Deep Clean: Varieties of Democracy (V-Dem)

Joshua BrinksISciences, LLC 

Keywords:

pre-processing, country-year

Contents:

Introduction

This guide is an entry in a series of proposed vignettes in which we walk through a deep cleaning or exploratory data analysis (EDA) of a widely employed environment-security dataset. For this entry, we will explore the Varieties of Democracy dataset (V-Dem; Coppedge et al. (2020)). V-Dem is a massive dataset that aims to provide quantitative assessments of historical and nation-state democracy. V-Dem provides both multidimensional and disaggregated measures of democracy across five primary principals: electoral, liberal, participatory, deliberative, and egalitarian (Pemstein et al. 2018). The V-Dem team is comprised of dozens of scientists spread across the globe working with thousands of local experts to quantify local and regional aspects of democracy.

V-Dem is not alone in its efforts to quantify qualitative aspects of nation-state democracy, civil liberties, and elections. Similar datasets include Polity5 (Marshall and Jaggers 2002), Freedom House’s Freedom in the World, Countries at the Crossroads, and Freedom of the Press (Freedom House 2014), and the Institutions and Elections Project (Wig, Hegre, and Regan 2015). Although these datasets are similar in many ways, V-Dem stands out with the sheer number of metrics included. V-Dem features over 470 indicators, 82 indices, and 5 high-level metrics. That is an overwhelming amount of data on par with the World Development Indicators (The World Bank 2017). Let’s get started.

Acquiring the Data

The V-Dem V10 dataset is available from the V-Dem data homepage in preconfigured csv, SPSS, and STATA formats, however, there is a recommended package available to R users available on GitHub. Installing the remote package from GitHub requires devtools. For this guide we’ll be using data.table, but all of these steps could be performed with dplyr and the greater tidyverse, or even base R if you’re a sadist. Lastly, to assist with country coding, we’ll be using the states package, which should also be pulled from GitHub to ensure you have the most recent version.

install.packages('devtools')
devtools::install_github("vdeminstitute/vdemdata")
devtools::install_github("andybega/states")

After the packages are installed load vdemdata and data.table.

library(vdemdata)
library(data.table)
library(states)

The vdemdata package is immature and not available on CRAN, but it provides direct access to the most recently available V-Dem data. The raw data and codebook are stored as embedded package datasets in the vdemdata package.

vdem.raw <- data.table::setDT(vdemdata::vdem)
vdem.codebook <- data.table::setDT(vdemdata::codebook)

Determining Variables of Interest

Using the RStudio data viewer and filter interface with the codebook allows you to quickly search for keywords and variables of interest. Although there are 4108 variables included in vdem.raw, for the purposes of this guide we’ll focus on 2 widely used high-level metrics from vdem: v2x_libdem and v2x_polyarchy. The codebook can be filtered to provide greater context.

metrics<-c('v2x_libdem','v2x_polyarchy')
vdem.codebook[tag %in% metrics, .(name, vartype, tag, question, scale)]
name vartype tag question scale
Electoral democracy index D v2x_polyarchy To what extent is the ideal of electoral democracy in its fullest sense achieved? Interval, from low to high (0-1).
Liberal democracy index D v2x_libdem To what extent is the ideal of liberal democracy achieved? Interval, from low to high (0-1).

The codebook reveals that these are 2 high level (vartype==D) democracy indices quantifying the extent of electoral (v2x_polyarchy) and liberal (v2x_libdem) democracy. Both metrics are continuous variables bound by 0-1. In addition to our desired indices, we should also subset the raw data for identification metrics such as country names, observation year, coding schemes that assist with harmonizing V-Dem data with other datasets, and indicators for country start and stop dates to manage secessions, civil wars, etc..

id.vars<-c('country_name', 'COWcode','histname' ,'codingstart_contemp', 'codingend_contemp','year')
vars<-c(id.vars, metrics)

Now we can subset the raw data and toss what we don’t need.

vdem<-vdem.raw[, ..vars]
rm(vdem.raw)

Determining Years of Interest

We’ll perform a last bit of pruning for temporal considerations. V-Dem has a large historical record dating back to 1789. This is valuable data, but far greater than most practitioners or analysts require. More commonly, analyses will start just before or after key events; i.e. WWII, the Cold War, and the War on Terror. Practically speaking, when preparing historical country-year data, we are most concerned with the headaches brought on by coding nation-state secessions, independence, unifications, etc.

With this in mind, important periods to consider/avoid are: Sudan 2011, Yugoslavia/Kosovo/Serbia/Montenegro 2003-2008, Eritrea 1993, Czech/Slovakia 1993, an even more complicated Yugoslavian dissolution, and Cold War fallout 1989-1991. Sudan is usually an easy check, but Yugoslavia/Kosovo/Serbia/Montenegro are almost always a real pain to manage across multiple datasets and they usually must be included in the analysis. For the purpose of this guide we will subset our data to 1995 and investigate any issues associated with Yugoslavia/Kosovo/Serbia/Montenegro.

vdem <- vdem[year>1994]

Country Code Checks

The most important issue to address with country-year datasets is accurate annual country codes. This includes nation-state secessions and independence (Sudan, Yugoslavia), independently listed territories (Hong Kong, Puerto Rico, Guam, French Guiana), and states with limited international recognition (Kosovo, West Bank/Palestine, Taiwan). These issues afflict international datasets in a wide variety of ways. Before you attempt to “fix” these issues, it’s important to consider how they will be addressed in all the datasets required for your analysis. Do not spend copious amounts of time coding changes to Kosovo and the West Bank if they’re completely ignored in your other datasets of concern.

V-Dem contains Correlates of War (CoW; COWcode) country codes. This is a popular coding scheme that makes country-coding an easier task. We’ll start be renaming the variable, because we will have to manipulate it a lot.

names(vdem)[2]<-"cow"

The states package can serve as a reference to check Correlates of War and Gleditsch and Ward country codes. Both are embedded in the package and available with calls to states::cowstates or states::gwstates. Let’s start by checking if any CoW codes are missing.

unique(vdem[is.na(cow),country_name])
## [1] "Palestine/West Bank" "Palestine/Gaza"      "Somaliland"          "Hong Kong"

It may seem like the easy way out, but these states are commonly ignored in popular environment-security datasets, and can usually be dropped from analysis. One dataset where they would be included is United Nations refugee and asylum seeker data, in which case, you would have to introduce ISO codes to harmonize them with other United Nations data. This could be done with minimal trouble using the countrycode package, but will likely lead to other issues.

library(countrycode)

vdem[, iso3:=countrycode::countrycode(cow, 
                                      origin = "cown",
                                      destination = "iso3c")]
## Warning in countrycode::countrycode(cow, origin = "cown", destination = "iso3c"): Some values were not matched unambiguously: 345, 347, 511

Now we go down the rabbit hole; who were matched unambiguously?

vdem[cow %in% c(345, 347, 511), unique(country_name)]
## [1] "Kosovo"   "Serbia"   "Zanzibar"

These require hard-coded fixes to their ISO3 values. This is beyond the scope of the purpose of this vignette so we will drop the missing cow observations in V-Dem and move on, but I wanted to illustrate the beginning of a country code black hole.

vdem <- vdem[!is.na(cow)][, iso3:=NULL]

Yugoslavia, Serbia, Montenegro, and Kosovo

Official CoW codes for Yugoslavia, Serbia, Montenegro, and Kosovo are 345, 345, 341, and 347, respectively. CoW maintains the 345 numeric AND YUG character designations for Serbia after the Yugoslavia break. CoW assigns Montenegro 341 starting in 2006 and Kosovo 347 in 2008 (review these changes in states::cowstates).

Check how V-Dem assigns these changes.

dcast(vdem[cow %in% c(345, 341, 347), .(country_name, cow, year)],
      year~cow, value.var = "country_name")
year 341 345 347
1995 NA Serbia NA
1996 NA Serbia NA
1997 NA Serbia NA
1998 Montenegro Serbia NA
1999 Montenegro Serbia Kosovo
2000 Montenegro Serbia Kosovo
2001 Montenegro Serbia Kosovo
2002 Montenegro Serbia Kosovo
2003 Montenegro Serbia Kosovo
2004 Montenegro Serbia Kosovo
2005 Montenegro Serbia Kosovo
2006 Montenegro Serbia Kosovo
2007 Montenegro Serbia Kosovo
2008 Montenegro Serbia Kosovo
2009 Montenegro Serbia Kosovo
2010 Montenegro Serbia Kosovo
2011 Montenegro Serbia Kosovo
2012 Montenegro Serbia Kosovo
2013 Montenegro Serbia Kosovo
2014 Montenegro Serbia Kosovo
2015 Montenegro Serbia Kosovo
2016 Montenegro Serbia Kosovo
2017 Montenegro Serbia Kosovo
2018 Montenegro Serbia Kosovo
2019 Montenegro Serbia Kosovo

Thankfully the codes themselves are correct, however, V-Dem maintains independent listings for all three states even while they were unified under various arrangements between 1992-2005. The course of action here depends on your intended use and additional datasets. Taking the mean of Serbia and Montenegro (maybe even Kosovo) over this time period is one potential correction. For this guide we will average Serbia and Montenegro. You may want to consider doing the same for Kosovo and Serbia or all 3 states.

for(i in 1995:2005) vdem[cow %in% c(341,345) & year==i, (metrics):=lapply(.SD, mean, na.rm = TRUE), .SDcols = metrics]

The coverage and coding for Kosovo is correct; it can be left if other data of interest recognizes the state.

Other Considerations

Sudan (625) and South Sudan (626) split in 2011. Check them in V-Dem.

dcast(vdem[cow %in% c(625,626), .(country_name, cow, year)],year~cow, value.var = "country_name")
year 625 626
1995 Sudan NA
1996 Sudan NA
1997 Sudan NA
1998 Sudan NA
1999 Sudan NA
2000 Sudan NA
2001 Sudan NA
2002 Sudan NA
2003 Sudan NA
2004 Sudan NA
2005 Sudan NA
2006 Sudan NA
2007 Sudan NA
2008 Sudan NA
2009 Sudan NA
2010 Sudan NA
2011 Sudan South Sudan
2012 Sudan South Sudan
2013 Sudan South Sudan
2014 Sudan South Sudan
2015 Sudan South Sudan
2016 Sudan South Sudan
2017 Sudan South Sudan
2018 Sudan South Sudan
2019 Sudan South Sudan

This is correct. Lastly, we should check V-Dem against our CoW reference (states::cowstates) to see if V-Dem is missing any countries.

cowstates<-data.table::setDT(states::cowstates)
missing_in_vdem<-cowstates[end >= sprintf("%s-01-01", 1995)][!cowcode %in% vdem$cow]
knitr::kable(missing_in_vdem)
cowcode cowc country_name start end microstate
31 BHM Bahamas 1973-07-10 9999-12-31 FALSE
54 DMA Dominica 1978-11-03 9999-12-31 TRUE
55 GRN Grenada 1974-02-07 9999-12-31 TRUE
56 SLU St. Lucia 1979-02-22 9999-12-31 TRUE
57 SVG St. Vincent and the Grenadines 1979-10-27 9999-12-31 TRUE
58 AAB Antigua & Barbuda 1981-11-01 9999-12-31 TRUE
60 SKN St. Kitts and Nevis 1983-09-19 9999-12-31 TRUE
80 BLZ Belize 1981-09-21 9999-12-31 FALSE
221 MNC Monaco 1993-05-28 9999-12-31 TRUE
223 LIE Liechtenstein 1990-09-18 9999-12-31 TRUE
232 AND Andorra 1993-07-28 9999-12-31 TRUE
331 SNM San Marino 1992-03-02 9999-12-31 TRUE
835 BRU Brunei 1984-01-01 9999-12-31 FALSE
946 KIR Kiribati 1999-09-14 9999-12-31 TRUE
947 TUV Tuvalu 2000-09-05 9999-12-31 TRUE
955 TON Tonga 1999-09-14 9999-12-31 TRUE
970 NAU Nauru 1999-09-14 9999-12-31 TRUE
983 MSI Marshall Islands 1991-09-17 9999-12-31 TRUE
986 PAL Palau 1994-12-15 9999-12-31 TRUE
987 FSM Federated States of Micronesia 1991-09-17 9999-12-31 TRUE
990 WSM Samoa 1976-12-15 9999-12-31 TRUE

There is nothing of consequence here; these are mostly microstates that are commonly omitted from environment-security analysis. For simplicity, the remaining microstates included in V-Dem may be dropped unless you are carrying out a specialized analysis.

microstates <- cowstates[microstate==TRUE,unique(cowcode)]
vdem<-vdem[!(cow %in% microstates)]

Finally, we’ll examine V-Dem for duplicate country names to ensure we don’t miss any peculiarities.

dupes<-unique(vdem[,.(country_name, cow)])
# check for duplicate names across codes
table(duplicated(dupes$country_name))
## 
## FALSE 
##   172

Excellent!

Missing Values

As previously covered, v2x_polyarchy and v2x_libdem are 2 high level (vartype==D) democracy indices quantifying the extent of electoral and liberal democracy in a given state. Both metrics are continuous variables bound by 0-1. We can quickly check their distributions to get a better sense of the data.

hist.dat<-melt(vdem, 
               id.vars = c("cow", "year"),
               measure.vars = c("v2x_libdem",
                                "v2x_polyarchy"),
               variable.name = "metric",
               value.name = "value")

ggplot2::ggplot(hist.dat, ggplot2::aes(x=value))+
  ggplot2::geom_histogram()+
  ggplot2::facet_wrap(~metric)+
  ggplot2::labs(title = "V-Dem Metric Distributions",
                x = "Value",
                y= "Count")+
  ggplot2::theme_minimal()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 11 rows containing non-finite values (stat_bin).

These look pretty good with (mostly) uniform converage. The warnings have tipped us off to a few missing values; let’s investigate further.

vdem[is.na(v2x_libdem) | is.na(v2x_polyarchy),.(unique(country_name), n=.N, last_year=max(year)), by=cow]
cow V1 n last_year
860 Timor-Leste 4 1998
692 Bahrain 7 2001

There are only 11 missing values, but they should be investigated. First Timor-Leste.

vdem[cow==860, .(country_name, year, v2x_libdem, v2x_polyarchy)]
country_name year v2x_libdem v2x_polyarchy
Timor-Leste 1995 NA 0.079
Timor-Leste 1996 NA 0.079
Timor-Leste 1997 NA 0.079
Timor-Leste 1998 NA 0.096
Timor-Leste 1999 0.087 0.094
Timor-Leste 2000 0.184 0.225
Timor-Leste 2001 0.240 0.288
Timor-Leste 2002 0.383 0.495
Timor-Leste 2003 0.452 0.611
Timor-Leste 2004 0.452 0.611
Timor-Leste 2005 0.409 0.598
Timor-Leste 2006 0.420 0.603
Timor-Leste 2007 0.472 0.609
Timor-Leste 2008 0.503 0.663
Timor-Leste 2009 0.503 0.658
Timor-Leste 2010 0.471 0.608
Timor-Leste 2011 0.462 0.617
Timor-Leste 2012 0.492 0.644
Timor-Leste 2013 0.489 0.641
Timor-Leste 2014 0.460 0.636
Timor-Leste 2015 0.484 0.667
Timor-Leste 2016 0.463 0.644
Timor-Leste 2017 0.475 0.689
Timor-Leste 2018 0.536 0.757
Timor-Leste 2019 0.522 0.754

They are missing v2x_libdem for 1995-1998. These years are during the Indonesian occupation and prior to their internationally recognized independence. They can be ignored or dropped unless you have a special use case.

Now Bahrain.

vdem[cow==692, .(country_name, year, v2x_libdem, v2x_polyarchy)]
country_name year v2x_libdem v2x_polyarchy
Bahrain 1995 NA 0.051
Bahrain 1996 NA 0.051
Bahrain 1997 NA 0.051
Bahrain 1998 NA 0.051
Bahrain 1999 NA 0.050
Bahrain 2000 NA 0.078
Bahrain 2001 NA 0.113
Bahrain 2002 0.073 0.151
Bahrain 2003 0.090 0.230
Bahrain 2004 0.078 0.230
Bahrain 2005 0.081 0.233
Bahrain 2006 0.090 0.234
Bahrain 2007 0.093 0.235
Bahrain 2008 0.093 0.235
Bahrain 2009 0.098 0.234
Bahrain 2010 0.089 0.231
Bahrain 2011 0.075 0.218
Bahrain 2012 0.038 0.165
Bahrain 2013 0.038 0.163
Bahrain 2014 0.040 0.161
Bahrain 2015 0.038 0.127
Bahrain 2016 0.037 0.122
Bahrain 2017 0.039 0.123
Bahrain 2018 0.031 0.117
Bahrain 2019 0.050 0.118

Bahrain declared independence in 1971 and converted to a Constitutional Monarchy in 2001. The missing value in 2001 may pose an issue when trying to join on additional data sets. A simple fix would be to replace the 2001 value with the 2002 value. A more complicated fix would be some type of lead-in imputation. Let’s examine the time series.

ggplot2::ggplot(vdem[cow==692], ggplot2::aes(x=year, y=v2x_libdem))+
  ggplot2::geom_point(size = 2)+
  ggplot2::labs(title="Bahrain Libdem Time Series",
                x = "Year",
                y = "Libdem")+
  ggplot2::theme_minimal()
## Warning: Removed 7 rows containing missing values (geom_point).

There is a bit of a linear trend, but imputation would be more trouble than it’s worth. An adequate correction is to put in the 2002 value.

vdem[cow==692 & year==2001, v2x_libdem := vdem[cow==692 & year==2002, v2x_libdem]]

Final Cleanup

Before finishing, we will perform a few final processing steps. First, extract only the minimum number of variables.

vdem <- vdem[, .(cow, year, v2x_libdem, v2x_polyarchy)]

Next, set the year and CoW columns to integers.

cols<-c("cow", "year")
vdem[, (cols):=lapply(.SD, as.integer), .SDcols = cols]

Lastly, if you are working with other colleagues, strip the data.table class from the object.

data.table::setDF(vdem)

And we’re finished. I hope you found this exercise informative, and please contact me with any questions, concerns, or tips.

References

Coppedge, Michael, John Gerring, Carl Henrik Knutsen, Staffan I. Lindberg, Jan Teorell, David Altman, Michael Bernhard, et al. 2020. “V-Dem Codebook V10.” SSRN Scholarly Paper ID 3557877. Rochester, NY: Social Science Research Network. https://doi.org/10.2139/ssrn.3557877.

Freedom House. 2014. Freedom in the World 2014: The Annual Survey of Political Rights and Civil Liberties. Rowman & Littlefield. http://books.google.com?id=uiDfBQAAQBAJ.

Marshall, Monty, and Keith Jaggers. 2002. “Polity IV Project: Political Regime Characteristics and Transitions, 1800-2002.”

Pemstein, Daniel, Kyle L. Marquardt, Eitan Tzelgov, Yi-ting Wang, Joshua Krusell, and Farhad Miri. 2018. “The V-Dem Measurement Model: Latent Variable Analysis for Cross-National and Cross-Temporal Expert-Coded Data.” SSRN Scholarly Paper ID 3167764. Rochester, NY: Social Science Research Network. https://doi.org/10.2139/ssrn.3167764.

The World Bank. 2017. “World Development Indicators.” Data Set. Washington, DC: The World Bank. https://data.worldbank.org/data-catalog/world-development-indicators.

Wig, Tore, Håvard Hegre, and Patrick M. Regan. 2015. “Updated Data on Institutions and Elections 1960: Presenting the IAEP Dataset Version 2.0.” Research & Politics 2 (2): 2053168015579120. https://doi.org/10.1177/2053168015579120.

Additional Meta-Data

Data Categories:

tabular, country-year

Add new comment

Plain text

  • Allowed HTML tags: <a href hreflang> <em> <strong> <cite> <blockquote cite> <code> <ul type> <ol start type> <li> <dl> <dt> <dd>
  • No HTML tags allowed.
  • Web page addresses and email addresses turn into links automatically.