Data exploration

Labor productivity and its proximate determinants

1 Libraries

knitr::opts_chunk$set(
  echo = TRUE,
  message = FALSE,
  warning = FALSE
)
library(tidyverse)
library(ExPanDaR)      # explore panel data interactively  

theme_set(theme_minimal())

# Change the presentation of decimal numbers to 4 and avoid scientific notation
options(prompt="R> ", digits=6, scipen=7)

2 Import data

dat <- read_csv("dat.csv") 

glimpse(dat)

Rows: 2,700
Columns: 29
$ id            <dbl> 62, 62, 62, 62, 62, 62, 62, 13, 13, 13, 13, 62, 13, 13, 1…
$ country       <chr> "Mozambique", "Mozambique", "Mozambique", "Mozambique", "…
$ year          <dbl> 1990, 1991, 1992, 1993, 1994, 1995, 1996, 2004, 2003, 200…
$ Y             <dbl> 7034, 7743, 6792, 7223, 8194, 7671, 9125, 4936, 4666, 490…
$ K             <dbl> 6262, 6462, 6592, 6859, 7246, 7734, 8121, 10047, 9311, 10…
$ pop           <dbl> 13.37197, 13.71985, 14.20399, 14.77588, 15.36307, 15.9131…
$ L             <dbl> 5.41371, 5.59319, 5.84473, 6.18786, 6.51367, 6.80472, 7.0…
$ s             <dbl> 0.996469, 0.982938, 0.969407, 0.955876, 0.942344, 0.92881…
$ alpha_it      <dbl> 0.573771, 0.573771, 0.573771, 0.573771, 0.573771, 0.57377…
$ GDPpc         <dbl> 526.026, 564.365, 478.176, 488.837, 533.357, 482.056, 556…
$ lp            <dbl> 1299.29, 1384.36, 1162.07, 1167.29, 1257.97, 1127.31, 129…
$ h             <dbl> 1.34708, 1.34363, 1.34018, 1.33672, 1.33325, 1.32977, 1.3…
$ kl            <dbl> 1156.69, 1155.33, 1127.85, 1108.46, 1112.43, 1136.56, 114…
$ kp            <dbl> 1.123283, 1.198236, 1.030340, 1.053069, 1.130831, 0.99185…
$ ky            <dbl> 0.890247, 0.834560, 0.970554, 0.949605, 0.884306, 1.00821…
$ TFP           <dbl> 203.955, 220.003, 189.115, 194.962, 213.737, 193.199, 222…
$ log_GDPpc_raw <dbl> 6.26535, 6.33570, 6.16998, 6.19203, 6.27919, 6.17806, 6.3…
$ log_lp_raw    <dbl> 7.16958, 7.23299, 7.05796, 7.06244, 7.13725, 7.02759, 7.1…
$ log_ky_raw    <dbl> -0.11625594, -0.18085031, -0.02988867, -0.05170874, -0.12…
$ log_h_raw     <dbl> 0.297936, 0.295377, 0.292805, 0.290219, 0.287620, 0.28500…
$ log_tfp_raw   <dbl> 5.31790, 5.39364, 5.24235, 5.27280, 5.36475, 5.26372, 5.4…
$ log_GDPpc     <dbl> 6.16375, 6.19572, 6.22795, 6.26104, 6.29544, 6.33144, 6.3…
$ log_lp        <dbl> 7.05023, 7.07574, 7.10155, 7.12835, 7.15673, 7.18709, 7.2…
$ log_ky        <dbl> -0.129063, -0.130162, -0.131228, -0.132358, -0.133391, -0…
$ log_h         <dbl> 0.277040, 0.279689, 0.282389, 0.285233, 0.288339, 0.29183…
$ log_tfp       <dbl> 5.25749, 5.28692, 5.31650, 5.34665, 5.37760, 5.40939, 5.4…
$ region        <chr> "Africa", "Africa", "Africa", "Africa", "Africa", "Africa…
$ hi1990        <chr> "no", "no", "no", "no", "no", "no", "no", "no", "no", "no…
$ isocode       <chr> "MOZ", "MOZ", "MOZ", "MOZ", "MOZ", "MOZ", "MOZ", "BDI", "…

Select all variables but id

dat <- dat %>% 
  select(
    -id
  )

3 Definitions of variables

df_definitions <- read_csv("dat-definitions.csv") 
df_definitions 

4 Interactive exploration

4.1 Initial exploration

# Run it in the console
ExPanD(
  df = dat,
  df_def = df_definitions,
  export_nb_option = TRUE,
  title = "Data exploration",
  abstract = paste("Full sample")
    )

4.2 Customized exploration

customized <- readRDS("customized.RDS")

# Run it in the console
ExPanD(
  df = dat,
  df_def = df_definitions,
  config_list = customized,
  export_nb_option = TRUE,
  title = "Data exploration",
  abstract = paste("Full sample")
    )

END