Democracy Data, Updated

(Of interest mostly to political scientists or other users of country-year democracy data)

Quick announcement: I’ve just updated my democracyData and QuickUDS R packages (described in this post at more length) to incorporate the latest data from Freedom House (Freedom in the World 2018) and most recent update of the voice and accountability index from the Worldwide Governance Indicators. The democracyData package (https://xmarquez.github.io/democracyData/) allows you to download, tidy, and use a wide variety of datasets with regime and democracy indicators, while the QuickUDS package (https://xmarquez.github.io/QuickUDS/) facilitates the construction of Unified Democracy Scores-style latent variable indexes of democracy.

Here’s what Freedom House’s latest data (use with care!) says about the average level of freedom in the world (all countries equally weighted):

Or aggregated by status (free, partly free, not free):

Not so much evidence of a democratic recession, but some evidence of stagnation.

And here in some selected countries:

For contrast, here’s what my version of the Unified Democracy Scores (which incorporate the Freedom House scores as one of their inputs) says about the average level of democracy in the world:

This measure shows a bit more evidence of a decline in the average level of democracy in the world over the past few years, at least according to the indices commonly used by political scientists. This may be simply because only REIGN and Freedom House have data for 2017 so far, so best not to take that dip for 2017 too seriously.

And again the extended UDS for selected countries:

Finally, here’s what the Varieties of Democracy dataset, which I consider to have the best and most flexible set of measures, says:

Here there is only a hint of a downturn in the average level of democracy in the world (but note V-Dem has not yet been updated with 2017 data).

And here is what this data looks like for selected countries:

Enjoy!

The quantification of power: some thoughts on, and tools for, measuring democracy

(More substantive content soon! This is mostly of interest to political scientists, R users, and people concerned with the measurement of democracy).

Democracy is the government of numbers. No other form of government has historically been as concerned with the quantification of power. Indeed, the idea that power depends on the exact numerical strength of one’s supporters, rather than their qualities, would have seemed absurd for most of human history. And I would guess no other form of government has evoked so much mathematical effort. (Even the recent election here in NZ produced extraordinarily sophisticated Bayesian models to predict the outcome).

And yet because the concept of democracy uneasily mingles what is, what can be, and what ought to be, people often object to the attempt to quantify its degree (or even its existence) in particular places and times. (My students often do!). Democracy does not seem like the kind of thing that would be easily and uncontroversially measurable. On the contrary, because any attempt to measure democracy reflects certain normative standards, it cannot but be controversial, especially since most of its conceptualizations for such purposes tend to reduce it to competitive elections with a wide suffrage, which for a variety of reasons seems like an unacceptably narrow view of the ideal to many people.

This is most obvious when we’re talking about cases like Venezuela, where to take a position on the question – to say “Venezuela is a democracy” or “Venezuela is not a democracy” – is to take sides in a rancorous political dispute. But even to say something relatively uncontroversial, like “the United States is a consolidated democracy”, is fraught with normative implications, since clearly “actually existing democracies” (representative governments with non-Potemkin opposition parties and nearly universal suffrage) are highly imperfect, and to give them top scores in some scale seems to imply that they are better than they truly are. In any case, although most people around the world accept democracy as the only legitimate form of government, they disagree enormously about whether or not a given place is or is not actually democratic, and the degree to which particular practices and institutions “matter” for democracy.

Democracy measurement, then, is a somewhat dubious enterprise. The essential contestability of the concept (is democracy about equality, or about self-government, or about freedom? In what proportions?), as well as good-faith differences of opinion about the sorts of preconditions that are essential for its functioning and the kinds of institutions that actualize its values, make it difficult to take seriously any single measurement of “democraticness.” And these disagreements are not really resolvable by appeal to the dictionary; they go back to the earliest discussions of democracy as a distinct phenomenon in history.[1]

Yet I still think the attempt to summarize in some disciplined way particular judgments about “democraticness” over time and in space is useful. A democracy measure seems to me to be a numerical crystalization of a political history: a history at a (literal) glance that can be put to use to say more interesting things about the world. One need not agree with any particular conceptualization of democracy, or take any given measure as a normative standard of what democracy should be, to appreciate the possibility of historical comparison across time and space. And because the concept of democracy is inescapably contested, I think the more the merrier: let a hundred measures of democracy bloom, let a thousand schools of thought contend!

I am thus pleased to announce three different R packages (or rather, two and one update) for accessing and manipulating all the democracy datasets I know about:

1. A package to access the Varieties of Democracy (V-Dem) dataset, version 7.1 (the latest update). The V-Dem dataset is the gold standard of democracy measurement today. It provides indexes targeting multiple conceptualizations of democracy, and an extremely wide variety of indicators that you can use to satisfy basically every measurement need that you might have; if you don’t like their particular conceptualizations of democracy, you can basically build your own. Each country is coded by at least five people, all of whom live there, and subject to rigorous aggregation and validation procedures. Plus, it is annually updated, and covers the entire period 1900-2016, so it’s pretty comprehensive. If you do any serious empirical research that requires you to use measures of democracy, you should seriously consider using V-Dem as your first choice of measure. This package allows you to access the entire V-Dem dataset (more than 3,000 variables, including external ones) directly from R, and to extract combinations of columns easily according to particular criteria (e.g., section of the codebook where they appear, label, etc.). Check it out at https://xmarquez.github.io/vdem, and install it using devtools::install_github("xmarquez/vdem").
2. A package to download or access most other democracy datasets used in scholarly work from R, including Polity IV, Freedom House, Geddes, Wright, and Frantz’s Autocratic Regimes dataset, the World Governance Indicators’ “Voice and Accountability” index, the PACL/ACLP/DD dataset, and many others, including some which are now of merely historical interest. (There are 32 of them in the package). The package automates the process of putting these datasets in standard country-year format, assigning appropriate country codes, and the like, and makes it easy to access some less well-known democracy datasets. (Mostly I created it because I’ve spent hundreds of hours tediously repeating these operations!). Check it out at https://xmarquez.github.io/democracyData, and install it using devtools::install_github("xmarquez/democracyData").
3. Finally, I’ve also updated my package to replicate and extend the Unified Democracy scores. (I first described this package on this blog). This produces a latent variable index from multiple democracy measures, based on methods discussed by Pemstein, Meserve, and Melton in 2010; the most recent update of the package extendes these scores up to 2016 and incorporates revisions and updates of a variety of datasets, including Polity IV, Freedom House, and V-Dem It also includes improvements to the functions used to calculate UDS-style models. Check it out at https://xmarquez.github.io/QuickUDS, and install it using devtools::install_github("xmarquez/QuickUDS").

Feedback, contributors, and pull requests for any of these packages welcome; I hope to be able to submit at least 2 of these packages to CRAN in the near future, so if you use them and encounter any problems let me know. (The V-Dem package is too large for CRAN and will probably never be there).

In what follows, a short discussion of the characteristics of these measures, probably of most interest to people who already use them.

Some general characteristics of democracy measures

The numerical measurement of democracy is about fifty years old. The earliest comprehensive measures of democracy – the Polity project, Freedom House’s Freedom in the World index (first known as the Gastil index), Kenneth Bollen's and Tatu Vanhanen's measures of democracy – go back to the late 1960s and early 1970s. (Vanhanen, who’s been at this business longer than most, identifies some earlier attempts to measure democracy numerically, some going back to the early 1950s, but these were pretty small and unsystematic). There are now 32 different accesible datasets containing some measure of democracy, most developed in the first decade of this century (at least AFAIK):


Most of these measures tend to be highly but not perfectly correlated, reflecting differences in conceptualization as well as varying judgments about the political situation of specific countries and periods:

Yet the high overall level of correlation among these measures masks substantial variation over time:

There is a lot more agreement among measures of democracy after the 1920s than before, simply because it is harder to make judgments of democracy for the more distant past (how much should class-stratified male suffrage count? etc.), though go back far enough and it’s reasonably easy (since there are no democracies past a certain point). In any case, only 13 of the 32 datasets measuring democracy code countries during the 19th century, and only 8 of these make any effort to be comprehensive (mostly because they follow the Polity IV panel, or modify the polity IV scores in some way).

These correlations among measures also mask substantial variation in space:

In other words, while on average the pairwise correlation between different measures of democracy within individual country histories is quite high (0.7), for a substantial minority of countries correlations can be much lower, or even negative. These numbers are better if we only look at the degree of agreement among measures from large, well-resourced projects, to be sure, but they are still by no means reassuring if we are looking for consensus:


Most democracy measurement projects are actually variants of these large-scale efforts; a large number of them take Polity, PACL/ACLP, or Freedom House as starting points to develop their own measures. If we take their correlations as measures of similarity, we can cluster the indexes hierarchically to show these quasi-genealogical family resemblances:


At the top, we have the “Polity cluster” – measures of democracy that mostly just modify Polity, including the Participation-Enhanced Polity Scores (PEPS), the PITF indicators (based on subcomponents of Polity), and the Polity scores themselves. These are highly related with some calculated indexes, including the Unified Democracy Scores and my extension, Freedom House, and Coppedge, Alvarez, and Maldonado’s “contestation dimension” (from a principal components analysis of a number of democracy measures), that attempt to weigh multiple factors in the construction of a measure of democracy, but mostly end up giving weight to the contestability of power and civil liberties.

In the middle we have a cluster that attempts to weigh participation and contestation more equally (LIED, the V-Dem Additive Polyarchy Index, Vanhanen’s Index of Democratization, etc.) and then a cluster of measures that derive from PACL’s attempts to develop a dichotomous measure of democracy (including Boix, Miller and Rosato’s extension as well as Geddes, Wright, and Frantz’s dataset of Autocratic regimes, as well as several other academic datasets). Then there is another cluster of measures that give more weight to formal inclusion (e.g. Doorenspleet, and Bernhard, Nordstrom, and Reenock, both of which make democracy depend on the existence of universal suffrage), a cluster of V-Dem indexes (which weigh multiple factors to come up with a number, including formal inclusiveness), and finally at the bottom we find measures that simply gauge the degree of participation (Vanhanen’s index of participation and the “inclusion dimension” calculated by Coppedge, Alvarez, and Maldonado).

There is a lot more that one could show here, but this is probably enough for now; hope these tools are useful to others! All code for this post available in this repository.

[1] On the other hand, unlike other controversial numerical measures of social phenomena, like university rankings or GDP per capita, governments and other organizations do not spend much time trying to “game” measures of democracy, because few people other than a small number of political scientists care, and little money is at stake. This is probably a good thing, on balance.

New Book: Non-Democratic Politics

My new book, Non-Democratic Politics: Authoritarianism, Dictatorship, and Democratization has been out for a few weeks (Palgrave, Amazon). For the usual vaguely superstitious reasons, I did not want to make an announcement until I had a copy in my hands, but now I do. Just in time for the holidays!

I confess that I feel a bit ambivalent about the book’s publication. On the one hand, I’m of course glad the book is finally out in the wild; it’s been a long process, and it’s great to be able to touch and see the physical result of my work, and to know that at least some other people will read it. (Much better scholars of authoritarian politics than me also said some nice things about it in the back cover, which is extremely gratifying). Moreover, if you have followed this blog, you will find that some material in the book elaborates and supports many things I have said here more informally (on cults of personality, propaganda, robust action in the Franco regime, the history of political regimes, the Saudi monarchy, etc.); one reason I wrote the book was to be able to put together in a reasonably coherent way my thoughts on these subjects, and I felt encouraged enough by some of the reaction to my writing here to think that I had something to say. (Without this blog, this book probably would not exist; thank you readers!) And since I teach this material here at Vic, the result should be useful as a textbook. (If you teach classes on non-democratic politics do consider the book for use in your course!).

But I also feel that the book should be seen as “version 0.1” of what I really wanted to do. There was more that I wanted to write, and there are things I already want to add or revise (partly in response to current events, partly in response to learning new things), though I will only be able to do this if Palgrave decides there’s enough demand for a second edition. If I had more contractual leeway (and academic clout) I would put the whole thing in my Github repository and make it into an evolving work, adding or deleting material over time as I learn more, or correcting errors as they are brought to my attention, and releasing new versions every so often. But I don’t have that kind of leeway or clout yet (perhaps in the future – we’ll see); and traditional publication still offers some advantages (including dedicated peer review, from which I benefited a lot. Thank you, anonymous reviewers, whoever you are, for helping me improve this book).

In lieu of putting the entire work online, however, I have created a website where all the charts and data in the book are available, and where I can give free rein to my love of ggplot2 graphs and data art. The site (https://xmarquez.github.io/AuthoritarianismBook/) contains replication code for all the figures and tables in the book, natural-language explanations of the code, and full documentation for all the datasets, and is to boot available for download as a single R package. It also contains some extensions of the figures in the book, including huge vertical graphs of the kind that sometimes appear in this blog but could never fit in a normal book. My hope is that people can use this package (and the associated website) to easily do their own exploratory data analysis on the topic. I have tried to make it as user-friendly as possible for people with little experience using R; and I intend to update it regularly and add new features and corrections. Check it out![1]

The hardcover is unfortunately priced (I don’t recommend you buy it, unless you’re an academic library), and I think even the paperback should be cheaper, but I don’t make those decisions. Nevertheless, if you have enjoyed this blog in the past, and would like to see how many of the aspects of non-democratic politics I have discussed here fit together, or you simply wish to learn more about non-democratic politics, consider buying it!

Normal service on this blog will resume shortly.

---

1. There will also be some further narrative material available at a different website, including extended discussions of a few cases, but I’m way behind on producing these narratives. ↩

Artisanal Democracy Data: A Quick and Easy Way of Extending the Unified Democracy Scores

(Apologies for the lack of posting - I've been finishing some big projects. This is of interest primarily to people who care about quantitative measures of democracy in the 19th century, or for some unknown reason enjoy creating latent variable indexes of democracy. Contains a very small amount of code, and references to more.)

If you have followed the graph-heavy posts in this blog, you may have noticed that I really like the Unified Democracy Scores developed by Daniel Pemstein, Stephen Meserve, and James Melton. The basic idea behind this particular measure of democracy, as they explain in their 2010 article, is as follows. Social scientists have developed a wealth of measures of democracy (some large-scale projects like the Polity dataset or the Freedom in the World index, some small “boutique” efforts by political scientists for a particular research project). Though these measures are typically highly correlated (usually in the 0.8-0.9 range), they still differ significantly for some countries and years. These differences are both conceptual (researchers disagree about the essential characteristics of democracy) and empirical (researchers disagree about whether a given country-year is democratic according to a particular definition).

PMM argue that we can assume that these measures are all getting at a latent trait that is only imperfectly observed and conceptualized by the compilers of all the datasets purporting to measure democracy, and that we can estimate this trait using techniques from item response theory that were originally developed to evaluate the performance of multiple graders in academic settings. They then proceeded to do just that, producing a dataset that not only contains latent variable estimates of democracy for 9850 country-years (200 unique countries), but also estimates of the measurement error associated with these scores (derived from the patterns of disagreement between different democracy measures).

This, to be honest, is one of the main attractions of the UDS for me: I get nervous when I see a measure of democracy that does not have a confidence interval around it, given the empirical and conceptual difficulties involved in producing numerical estimates of a woolly concept like “democracy.” Nevertheless, the UDS had some limitations: for one thing, they only went back to 1946, even though many existing measures of democracy contain information for earlier periods, and PMM never made use of all the publicly available measures of democracy in their construction of the scores, which meant that the standard errors around them were relatively large. (The original UDS used 10 different democracy measures for its construction; the current release uses 12, but I count more than 25).

Moreover, the UDS haven’t been updated since 2014 (and then only to 2012), and PMM seem to have moved on from the project. Pemstein, for example, is now involved with measurement at the V-Dem institute, whose “Varieties of Democracy” dataset promises to be the gold standard for democracy measurement, so I’m guessing the UDS will not receive many more updates, if any. (If you are engaged in serious empirical research on democracy, you should probably be using the V-dem dataset anyway. Seriously, it’s amazing - I may write a post about it later this year). And though in principle one could use PMM's procedure to update these scores, and they even made available an (undocumented) replication package in 2013, I was never able to make their software work properly, and their Bayesian algorithms for estimating the latent trait seemed anyway too computationally intensive for my time and budget.

I think this situation is a pity. For my own purposes – which have to do mostly with the history of political regimes for my current project – I’d like a summary measure of democracy that aggregates both empirical and conceptual uncertainty in a principled way for a very large number of countries, just like I believe the UDS did. But I also would like a measure that goes back as far as possible in time, and is easily updated when new information arises (e.g., there are new releases of Freedom House or Polity). The new V-dem indexes are great on some of these counts (they come with confidence intervals) but not on others (they only cover 2014-1900, they are missing some countries, and the full dataset is a bit unwieldy – too many choices distract me). Other datasets – the trusty Polity dataset, the new and excellent LIED index – do go back to the 19th century, but they provide no estimates of measurement error, and they make specific choices about conceptualization that I do not always agree with.

But why wait for others to create my preferred measure when I can do it myself? So I went ahead and figured out how to first replicate the Unified Democracy scores without using a computationally intensive Bayesian algorithm, and then extended them both forwards to 2015 and backwards to the 19th century (in some cases to the 18th century), using information from 28 different measures of democracy (some of them rather obscure, some just new, like the LIED index or the latest version of the Freedom House data). And I created an R package to let you do the same, should you wish to fiddle with the details of the scores or create your own version of the UDS using different source measures. (Democratizing democracy indexes since 2016!).

The gory details are all in this paper, which explains how to replicate and extend the scores, and contains plenty of diagnostic pictures of the result; but if you only want to see the code to produce the extended UDS scores check out the package vignette here. If you are an R user, you can easily install the package and its documentation by typing (assuming you have devtools installed, and that I’ve done everything correctly on my side):

devtools::install_github(repo = "xmarquez/QuickUDS")

The package includes both my “extended” UD scores (fully documented and covering 24111 country-years going all the way to the 18th century in some cases, for 224 sovereign countries and some non-sovereign territories) and a replication dataset which includes 61 different measures of democracy from 29 different measurement efforts covering a total of 24149 country-years (also fully documented). (Even if you are not interested in the UDS, original or extended, you may be interested in that dataset of democracy scores). For those poor benighted souls who use Stata or (God fobid) some awful thing like SPSS (kidding!), you can access a CSV version of the package datasets and a PDF version of their documentation here.

To be sure, for most research projects you probably don’t need this extended Unified Democracy measure. After all, most useful variables in your typical democracy regression are unmeasured or unavailable before the 1950s for most countries, and if your work only requires going back to the 1900s, you are better off with the new V-dem data, rather than this artisanal version of the UDS. But the extended UDS is nice for some things, I think.

First, quantitative history (what I wanted the extended UDS for). For example, consider the problem of measuring democracy in the USA over the entirety of the last two centuries. Existing democracy measures disagree about when the USA first became fully democratic, primarily because they disagree about how much to weigh formal restrictions on women’s suffrage and the formal and informal disenfranchisement of African Americans in their conceptualization. Some measures give the USA the highest possible score early in the 19th century, others after the civil war, others only after 1920, with the introduction of women’s suffrage, and yet others (e.g. LIED) not until 1965, after the Civil Rights Movement. With the extended UDS these differences do not matter very much: as consensus among the different datasets increases, so does the measured US level of democracy:


In the figure above, I use a transformed version of the extended UDS scores whose midpoint is the “consensus” estimate of the cutoff between democracy and non-democracy among minimalist, dichotomous measures in the latent variable scale. (For details, see my paper; the grey areas represent 95% confidence intervals). This version can be interpreted as a probability scale: “1” means the country-year is almost certainly a democracy, “0” means it is almost certainly not a democracy, and “0.5” that it could be either. (Or we could arbitrarily decide that 0-0.33 means the country is likely an autocracy of whatever kind, 0.33-0.66 that it is likely some kind of hybrid regime, and 0.66-1 that is pretty much a democracy, at least by current scholarly standards).

In any case, the extended UDS shows an increase in the USA’s level of democracy in the 1820s (the “Age of Jackson”), the 1870s (after the civil war), the 1920s after female enfranchisement, and a gradual increase in the 1960s after the Civil Rights movement, though the magnitude of each increase (and of the standard error of the resulting score) depends on exactly which measures are used to construct the index. (The spike in the 2000s is an artifact of measurement, having more to do with the fact that lots of datasets end around that time than with any genuine but temporary increase in the USA’s democracy score). Some of these changes would be visible in other datasets, but no other measure would show them all; if you use Polity, for example, you would see a perfect score for the USA since 1871.

Just because what use is this blog if I cannot have a huge vertical visualization, here are ALL THE DEMOCRACY SCORES, alphabetically by country:

(Grey shaded areas represent 95% confidence intervals; blue shaded areas are periods where the country is either deemed to be a member of the system of states in the Gleditsch and Ward list of state system membership since 1816, i.e., independent, or is a microstate in Gleditsch’s tentative list).


A couple of things to note. First, scores are calculated for some countries for periods when they are not generally considered to be independent; this is because some of the underlying data used to produce them (e.g., the V-Dem dataset) produce measures of democracy for existing states when they were under imperial governance (see, e.g., the graphs for India or South Korea).

Second, confidence intervals vary quite a bit, primarily due to the number of measures of democracy available for particular country-years and the degree of their agreement. For some country-years they are so large (because too few datasets bother to produce a measure for a period, or the ones that do disagree radically) that the extended UD score is meaningless, but for most country-years (as I explain in my paper) the standard error of the scores is actually much smaller than the standard error of the “official” UDS, making the measure more useful for empirical research.

Finally, maybe this is just me, but in general the scores tend to capture my intuitions about movements in democracy levels well (which is unsurprising, since they are based on all existing scholarly measures of democracy); see the graphs for Chile or Venezuela, for example. And using these scores we can get a better sense of the magnitude of the historical shifts towards democracy in the last two centuries.

For example, according to the extended UDS (and ignoring measurement uncertainty, just because this is a blog), a good 50% of the world’s population today lives in countries that can be considered basically democratic, but only around 10% live in countries with the highest scores (0.8 and above):

And Huntington’s three waves of democratization are clearly visible in the data (again ignoring measurement uncertainty):


But suppose you are not into quantitative history. There are still a couple of use cases where long-run, quantitative data about democracy with estimates of measurement error is likely to be useful. Consider, for example, the question of the democratic peace, or of the relationship between economic development and democracy – two questions that benefit from very long-run measures of democracy, especially measures that can be easily updated, like this one.

I may write more about this later, but here is an example about a couple of minor things this extended democracy measure might tell us about the basic stylized fact of the “democratic peace.” Using the revised list of interstate wars by Gleditsch, we can create a scatterplot of the mean extended UD score of each side in an interstate war, and calculate the 2-d density distribution of these scores while accounting for their measurement error:

The x- coordinate of each point is the mean extended UD score (in the 0-1 probability scale where 0.5 is the average cutoff between democracy and non-democracy among the most minimalistic measures) of side A in a war listed by Gleditsch; the y-coordinate is the mean extended UD score of side B; each blue square is the 95% “confidence rectangle” around these measures; the shaded blobs are the 2-d probability densities, accounting for measurement error in the scores.

As we can see, the basic stylized fact of a dyadic democratic peace is plausible enough, at least for countries which have a high probability of being democratic. In particular, countries whose mean extended UD democracy score is over 0.8 (in the transformed 0-1 scale) have not fought one another, even after accounting for measurement error. (Though they have fought plenty of wars with other countries, as the plot indicates). But note that the dyadic democratic peace only holds perfectly if we set the cutoff for “being a democracy” quite high (0.8 is in the top 10% of country-years in this large sample; few countries have ever been that democratic); as we go down to the 0.5 cutoff, exceptions accumulate (I’ve labeled some of them).

Anyway, I could go on; if you are interested in this “artisanal” democracy dataset (or in creating your own version of these scores), take a look at the paper, and use the package – and let me know if it works!

(Update 3/25/2016 - some small edits for clarity).

(Update 3/28 - fixed code error).

(Update 3/30 - re-released the code, and updated the graphs, to fix one small mistake with the replication data for the bnr variable).

(Code for this post is available here. Some of it depends on a package I’ve created but not shared yet, so you may not be able to replicate it all.)