr>,
## #   n_of_employer_group_certificates <chr>, n_total <dbl>,
## #   size_of_ind_contracts <dbl>, size_of_group_ind_contracts <dbl>,
## #   size_of_employer_group_certificates <dbl>, size_total <dbl>

Firms by Median Participants

I think getting medians of participants is a good parameter to measure how firms are performing.

raw_data <- raw_data %>% 
  group_by(pension_fund_company) %>% 
  mutate(medians = median(n_of_participants))

Barplot of firms presented below by their median numbers of participants.

ggplot(data=raw_data, aes(x=pension_fund_company, y=medians, fill=pension_fund_company)) +
  geom_bar(stat="identity")+ 
  theme_classic() + xlab("Firms") + 
  theme(axis.text.x = element_text(angle = 90)) + ylab("Median Number of Participants")
## Warning: Removed 76 rows containing missing values (position_stack).