Historical state union density

Author

Daniel Perez, EARN/EPI

This script uses Current Population Survey (CPS) microdata extracts from https://microdata.epi.org/ to calculate union density from 1983-Present.

library(tidyverse)
library(here)
library(epiextractr)

Load CPS data using epiextractr

basic <- load_basic(1983:2022, year, month, statefips, basicwgt, union, unmem, age, emp, selfemp, selfinc) %>%
  filter(age>=16, emp==1) %>%
  #remove self-employed and self-incorporated workers from sample
  mutate(selfemp0 = ifelse(selfemp==1 & !is.na(selfemp), yes=1, no=0),
         selfinc0 = ifelse(selfinc==1 & !is.na(selfinc), yes=1, no=0)) %>%
  filter(selfemp0==0, selfinc0==0)

Using EPI CPS Basic Monthly Extracts, Version 1.0.59

Calculate US union density 1983–2022

#US union members and union represented by year, 1983-2022

density_us <- basic %>% 
  group_by(year) %>% 
  summarise(represented_share = weighted.mean(union, w=basicwgt/12, na.rm=TRUE),
            rep_n = sum(union, na.rm=TRUE),
            member_share = weighted.mean(unmem, w=basicwgt/12, na.rm=TRUE),
            memb_n = sum(unmem, na.rm=TRUE),
            wgt_memb = sum(unmem * basicwgt/12, na.rm=TRUE))

density_us

# A tibble: 40 × 6
    year represented_share rep_n member_share memb_n wgt_memb
   <int>             <dbl> <int>        <dbl>  <int>    <dbl>
 1  1983           NaN         0        0.201  34258 4422628.
 2  1984             0.216 38008        0.188  32921 4328307.
 3  1985             0.205 36788        0.180  32185 4236957.
 4  1986             0.199 35321        0.175  31013 4230555.
 5  1987             0.192 34505        0.170  30488 4221013.
 6  1988             0.190 32242        0.168  28406 4241194.
 7  1989             0.186 32079        0.164  28261 4235755.
 8  1990             0.182 34110        0.160  29898 4192916.
 9  1991             0.181 32920        0.160  29051 4152415.
10  1992             0.177 31725        0.157  28022 4098902.
# ℹ 30 more rows

Calculate state level union representation, 1983–2022

#Union representation by year and state, 1983–Present
density_state <- basic %>% 
summarise(represented_share = weighted.mean(union, w=basicwgt/12, na.rm=TRUE),
          .by = c(year, statefips)) %>%
  
  #Turn statefips labels into strings
  mutate(statefips = haven::as_factor(statefips)) %>% 
  #sort by year and state
  arrange(year, statefips) %>% 
  #reshape data
  pivot_wider(id_cols = year, names_from = statefips, values_from = represented_share)

density_state

# A tibble: 40 × 52
    year      AL      AK       AZ      AR      CA      CO      CT      DE
   <int>   <dbl>   <dbl>    <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>
 1  1983 NaN     NaN     NaN      NaN     NaN     NaN     NaN     NaN    
 2  1984   0.179   0.279   0.120    0.120   0.248   0.146   0.222   0.193
 3  1985   0.177   0.280   0.121    0.133   0.239   0.137   0.222   0.185
 4  1986   0.181   0.267   0.109    0.123   0.231   0.148   0.207   0.190
 5  1987   0.155   0.256   0.0825   0.133   0.223   0.138   0.200   0.180
 6  1988   0.161   0.268   0.0863   0.117   0.216   0.124   0.205   0.167
 7  1989   0.157   0.249   0.0877   0.121   0.218   0.113   0.193   0.173
 8  1990   0.145   0.258   0.0941   0.121   0.209   0.120   0.196   0.168
 9  1991   0.155   0.239   0.0979   0.125   0.206   0.118   0.200   0.185
10  1992   0.162   0.221   0.0952   0.110   0.209   0.120   0.189   0.184
# ℹ 30 more rows
# ℹ 43 more variables: DC <dbl>, FL <dbl>, GA <dbl>, HI <dbl>, ID <dbl>,
#   IL <dbl>, IN <dbl>, IA <dbl>, KS <dbl>, KY <dbl>, LA <dbl>, ME <dbl>,
#   MD <dbl>, MA <dbl>, MI <dbl>, MN <dbl>, MS <dbl>, MO <dbl>, MT <dbl>,
#   NE <dbl>, NV <dbl>, NH <dbl>, NJ <dbl>, NM <dbl>, NY <dbl>, NC <dbl>,
#   ND <dbl>, OH <dbl>, OK <dbl>, OR <dbl>, PA <dbl>, RI <dbl>, SC <dbl>,
#   SD <dbl>, TN <dbl>, TX <dbl>, UT <dbl>, VT <dbl>, VA <dbl>, WA <dbl>, …