Benjamin Lauderdale

Pragmatic Social Measurement

Tue, 15 Sep 2026 00:00:00 +0000

This is a draft manuscript for a book about measuring social science concepts. The first draft was available on my personal website starting in autumn 2021. I was then occupied with academic administration for four years and was unable to make any progress on revision. This second draft has been available since autumn 2026. Relative to the first publicly available version, this current version has fewer outright errors, grammatical problems, inconsistencies of UK and US spelling, infelicities of language and mathematical expression, missing and inconsistently formatted citations, hideous regression outputs, and other rough edges. But it still has a fair number of each of these. Feedback and suggestions to (b.lauderdale@ucl.ac.uk) remain very much welcome.

UCL POLS0013: Measurement in Data Science

Sun, 01 Sep 2019 00:00:00 +0000

Please visit the module website at https://uclspp.github.io/POLS0013/index.html

Studying Individual-Level Attitudes Towards Important Problems Using Pairwise Comparisons

Fri, 12 Dec 2025 00:00:00 +0000

How can we measure citizens’ attitudes towards political problems in a way that generates data which are comparable across individuals, across countries, and across time? In this paper, I show how to measure these attitudes using pairwise comparisons, such that the assessments can be used as either individual-level dependent or independent variables for subsequent analyses. Even where it is infeasible for respondents to answer sufficient pairwise comparisons to recover a respondent-level ranked order, model-based multiple imputation enables the analyses that would be possible if all respondents compared all possible pairs of categories. I validate this approach using assessments of political problems in the UK according to the categories of the Comparative Agendas Project. By enabling individual-level analysis on researcher-defined categories with accessible questions, these methods make supplementing or replacing the typical most important problem and issue questions asked on national election studies with pairwise comparisons broadly advantageous for future research.

Idiosyncratic Issue Opinion and Political Choice

Mon, 01 Dec 2025 00:00:00 +0000

What is the nature of mass opinion on public policies? And what role do citizens’ policy opinions play in their political choices? This book re-examines these questions, which lie at the heart of fundamental debates concerning whether democratic elections can make policymakers responsive to citizens’ policy preferences. Prevailing answers to these questions tend to reflect one of two contrasting perspectives. The ‘ideological voter’ account suggests that citizens’ opinions across different policies are ideologically organised, so that political choice reduces to comparing positions on a small number of ideological dimensions. This simplifies democratic policy responsiveness. The ‘innocent voter’ account suggests that most citizens lack meaningful policy opinions on most issues. They express policy opinions that lack stability and ideological organisation, except where they simply mimic the policies espoused by the parties they support. This severely limits democratic policy responsiveness. This book argues for a third perspective: an ‘idiosyncratic voter’ account. This says that citizens develop meaningful policy opinions on different sets of issues, but the combinations of opinions they form on those issues are often idiosyncratic rather than ideologically organised. An analysis of panel survey data from Britain shows that both the ideological and innocent voter accounts do explain important aspects of mass policy opinion and political choice. Nonetheless, idiosyncratic policy opinion is also widespread and significantly shapes political choices. This means that idiosyncratic opinion serves alongside ideological opinion as an additional starting point for democratic policy responsiveness. Yet it also means that electoral politics is highly multidimensional and therefore volatile.

Inferring Individual Preferences from Group Decisions: Judicial Preference Variation and Aggregation in Asylum Appeals

Tue, 18 Nov 2025 00:00:00 +0000

While many democracies nominate partisan judges, empirical research has struggled to assess whether such judges adhere to Aristotle’s maxim that like cases should be treated alike. One fundamental problem hindering empirical research is that many courts only report decisions of panels, not the opinions of individual judges. We propose a methodology that tests which of several decision-theoretic models of group decision-making best fit the panel decisions, infers judges’ individual preferences, and quantifies the proportion of cases that would be decided differently if the courts’ consensus were consistently applied (an inconsistency rate). Applying this methodology to the Swiss asylum appeal process, where cases are assigned conditionally at random and have a common, unidimensional structure, we find a persistent inconsistency rate of about 5% due to variation in decision-making between judges, and that judges’ estimated preferences are correlated with party membership in expected ways.

Winning Votes and Changing Minds: Do Populist Arguments Affect Candidate Evaluations and Issue Preferences?

Tue, 22 Apr 2025 00:00:00 +0000

Populist rhetoric – presenting arguments in people-centric, anti-elite and ‘good v. evil’ frames – is said to provide populist parties and candidates with an advantage in electoral competition. Yet, identifying the causal effect of populist rhetoric is complicated by its enmeshment with certain positions and issues. We implement a survey experiment in the UK (n≈9,000), in which hypothetical candidates with unknown policy positions randomly make (non-)populist arguments, taking different positions on various issues. Our findings show that, on average, populist arguments have a negative effect on voters’ evaluations of the candidate profiles and no effect on voters’ issue preferences. However, populist arguments sway voters’ issue preferences when made by a candidate profile that voters are inclined to support. Among voters with strong populist attitudes, populist arguments also do not dampen candidates’ electoral viability. These findings suggest that populist rhetoric is useful in convincing and mobilizing supporters but detrimental in expanding electoral support.

Polarization over the Priority of Political Problems

Mon, 03 Mar 2025 00:00:00 +0000

What drives ideological division about political problems? When prioritising which problems are most in need of redress, voters might disagree about the severity of individual outcomes that constitute such problems; the prevalence of those problems; or whether such problems are amenable to solution by government action. We field a large survey experiment in the UK and US and develop a new measurement approach which allows us to evaluate how ideological disagreements change when respondents consider the individual badness, social severity, and priority for government action of a set of 41 political problems. We find that large ideological divergences are observed in beliefs about social severity and priority for government action, not individual problem badness, and only in the US. An important implication of these results is that perceptions of problem prevalence are a key source of polarization over problem-prioritization in the US.

"Moderates"

Mon, 20 Jan 2025 00:00:00 +0000

Many Americans express a mix of conservative and liberal views across issues. Prior research indicates these voters are cross-pressured. A recent, influential article “Moderates” (Fowler et al. 2023) argues that these voters instead largely have centrist views on issues. To reach this conclusion, “Moderates” develops a method to determine which voters’ views are well-summarized by left-right ideology. “Moderates” finds that most voters’ views are, and therefore concludes that the large number of voters with centrist estimated ideologies—“moderates”—must hold centrist views on issues. We show that this method systematically overstates how many voters’ views are well-summarized by left-right ideology: it assumes voters are ideologues unless they either answer questions randomly or form a single cluster with distinctive views. In simulations, we show this bias is large. The article’s core conclusion that voters who express a mix of conservative and liberal views can be inferred to support centrist policies therefore remains in doubt.

Liberals and Conservatives Rely on Very Similar Sets of Foundations When Comparing Moral Violations

Wed, 31 Jul 2024 00:00:00 +0000

Applications of Moral Foundations Theory (MFT) in political science have revealed differences in the degree to which liberals and conservatives explicitly endorse five core moral foundations of care, fairness, authority, loyalty and sanctity. We argue that differences between liberals and conservatives in their explicit ratings of abstract and generalized moral principles do not imply that citizens with different political orientations have fundamentally different moral intuitions. We introduce a new approach for measuring the importance of the 5 moral foundations by asking UK and US survey respondents to compare pairs of vignettes describing violations relevant to each foundation. We analyse responses to these comparisons using a hierarchical Bradley-Terry model which allows us to evaluate the relative importance of each foundation to individuals with different political perspectives. Our results suggest that, despite prominent claims to the contrary, voters on the left and the right of politics share broadly similar moral intuitions.

The Effects of Party Labels on Vote Choice with Realistic Candidate Differentiation

Wed, 22 May 2024 00:00:00 +0000

In this paper we test how much party labels influence vote choices between candidates when voters have access to realistically distributed information about candidate positions and demographics. We do not seek to adjudicate a long-running debate about the role of party labels, but present some nuances on the two archetypal theoretical views on vote choices. We use data from the Representative Audit of Britain (RAB) and the British Elections Study (BES) to generate electoral match-ups between randomly selected Conservative versus Labour candidates, with only half of respondents seeing party labels in addition to candidates’ positions and demographics. For our experiment fielded in October 2021, we find negligible to moderate effects of party labels on vote choices. Our results suggest the information on candidate positions and party labels largely act as substitutes for one another, with only modest changes when party labels are made explicit.

Public Preferences over Changes to the Composition of Government Tax Revenue

Fri, 17 May 2024 00:00:00 +0000

How governments raise tax revenue is at the core of domestic political conflict. Public opinion towards taxation is measured generally and qualitatively by many surveys, but previous research has not closely linked public preferences to the budget problem faced by governments regarding how best to raise or cut a marginal quantity of revenue. We present results from a novel tax preference experiment in which UK respondents are given choices over different tax ‘levers’ that are expected to raise or cut equal revenue. We find that while different tax levers vary substantially in their popularity, there is a ‘hidden consensus’ regarding different tax levers across income levels and partisanship of the respondents.

The Variable Persuasiveness of Political Rhetoric

Mon, 01 Jan 2024 00:00:00 +0000

Which types of political rhetoric are most persuasive? Politicians make arguments that share common rhetorical elements, including metaphor, ad hominem attacks, appeals to expertise, moral appeals, and many others. However, political arguments are also highly multidimensional, making it difficult to assess the relative persuasive power of these elements. We report on a novel experimental design which assesses the relative persuasiveness of a large number of arguments that deploy a set of rhetorical elements to argue for and against proposals across a range of UK political issues. We find modest differences in the average effectiveness of rhetorical elements shared by many arguments, but also large variation in the persuasiveness of arguments of the same rhetorical type across issues. In addition to revealing that some argument-types are more effective than others in shaping public opinion, these results have important implications for the interpretation of survey-experimental studies in the field of political communication.

The Future of Democracy in the UK. Public Attitudes and Policy Responses.

Thu, 30 Nov 2023 00:00:00 +0000

Over the last three years, a Constitution Unit team has conducted detailed research into public attitudes to democracy in the UK. This has comprised two large-scale surveys of the UK population, conducted in summer 2021 and summer 2022, and the Citizens’ Assembly on Democracy in the UK, which met over six weekends in late 2021. Previous reports have set out the findings of each part of the project. This final report pulls these findings together, supplementing them with extensive new analysis. It also reflects on policy implications.

Public Preferences for Integrity and Accountability in Politics. Results of a Second Survey of the UK Population

Fri, 31 Mar 2023 00:00:00 +0000

Public confidence in our democratic process is at a low ebb. Years of contestation over Brexit raised fundamental questions about how democracy in the UK should work. Concerns have been heightened further over the past 18 months by the Owen Paterson affair, the ‘Partygate’ scandal, and a premiership that crashed and burned in under 50 days. Many voters were alarmed by how Boris Johnson sought to cling to power, while others were equally perturbed that a democratically elected leader was felled without recourse to the electorate. Many commentators now view political reform as essential for restoring equilibrium and confidence, while others think rebuilding trust requires not tinkering with process, but delivering policy outcomes.

A Leader Who Sees the World as I Do: Voters Prefer Candidates Whose Statements Reveal Matching Social-Psychological Attitudes

Tue, 21 Mar 2023 00:00:00 +0000

Politicians are increasingly able to communicate their values, attitudes, and concerns directly to voters. Yet little is known about which of these signals resonate with voters and why. We employ a discrete choice experiment to investigate whether and which social-psychological attitudes predict how adult British voters respond to corresponding attitudinal signals communicated by candidates in hypothetical social media posts. For all attitudes studied, covering social feelings (trust, collective nostalgia), social perceptions (nationalism, populist sentiment), and social commitments (national identification, authoritarianism, egalitarianism), we find that participants are much more likely to vote for candidates who signal proximity to their own attitudinal position and less likely for candidates who signal opposing views. The strongest effects were observed for national identification, authoritarianism, and egalitarianism, indicating the importance of commitment to a shared group and to particular principles for distributing power and resources within and between groups. We further demonstrate that social-psychological attitudes are not acting as mere proxies for participants’ past votes or left–right ideology. Our results extend adaptive followership theory to incorporate preferences concerning intragroup coordination and intergroup hierarchy, while highlighting the social-psychological dynamics of political communication that may transcend the concerns of particular election cycles.

What Kind of Democracy Do People Want? Results of a Survey of the UK Population

Mon, 31 Jan 2022 00:00:00 +0000

The past decade in UK politics has raised fundamental questions about the kind of democracy we want to live in. What role should be played by referendums? Where should the balance of power lie between government and parliament? How far should the courts be involved in adjudicating disputes or upholding basic rules? What standards of behaviour do we expect from our politicians, and how should these be maintained?

To address these questions, we conducted a major new survey of UK public opinion in the summer of 2021. We asked for people’s views on the fundamentals of the democratic system and how democracy is working in the UK today. The survey was fielded by YouGov in late July 2021, with a sample of almost 6,500 people, representative of the voting age population across the whole of the UK.

Pairwise Comparisons as a Scale Development Tool for Composite Measures

Thu, 06 Jan 2022 00:00:00 +0000

Composite scales are widely used for measuring aggregate social science concepts. These often consist of linear indices obtained as the weighted sum of a set of relevant indicators. However, selecting coefficients (or weights) that reflect the substantive importance of each indicator towards the concept of interest is a difficult task. We propose a method for the generation of linear indices for aggregate concepts based on pairwise comparisons. Specifically, we ask a group of subject-matter experts to perform a series of pairwise comparisons, with respect to the concept of interest, between profiles displaying different combinations of indicators. This allows us to estimate coefficients for each indicator that provide a linear approximation to how experts make the pairwise evaluations. As we show, the method makes it straightforward to assess intercoder reliability, while being a more accessible task than directly asking experts for coefficients. We demonstrate our method with an application to the concept of ‘productive ageing’, including a cross-cultural comparison of weighting schemes derived from a group of Italian and a group of South Korean experts on this concept.

Measuring Attitudes towards Public Spending using a Multivariate Tax Summary Experiment

Sat, 01 Jan 2022 00:00:00 +0000

It is difficult to measure public views on tradeoffs between spending priorities because public understanding of existing government spending is limited and the budgetary problem is complicated. We present a new measurement strategy using UK taxpayer summaries as the baseline for a continuous treatment, multivariate choice experiment. The experiment proposes deficit neutral bundles of changes in spending and taxation, allowing us to investigate attitudes towards modifications to the existing budget. We then use a structural choice model to estimate public preferences over 13 spending categories and the taxation level, on average and as a function of respondent attributes. We find that the UK public favours paying more in tax to finance large spending increases across major budget categories; that spending preferences are multidimensional; and that younger people prefer lower levels of taxation and spending than older people. Finally, we report a pre-registered out-of-sample validation of the estimates from the experiment.

Can Citizens Guess How Other Citizens Voted Based on Demographic Characteristics?

Mon, 13 Sep 2021 00:00:00 +0000

How well do citizens understand the associations between social groups and political divisions in their societies? Previous research has indicated systematic biases in how the demographic composition of party supporters are perceived, but this need not imply that citizens misperceive the likely voting behaviour of specific individuals. We report results from two experiments where subjects were provided with randomly selected demographic profiles of respondents to the 2017 British Election Study (BES) and then asked to assess either (1) which party that individual was likely to have voted for in the 2017 UK election or (2) whether that individual was likely to have voted Leave or Remain in the 2016 UK referendum on EU membership. We find that, despite substantial overconfidence in individual responses, on average citizens’ guesses broadly reflect the actual distribution of groups supporting the parties and referendum positions.

The Emergence of Coherent Political Choices from Incomplete Issue Preferences

Fri, 23 Jul 2021 00:00:00 +0000

Note: This working paper has been incorporated into our book Idiosyncratic Issue Opinion and Political Choice.

We provide the clearest evidence to date for an ‘issue publics’ account that reconciles conceptions of democracy premised on policy voting with longstanding evidence that citizens typically lack ‘real’, stable opinions on many policy issues. In this account, voters make coherent political choices based on the varying subsets of issues about which they as individuals care and form stable attitudes. Leveraging a novel three-wave panel survey experiment that repeatedly measures British respondents’ issue positions and their political choices between hypothetical candidates taking randomised issue positions, we provide the first direct evidence that higher opinion-stability issues have greater causal effect on citizens’ political choices. We then evidence hitherto untested issue publics implications: even restricted to issue-based considerations and given average issue opinion instability, individuals’ candidate choices are predictable and, when candidates contrast clearly on issues respondents’ care about, highly temporally stable. Aggregate issue opinion instability does not prohibit coherent issue voting.

Republican-Majority Appellate Panels Increase Execution Rates for Capital Defendants

Wed, 21 Apr 2021 00:00:00 +0000

We use the quasi-random assignment of cases to three-judge panels on the US Courts of Appeals to assess the consistency of adjudication of death penalty appeals. We find clear evidence that panels apply different standards depending on whether a majority of the panel was appointed by Democratic or Republican presidents. Unlike previous work on panel effects in the US Courts of Appeals, we show that these effects persist to the end of the process of adjudication. Since the the early 1980s, the probability of ultimate execution has been increased for inmates when their first Court of Appeals case was assigned to a panel with a majority of Republican appointees.

Things that I have learned by being a journal editor

Mon, 01 Jun 2020 00:00:00 +0000

I have just completed a 3.75 year tenure as an associate editor of the American Political Science Review. Over that time, as one of six associate editors, I have managed the review process for 742 manuscripts, about 200 per year. Here are some departing thoughts on the job in no particular order and with no overarching thesis.

I wish the new editorial team well. Being an editor is a constant, low-level source of stress. There is always a queue of editorial activity that you could be doing. Even though it is always something that you could put off until tomorrow if there is something more urgent, the fact that it never done is a constant source of nagging stress. The manuscript in the queue that is currently longest in review is always one that has been under review for too long. When you add to that the fact that you are constantly having to make difficult decisions (on which careers may depend) it is fundamentally not a fun job.
The ability of editors to make sound decisions is fundamentally dependent on reviewers taking their task seriously, and the vast majority of reviewers do so. While many journals struggle to get reviewers, the rate at which reviewers accepted our invitations was consistently high. I had remarkably few cases of intemperate or inappropriate reviews, although of course review quality does vary! The best reviews are remarkably detailed and thoughtful, but more importantly, most reviews were good enough to make me comfortable about the vast majority of the decisions. I am grateful for all the reviews that I received, many of them from political scientists I have never met.
Unfortunately, if you are handling the volume of manuscripts that the APSR handles, with the very low acceptance rate that the journal maintains, the only thing one can be very confident of is that some of the decisions would not have come out the same way if we re-ran the review process. Even beyond the judgment calls by reviewers and editors that might have come out another way, there are decisions which are simply mistakes, one way or the other, because the reviewers and editors err. Some of these become apparent, some do not. I had a few difficult exchanges with authors and reviewers about close calls, but remarkably few.
The experience of being an editor has been useful for improving how I present my own research. I learned things about the field and about the peer review process. I have had less time to do research for the last four years, but have also become far more efficient.
Most of my compensation from APSA went into supporting my research, primarily running survey experiments. Optimising for less time but more money with which to do research has contributed to shifting my research in new directions that I am pleased with.
Editorial work did not remain intellectually engaging for the entire term that I was editor. The hope is that you will get to read and think about lots of the latest and best research in the field. Unfortunately, given the submission rate, actually spending that much time thinking about each manuscript would require spending far too much time overall, so there is a strong incentive to be the most efficient classifier that you can be. Is this an APSR paper or not? At a certain point, like a machine learning classifier, you start to lose the ability to articulate how it is that you know the answer to this question. This is bad for two reasons. First, it makes writing the decision letters more difficult. Second, if you stop carefully thinking through why you are making the decisions you are making, it is very likely that you will let your potential biases go unreflected upon.
I would make the same decision to become an APSR editor again, knowing what I know now. Nonetheless, I have no intention to agree to be a journal editor again. From a reciprocity perspective I continue to believe that being an editor at some point was appropriate given all the editorial work that I have created and will create for others through my own submissions. But I have done my bit now, and then some. The amount of editorial work that I have done is a very healthy multiple of the amount I will generate for others to do over my career.
As a matter of personal taste, I would have preferred to be an editor for a less “prestigious” journal where more of the focus would have been on correctness and less on importance. The most difficult part of being an editor (or a reviewer) for a journal like the APSR is adjudicating the ineffable quality of being important enough to be in the APSR. A few of the papers that get submitted clearly meet this criterion, but not nearly enough to fill the journal. The most difficult decisions involve trading importance off against other qualities of papers (see item 15 below).
It is better to desk reject more, but it is “easier” to send papers out (at least in an immediate sense). Each paper you send out today takes 3 reviewers out of the pool of those who are available for the next four months (I generally tried not to ask for reviews from the same reviewer within 3 months of receiving the last one, excluding second round reviews). The set of reviewers that you have not recently asked for reviews is a precious resource because reviewers’ time is a precious resource. It is depressingly common that when you identify the ideal reviewers for a manuscript, most of them are unavailable because they are currently reviewing or have just reviewed another manuscript for the journal.
It is difficult to maintain a consistent standard for desk review that is not very low or very unevenly applied across areas of research. I desk rejected 23% of the manuscripts that made it to me from the main editor, who had already desk rejected a proportion. Maybe this sounds like a lot to you, but keep in mind that the APSR publishes something like 5% of initial submissions. The decision to desk reject is just a statement that you are sure the submission is not in the top 5%, not that you are precisely sure that it is in the bottom X%, where X is the proportion you are desk rejecting. The problem is that it is easier to quickly identify which manuscripts have a chance in the research areas that you are most familiar with, which makes it possible to be more aggressive at desk rejecting manuscripts in those areas. This is “unfair” if you view desk reject versus reject with reviews as an outcome that we should worry about with respect to fairness. This proposition is itself debatable. The tradeoff between time under review and feedback from reviews makes it unclear who is really better off (and of course much depends on the usefulness of the reviews).
I would have been a better editor if I were a better professional networker. I do not particularly enjoy going to conferences or otherwise engaging in networking activities. This means I know fewer people than I might, which brought a penalty when it came to selecting reviewers. That said, having been an editor, I have a much broader knowledge of scholars in the field, even the ones who never submitted a manuscript, but I discovered while looking for reviewers.
There are many manuscripts that are submitted to the APSR after being first rejected at the AJPS, and I often discovered this when invited reviewers told me that they had already reviewed the paper. Some reviewers refuse to review the same manuscript multiple times for different journals because they think it is unfair to the authors. I tried to fight against this as a reason to refuse to review, with middling success. If there is a problem with the manuscript, especially one that might not be obvious to an editor but which is clear to someone with expertise on that specific question, it is (imho) insane for that information to be withheld from the editor of the second journal that the authors submit to in order to ensure a “fair” peer review lottery. What if only one person has noticed some fatal flaw in a paper? Arguably the most important function of peer review is to minimise the number of published papers whose core claims are incorrect. Authors are not entitled to disjoint random draws from the pool of potential reviewers.
It is very common for invited reviewers to decline to review when they are on sabbatical. While I certainly have some sympathy for wanting to carve out time for research, I think that if you are on a research-active leave (that is, not on parental leave) during which you would submit journal articles or book manuscripts for review by other scholars, you should probably also be available to review. Of course the usual degree of discretion applies: no one is under any obligation to review any particular manuscript they are invited to review. I understand that circumstances vary and sometimes reviewing is not possible for various reasons, but the reciprocity argument–if you are making work for other reviewers you should be available to review–looms large for me. I should note here that I did not argue with anyone about their decision to decline, since I am not entitled to justifications for these decisions and many people will have had further constraints beyond the ones that they quickly typed into the text field that popped up when they declined. Perhaps for transparency I should note here that I only reviewed 11 manuscripts for other journals while I was an editor, which is a very light load over nearly 4 years! Mostly I did not get very many invites (editor solidarity!), but I did apply a higher bar for fit than I previously applied and I declined nearly all invites from journals to which I have never submitted articles.
The ordinal prompt to reviewers that has long been used by the APSR and many other journals is badly designed. The choices of “Accept”, “Minor Revision”, “Major Revision” and “Reject” are not good at extracting the relevant pieces of information from reviewers. This becomes immediately clear when you compare these responses to the review texts. Among other problems, there are two distinct questions that are being flattened into one. (1) Should the best version of this paper be published in this journal? (2) How far from that ideal version of the paper is the submitted manuscript? In my experience, “Minor Revision” is used by reviewers to mean everything from “This is a superb manuscript that needs a few minor edits that you should definitely publish in the APSR” to “This is ok scholarship and there is not much that could be done to improve it, but it definitely does not belong in the APSR”. “Major Revision” is used by reviewers to mean everything from “This is potentially groundbreaking work but it needs some significant revision before you should publish it in the APSR” to “This manuscript is a complete mess, and even if the author fixed it, it would not belong in the APSR”. You can usually figure out which the reviewer means by reading the review, but it would make sense to just ask the two questions separately.
In making decisions, I tried to keep in mind three criteria for publication: novelty, validity, and importance. Is this new? Is this true? How many “people” (heavily weighted towards political scientists) will care about this? To be published in the APSR, a manuscript needs to have a non-zero value on all three of these, significant strength in two of three, and an honest statement of all three. That is, a paper that does something very new and brings very strong evidence for its claims can get away with being on a less important question. A paper that is very new and very important can get away with somewhat weaker evidence (if the limitations are clearly stated and better evidence is not available). A paper that brings very strong evidence on a very important question can get away with being only modestly novel. This leaves room for lots of different kinds of papers, on different kinds of questions, with different kinds of methods.
The common “where is the theory?” reviewer criticism is often an “importance” concern in disguise. Why should I care about <congress, elections, bureaucracy, opinion, whatever> in <place> particularly? The answer is often that they speak to some broader puzzle in the field. There are certainly some reviewers that think that an APSR paper needs a section called “Theory” and a claim that a new theory is being presented, but most reviewers just want an engaging articulation of what is at stake and where it fits into what we already know.

Finally, a broad point about the APSR and the role of journals like it in political science. My conclusion at the end of being an editor of this journal is that the field might be better off without journals like the APSR, but I am honestly not sure. Many of the obvious problems with the current political science journal system are driven by the fact that having “top journals”, and more generally a status hierarchy thereof, means a tremendous amount of scholarly energy is directed through the peer review process towards distributing professional rewards to researchers. I am personally sympathetic to the view that this distracts from what I take to be the more fundamental function of peer review, which is quality control. A status hierarchy in journals creates incentives for overclaiming in manuscripts and also for authors to submit their manuscripts to all the “top journals” sequentially, which creates substantial costs that are then distributed across authors, reviewers and editors.

A Choice-Based Measure of Issue Importance in the Electorate

Tue, 25 Feb 2020 00:00:00 +0000

Measuring how much citizens care about different policy issues is critical for political scientists, yet existing measurement approaches have significant limitations. We provide a new survey-experimental, choice-based approach for measuring the importance voters attach to different positional issues, including issues not currently contested by political elites. We combine information from (i) direct questions eliciting respondents’ positions on different issues with (ii) a conjoint experiment asking respondents to trade-off departures from their preferred positions on those issues. Applying this method to study the relative importance of 34 issues in the UK, we show that British voters attach significant importance to issues like the death penalty which are not presently the subject of political debate and attach more importance to those issues associated with social liberal-conservative rather than economic left-right divisions.

2019 UK General Election MRP Post-mortem

Tue, 17 Dec 2019 00:00:00 +0000

The slide deck linked below reports an initial performance review for the YouGov MRP model of the 2019 UK general election. As I noted in a series of tweets the day after the election the overall performance was mixed. The headline Conservative seat prediction was too low (339 vs 365), but on many other metrics the model performed well, capturing many important features of how party vote shares changed across UK constituencies versus the previous election in 2017. I will be returning to this in the new year once sufficient data has been collected on reported vote to properly assess the details of any late swings.

Model-Based Pre-Election Polling for National and Sub-National Outcomes in the US and UK

Tue, 15 Oct 2019 00:00:00 +0000

We describe a strategy for applying multilevel regression and post-stratication (MRP) methods to pre-election polling. Using a combination of contemporaneous polling, census data, past election polling, past election results, as well as other sources of information, we are able to construct probabilistic, internally consistent estimates of national vote and the sub-national electoral districts that determine seats or electoral votes in many electoral systems. We report on the performance of three applications of the general framework conducted and publicly released in advance of the 2016 UK Referendum on EU Membership, the 2016 US Presidential Election, and the 2017 UK General Election.

Which outcome to the Article 50 process do the British people want?

Wed, 12 Dec 2018 00:00:00 +0000

This report contains a national and parliamentary constituency-level analysis of the British public’s preferences regarding the resolution of the current Article 50 withdrawal process from the European Union. The estimates provided here are based on the same modelling techniques that used in the YouGov 2017 UK General Election Model, which correctly predicted the hung parliament and 93% of individual seats. This approach allows us to not just calculate national support for different possible outcomes of the Brexit process, but to use demographic, geographic and political patterns in support for different parties across the UK to assess views in each parliamentary constituency. This report was prepared using polling data from 27 November to 6 December, in advance of the planned 11 December 2018 House of Commons vote on the deal negotiated and agreed by the UK government with the European Commission.

You cannot trick financial markets into solving your political problem if you tell the markets that this is the plan.

Thu, 22 Nov 2018 00:00:00 +0000

This post was co-authored with Andy Eggers (Nuffield College, Oxford)

Will Theresa May’s Brexit deal win the support of Parliament? A view is emerging in Westminster that May’s EU withdrawal plan will succeed in the same way that TARP (the Troubled Asset Relief Program) cleared the U.S. Congress in September of 2008: an initial rejection is followed by a stock market crash, which concentrates legislators’ minds and clears the way for successful passage.¹ A market crash may indeed be just the thing some MPs need to secure their support for May’s withdrawal bill, whether because it convinces them of the bill’s merits or provides the cover they need to take a politically unpopular position.

Abstract for a paper I do not have time to write

Wed, 27 Jun 2018 00:00:00 +0000

What follows is an abstract for a paper that I do not have time to write, but which I think would be a useful contribution to the literature, assuming what follows is actually true. Please feel free to do the actual research to find out. Let me know!

Conjoint experiments have experienced explosive growth in political science. The standard methodology for analysing them in political science involves using linear regression methods to estimate Average Marginal Component Effects (AMCEs, Hainmueller, Hopkins & Yamamoto 2014). While this approach is attractive for deriving results related to clearly defined causal estimands, given the binary (sometimes ordered ternary) responses generated by forced choice conjoint experiments, limited dependent variable (LDV, eg logistic) regression methods have some potential advantages. These advantages derive from the fact that such models are likely to better describe the data generating process, as many conjoint experiments have strong effects and the bounds on the predicted probabilities are therefore important to fitting the data well. By virtue of fitting the data generating process better, LDV models may reduce the sensitivity of estimates to the choice of conjoint randomization. Where this is the case, LDV models can then be used to more reliably generate estimates of various quantities of interest, including AMCEs with respect to populations that are not the one implicitly defined by the conjoint randomization. This approach involves moving from narrowly estimating a particular causal estimand dictated by the conjoint randomization to estimating a more general behavioural model which is then projected (post-stratified) onto populations of interest in order to generate a wider range of causal estimands. The resulting tradeoff is one of additional model dependency for greater flexibility in the quantities of interest that can be modelled from a single experiment.

Decomposing Public Opinion Variation into Ideology, Idiosyncrasy and Instability

Thu, 01 Mar 2018 00:00:00 +0000

We propose a method for decomposing variation in the issue preferences that US citizens express on surveys into three sources of variability that correspond to major threads in public opinion research. We find that, averaging across a set of high profile US political issues, a single ideological dimension accounts for about 1/7 of opinion variation, individuals’ idiosyncratic preferences account for about 3/7, and response instability for the remaining 3/7. These shares vary substantially across issue types and the average share attributable to ideology doubles when a second ideological dimension is permitted. We also find that (unidimensional) ideology accounts for almost twice as much response variation (and response instability is substantially lower) among respondents with high, rather than low, political knowledge. Our estimation strategy is based on an ordinal probit model with random effects, and is applicable to other data sets that include repeated measurements of ordinal issue position data.

Never Let a Good Crisis Go to Waste: Agenda Setting and Legislative Voting in Response to External Shocks

Mon, 22 Jan 2018 00:00:00 +0000

When exogenous shocks make status quo policies less attractive, legislators be- come more tolerant to proposed alternatives that are further from their ideal in general political dimensions. This increases the discretion of legislative agenda-setters, and allows them to pass policy that would have been impossible in the absence of a crisis. We argue that this dynamic explains changes in voting patterns of the European Parliament during the period of the financial crisis, given control of the agenda-setting process by pro-integration actors. We observe voting coalitions increasingly dividing legislators along the pro-anti integration dimension of disagreement, but only in policy areas related to the crisis. In line with more qualitative assessments of the content of passed legislation, the implication is that pro-integration actors were able to shift policy further towards integration than they could have without the crisis.

An assessment of the causes of the errors in the 2015 UK general election opinion polls

Wed, 25 Oct 2017 00:00:00 +0000

The opinion polls that were undertaken before the 2015 UK general election underestimated the Conservative lead over Labour by an average of 7 percentage points. This collective failure led politicians and commentators to question the validity and utility of political polling and raised concerns regarding a broader public loss of confidence in survey research. We assess the likely causes of the 2015 polling errors. We begin by setting out a formal account of the statistical methodology and assumptions that are required for valid estimation of party vote shares by using quota sampling. We then describe the current approach of polling organizations for estimating sampling variability and suggest a new method based on bootstrap resampling. Next, we use poll microdata to assess the plausibility of different explanations of the polling errors. Our conclusion is that the primary cause of the polling errors in 2015 was unrepresentative sampling.

Submission to House of Lords Select Committee on Political Polling and Digital Media

Fri, 11 Aug 2017 00:00:00 +0000

I gave oral evidence to the House of Lords Select Committee on Political Polling and Digital Media on 5 September 2017. Both a transcript and video are available. I also submitted written evidence on an individual basis in response to the call for evidence for the inquiry which I will link from here when it is posted on the House of Lords website.

New Website

Wed, 26 Jul 2017 00:00:00 +0000

The summer is a great time for catching up on research, or for frittering away time on inessential infrastructure projects. After updating my RMarkdown templates for presentations and papers, I have just spent a few days migrating my website off of Wordpress onto Hugo. Hugo is a static site generator, which means that all the content management happens on my computer, and all that gets uploaded to my site are a collection of static pages. It is fast, and the content lives in tidy markdown files in a sane folder hierarchy on my Dropbox, so I can update the site from any of my computers.

Dyadic representation in a Westminster system

Mon, 01 Aug 2016 00:00:00 +0000

Is policy representation in contemporary Westminster systems solely a function of programmatic national parties, or does the election of legislators via single member districts result in MPs whose policy positions are individually responsive to public opinion in their constituencies? We generate new measures of constituency opinion in Britain and show that, in three different policy domains and controlling for MP party, the observed legislative behaviour of MPs is indeed responsive to constituency opinion. The level of responsiveness is moderate, but our results do suggest a constituency-MP policy bond which operates in addition to the well-known bond between voters and parties.

Patterns of Switching in the 2016 US Presidential Election

Sun, 13 Nov 2016 09:55:25 +0000

I am posting the slides and audio here from a talk I gave at the LSE about the election, one day before it happened. Some things in here are right, some things in here are wrong. The polling estimates I was talking about were the penultimate estimates posted at https://today.yougov.com/us-election/ so the numbers there now are a bit different. Most of the value here post-election is the estimates of which kinds of voters were switching R to D and D to R versus 2012. A proper post-mortem on the estimates overall is coming, but needs to wait for the final vote counts, which may be a few weeks. Polling methodology problems have gone back to being non-pressing, as they usually are, so we can all wait.

Estimating Vote-Specific Preferences from Roll-Call Data Using Conditional Autoregressive Priors

Tue, 23 Aug 2016 00:00:00 +0000

Recent research has demonstrated that the preferences of US Supreme Court justices are not simply unidimensional. We demonstrate a new approach to Bayesian preference estimation that estimates case-specific preferences for justices, using a conditional autoregressive model with legal similarity determining the correlation between justices’ preferences across cases. We employ the overlap in legal topics addressed in each case to identify the most relevant precedent cases to describe variation in revealed preferences across areas of the law. In applications that test theories of bargaining on the Court, these estimates enable stronger identification of variation in preferences while holding the composition of the Court constant. We show that Chief Justices from 1946 to 2005 strategically assign authorship to their colleagues in cases where those colleagues are more closely in agreement with the Chief Justice, and patterns of other justices joining those opinions are consistent with the idea that authors shape the content of opinions.

Partisan Disagreements Arising from Rationalization of Common Information

Fri, 02 Oct 2015 00:00:00 +0000

Why do opposing partisans sometimes disagree about the facts and processes that are relevant to understanding political issues? One explanation is that citizens may have a psychological tendency toward adopting beliefs about the political world that rationalize their partisan preferences. Previous quantitative evidence for rationalization playing a role in explaining partisan factual disagreement has come from cross-sectional covariation and from correction experiments. In this paper, I argue that these rationalizations can occur as side effects when citizens change their attitudes in response to partisan cues and substantively relevant facts about a political issue. Following this logic, I motivate and report the results of a survey experiment that provides US Republicans and Democrats with information that they will be inclined to rationalize in different ways, because they have different beliefs about which political actors they should agree with. The results are a novel experimental demonstration that partisan disagreements about the political world can arise from rationalization.

Brexit Referendum MRP Post-mortem

Thu, 28 Jul 2016 11:33:04 +0000

In the lead up to the UK referendum on EU membership, Doug Rivers and I posted an analysis of several weeks of YouGov polling data, using a methodology called multilevel regression and post-stratification (MRP). This is a different approach to analysing polling responses than the approach YouGov uses to analyse most of its UK polls, including those released immediately before and after the referendum on 23 June. The MRP approach, in addition to yielding several interesting findings that we discussed in that post on YouGov’s site regarding the interactions of age, educational qualifications, party and referendum vote, also aims to better correct for demographic imbalances in raw polling samples. Now that we know the results, we can say that the MRP analysis provided a better, if still not perfect, estimate of the result of the election than conventional methods used by YouGov and most other pollsters.

An update on journal review debt

Thu, 28 Jul 2016 11:00:22 +0000

A couple years ago, I wrote a post on my journal review debt, which I defined as the difference between the number of peer reviews I had completed and the number I had caused other political scientists to write. I am going to be an Associate Editor for the American Political Science Review starting September 1, which is going to mess up this calculation of journal review debt because it does not take into account editorial work (an omission for which I will shortly be receiving my comeuppance). So before things get too much more complicated, here is an update of the graph from a couple years ago.

Measuring Political Positions from Legislative Speech

Wed, 04 Jan 2017 00:00:00 +0000

Existing approaches to measuring political disagreement from text data perform poorly except when applied to narrowly selected texts discussing the same issue and written in the same style. We demonstrate the first viable approach to scaling the entire speech corpus of a legislature, producing valid legislator-specific scores as well as extensive information about the evolution of speech polarization and politically loaded language. In the Irish Dail, we show that the dominant dimension of speech variation is government-opposition, with ministers more extreme on this dimension than backbenchers. In the US Senate, we estimate a dimension that has moderate within-party correlations with scales based on roll-call votes and campaign donation patterns, however we observe greater overlap across parties in speech positions than roll-call positions and partisan polarization in speeches varies more clearly in response to major political events.

Crowd-Sourced Text Analysis: Reproducible and Agile Production of Political Data

Thu, 04 Aug 2016 00:00:00 +0000

Empirical social science often relies on data that are not observed in the field, but are transformed into quantitative variables by expert researchers who analyze and interpret qualitative raw sources. While generally considered the most valid way to produce data, this expert-driven process is inherently difficult to replicate or to assess on grounds of reliability. Using crowd-sourcing to distribute text for reading and interpretation by massive numbers of non-experts, we generate results comparable to those using experts to read and interpret the same texts, but do so far more quickly and flexibly. Crucially, the data we collect can be reproduced and extended transparently, making crowd-sourced datasets intrinsically reproducible. This focuses researchers’ attention on the fundamental scientific objective of specifying reliable and replicable methods for collecting the data needed, rather than on the content of any particular dataset. We also show that our approach works straightforwardly with different types of political text, written in different languages. While findings reported here concern text analysis, they have far-reaching implications for expert-generated data in the social sciences.

Simulating Counterfactual Representation

Wed, 04 Jan 2017 00:00:00 +0000

We show how to use multilevel modeling and post-stratification to estimate legislative outcomes under counterfactual representation schemes that e.g. boost the representation of women or translate votes into seats differently. We apply this technique to two research questions: (1) Would the U.S. Congress be less polarized if state delegations were formed according to the principle of party proportional representation? (2) Would there have been stronger support for legalizing same-sex marriage in the U.K. House of Commons if Parliament more closely reflected the population in gender and age?

Report of the Inquiry into the 2015 British general election opinion polls

Thu, 31 Mar 2016 00:00:00 +0000

The opinion polls in the weeks and months leading up to the 2015 General Election substantially underestimated the lead of the Conservatives over Labour in the national vote share. This resulted in a strong belief amongst the public and key stakeholders that the election would be a dead heat and that a hung-parliament and coalition government would ensue.

In historical terms, the 2015 polls were some of the most inaccurate since election polling first began in the UK in 1945. However, the polls have been nearly as inaccurate in other elections but have not attracted as much attention because they correctly indicated the winning party.

Combining national and constituency polling for forecasting

Tue, 01 Mar 2016 00:00:00 +0000

We describe a method for forecasting British general elections by combining national and constituency polling. We reconcile national and constituency estimates through a new swing model.

Comparing Strategies for Estimating Constituency Opinion from National Survey Samples

Wed, 17 Feb 2016 00:00:00 +0000

Political scientists interested in estimating how public opinion varies by constituency have developed several strategies for supplementing limited constituency survey data with additional sources of information. We present two evaluation studies in the previously unexamined context of British constituency-level opinion: an external validation study of party vote share in the 2010 general election and a cross-validation of opinion toward the European Union. We find that most of the gains over direct estimation come from the inclusion of constituency-level predictors, which are also the easiest source of additional information to incorporate. Individual-level predictors combined with post-stratification particularly improve estimates from unrepresentative samples, and geographic local smoothing can compensate for weak constituency-level predictors. We argue that these findings are likely to be representative of applications of these methods where the number of constituencies is large.

Under-performing, Over-performing, or Just Performing? The Limitations of Fundamentals-based Presidential Election Forecasting

Wed, 01 Jul 2015 00:00:00 +0000

U.S. presidential election forecasts are of widespread interest to political commentators, campaign strategists, and the public. We argue that most fundamentals-based political science forecasts overstate what historical political and economic factors can tell us about the likely outcome of a forthcoming presidential election. Existing approaches generally overlook uncertainty in coefficient estimates, decisions about model specification, and the translation from popular vote shares to Electoral College outcomes. We introduce a novel Bayesian forecasting model for state-level presidential elections that accounts for each of these sources of error, and allows for the inclusion of structural predictors at both the national and state levels. Applying the model to presidential election data from 1952 to 2012, we demonstrate that, for covariates with typical amounts of predictive power, the 95% prediction intervals for presidential vote shares should span approximately +/- 10% at the state level and +/- 7% at the national level.

A Thought Experiment Regarding Experimental Ethics

Mon, 27 Oct 2014 20:42:01 +0000

The current controversy about a large scale experiment conducted in Montana by Stanford and Dartmouth political scientists raises several issues about research ethics in political science. To see a scan of the mailer that was sent to a random subset of Montana registered voters, follow this link.

Many of the objections I have read specifically refer to the form of the mailer. I am not going to engage with those objections here. I am interested in whether any experiment conveying the same information about candidates was necessarily objectionable, which is relevant for assessing whether the broad class of electoral field experiments are ethically problematic.

Scaling Meaningful Political Dimensions Using Texts and Votes

Fri, 07 Feb 2014 00:00:00 +0000

Item response theory models for roll-call voting data provide political scientists with parsimonious descriptions of political actors’ relative preferences. However, models using only voting data tend to obscure variation in preferences across different issues due to identification and labeling problems that arise in multidimensional scaling models. We propose a new approach to using sources of metadata about votes to estimate the degree to which those votes are about common issues. We demonstrate our approach using votes and opinions from the U.S. Supreme Court, using Latent Dirichlet Allocation to discover the extent to which different issues were at stake in different cases and estimating justice preferences within each of those issues. This approach can be applied using a variety of unsupervised and supervised topic models for text, community detection models for networks, or any other tool capable of generating discrete or mixture categorization of subject matter from relevant vote-specific data.

Journal Review Debt

Fri, 18 Apr 2014 13:01:21 +0000

For a while, I have wondered just how many more peer reviews I have caused to be written than I have written myself. I suspect that this kind of journal review debt is more or less inevitable as an early-career scholar. So rather than write a review that is due today, I decided to go back through my records to figure this out before it became too overwhelming to do so. It ought to be easier to keep these records going forward than it was to find all those old rejections in my email.

A Partisan Gap in the Supply of Female Potential Candidates

Tue, 01 Apr 2014 00:00:00 +0000

A partisan disparity in women representatives in the US House emerged in the 1980s and has continued to grow in magnitude. We show that this pattern closely mirrors the emergence of a partisan disparity in the fraction of women in the US public with the typical characteristics of high-level officeholders. Our analysis indicates that the fraction female in the Democratic pool of potential candidates is now two to three times larger than in the Republican pool of potential candidates. Given the current association of party identification with gender and other characteristics, this gap is more likely to increase than decrease over the coming decade, with potential consequences for the descriptive and substantive representation of women in American politics.

Does Inattention to Political Debate Explain the Polarization Gap Between the U.S. Congress and Public?

Wed, 23 Jan 2013 00:00:00 +0000

Recent studies of the U.S. Congress have demonstrated a substantial difference in partisan polarization between legislators’ votes and citizens’ survey responses about those votes. But perhaps public polarization would increase if citizens were more attentive to political debates in Congress? Using matching techniques on natural variation in citizens’ political information levels, I show that citizens who are informed about the partisan alignment of issues have a similar preference distribution to Congress, even after the former are re-weighted to resemble the entire public along salient political, social, and demographic dimensions. In contrast, using a survey experiment, I show that cue and argument treatments only partially reduce the discrepancy between the views expressed by the public and the voting behavior of Congress on the same issues. Both experimental and observational studies have significant limitations for measuring counterfactuals involving public opinion, and so our understanding of the polarization gap remains unfortunately limited.

The Supreme Court’s Many Median Justices

Thu, 01 Nov 2012 00:00:00 +0000

Theoretical and empirical research on the US Supreme Court has become increasingly channeled through a unidimensional spatial model of judicial decision-making. We argue that limitations in quantitative measurement of justices’ preferences have obscured the ways in which justices’ preferences vary across areas of the law and constrained the set of questions the research can pursue. We introduce a new approach, using multiple indices of substantive similarity among cases and a kernel-weighted optimal classification estimator to recover estimates of judicial preferences that are localized to particular legal issues as well as periods of time. Allowing preference variation across legal areas significantly improves the predictive power of estimated preference orderings versus a model that only allows for variation in preferences over time. We find judicial preferences are not reducible to simple left-right ideology and, as a consequence, there is substantial variation in the identity of the median justice across areas of the law during all periods of the modern court. These results suggest a need to reconsider empirical and theoretical research that hinges on the existence of a unitary and well-identified median justice.

Compound Poisson-Gamma Regression Models for Dollar Outcomes That Are Sometimes Zero

Sun, 01 Jul 2012 00:00:00 +0000

Political scientists often study dollar-denominated outcomes that are zero for some observations. These zeros can arise because the data-generating process is granular: the observed outcome results from aggregation of a small number of discrete projects or grants, each of varying dollar size. This article describes the use of a compound distribution in which each observed outcome is the sum of a poisson distributed number of gamma distributed quantities, a special case of the Tweedie distribution. Regression models based on this distribution estimate log-linear marginal effects without either the ad hoc treatment of zeros necessary to use a log-dependent variable regression or the change in quantity of interest necessary to use a tobit or selection model. The compound poisson-gamma regression is compared with commonly applied approaches in an application to data on high-speed rail grants from the U.S. federal government to the states, and against simulated data from several data-generating processes.

The Genealogy of Law

Sun, 01 Jul 2012 00:00:00 +0000

Many theories of judicial politics have at their core the concepts of legal significance, doctrinal development and evolution, and the dynamics of precedent. Despite rigorous theoretical conceptualization, these concepts remain empirically elusive. We propose the use of a genealogical model (or “family tree”) to describe the Court’s construction of precedent over time. We describe statistical assumptions that allow us to estimate this kind of structure using an original data set of citation counts between Supreme Court majority opinions. The genealogical model of doctrinal development provides a parsimonious description of the dependencies between opinions, while generating measures of legal significance and other related quantities. We employ these measures to evaluate the robustness of a recent finding concerning the relationship between ideological homogeneity within majority coalitions and the legal impact of Court decisions.

Distinguishing Between Influences on Brazilian Legislative Behavior

Wed, 27 Jul 2011 00:00:00 +0000

Ideal point estimators hold the promise of identifying multiple dimensions of political disagreement as they are manifested in legislative voting. However, standard ideal point estimates do not distinguish between ideological motivations and voting inducements from parties, coalitions, or the executive. In this article we describe a general approach for hierarchically identifying an ideological dimension using an auxiliary source of data. In the case we consider, we use an anonymous survey of Brazilian legislators to identify party positions on a left-right ideology dimension. We then use this data to distinguish ideological motivations from other determinants of roll-call behavior for eight presidential-legislative periods covering more than 20 years of Brazilian politics. We find that there exists an important nonideological government-opposition dimension, with the entrance and exit of political parties from the governing coalition appearing as distinct shifts in ideal point on this second dimension. We conjecture that the Brazilian president’s control over politically important resources is the source of this dimension of conflict, which has recently become far more important in explaining roll-call voting than the ideological dimension.

Legislator Characteristics, Constituency Characteristics, and Roll Call Voting

Fri, 01 Apr 2011 00:00:00 +0000

Which matters more when legislators make decisions, their own characteristics or those of the people they represent? This paper uses comprehensive data on the personal attributes of both members of Congress and their constituents to com- pare the relative influence of eight legislator and constituency characteristics–party, race, gender, age, income, education, religion, and occupation–on roll call voting in the 109th and 110th Congresses. Our findings suggest that who governs matters considerably more than the literatures on representation and legislative decision-making have previously acknowledged: the effects of legislators’ own backgrounds are not limited to the handful of issue areas and personal characteristics that previous studies have examined. These findings strongly support recent calls for renewed attention to the “personal roots” of elite decision-making.

Recovering Vote by Race in Primary Elections: Does Local Ecological Inference Provide Accurate Estimates of Voting Behavior Without Polling Data?

Fri, 01 Apr 2011 00:00:00 +0000

Scholars know far less about voting behavior in primary elections than in general elec- tions, yet in the many parts of the country where one party dominates, it is primary elections that determine who holds office. Because of the absence of the party cue, the roles of race, income and education in voting behavior are potentially more varied and consequential in the context of primaries. For example, elections contested by multiple black candidates–typically in majority-black electorates–can show striking patterns of racial voting despite the apparent lack of any overt cue from the race of the candidate. Unfortunately, studying primary elections is difficult because polling is sparse and of low quality. In this paper, we begin an assessment of whether the use of a local ecologi- cal inference method based on geographically-weighted kernel regressions can facilitate systematic study of these unpolled elections. Our local ecological inference technique weakens the assumptions made by standard ecological inference methods in an intuitive way that is appropriate to political geography. We demonstrate the relative robustness of our local ecological estimates of support by race in a difficult case where the correct answer is known and standard ecological inference methods give spectacularly wrong estimates: the state-level vote by race for Barack Obama and John McCain in the 2008 presidential election. We then apply these methods to a pilot study of the 2000 Illinois 1st Congressional District primary between Barack Obama and Bobby Rush.

Locating Supreme Court Opinions in Doctrine Space

Wed, 21 Jul 2010 00:00:00 +0000

We develop a scaling model to estimate U.S. Supreme Court opinion locations and justice ideal points along a common spatial dimension using data derived from the citations between opinions. Citations from new opinions to precedent opinions usually apply and endorse the doctrine of the precedent opinion; however, sometimes they implicitly or explicitly dispute the precedent opinion. We collect original datasets classifying citations from search and seizure and freedom of religion opinions written between 1953 and 2006 into these different types and develop a model relating the similarity of the doctrine embodied in the citing and cited opinions to the relative probability of these different types of citations. The resulting spatial estimates of opinion location are used to evaluate theories of Supreme Court bargaining and opinion writing. We find empirical support for theoretical models that predict the majority opinion will fall at the ideal point of the median member of the majority coalition. Given the centrality of theories of judicial policymaking to various substantive problems in political science, the method of scaling opinions developed in this article can facilitate a range of future research.

Unpredictable Voters in Ideal Point Estimation

Thu, 01 Apr 2010 00:00:00 +0000

Ideal point estimators are typically based on an assumption that all legislators are equally responsive to modeled dimensions of legislative disagreement; however, particularistic constituency interests and idiosyncrasies of individual legislators introduce variation in the degree to which legislators cast votes predictably. I introduce a Bayesian heteroskedastic ideal point estimator and demonstrate by Monte Carlo simulation that it outperforms standard homoskedastic estimators at recovering the relative positions of legislators. In addition to providing a refinement of ideal point estimates, the heteroskedastic estimator recovers legislator-specific error variance parameters that describe the extent to which each legislator’s voting behavior is not conditioned on the primary axes of disagreement in the legislature. Through applications to the roll call histories of the U.S. Congress, the E.U. Parliament, and the U.N. General Assembly, I demonstrate how to use the heteroskedastic estimator to study substantive questions related to legislative incentives for low-dimensional voting behavior as well as diagnose unmodeled dimensions and nonconstant ideal points.

Pass the Pork: Measuring Legislator Shares in Congress

Tue, 12 Feb 2008 00:00:00 +0000

Linear regression models are frequently used to analyze distributive politics in the U.S. Congress; however, authors have used a variety of specifications with different implicit assumptions about how bicameralism shapes legislative bargaining. I derive a model that describes district or state spending authorizations as the aggregation of spending secured by multiple legislators working on behalf of overlapping constituencies. This bicameral shares model allows the disaggregation of House and Senate influence through simultaneous estimation of the relative bargaining power of the two chambers and the advantages that accrue to legislators holding partisan, committee, and other relevant affiliations. In the 2005 transportation bill, the model better predicts the functional form of small state advantage than recently employed specifications in the literature.

Latent Versus Self-Reported Ideology

Sun, 01 Jul 2007 00:00:00 +0000

Spatial voting axes are seldom directly measurable. In general, political scientists employ latent variable models that aim to infer the presence and characteristics of axes from their impact on measurable quantities such as voting behavior. Ideology in the electorate is a rare case where researchers regularly attempt to measure a spatial quantity directly, typically by asking people to rank themselves on ordinal scales from liberal to conservative. These self-reported ideology scores have been widely used as a nationally comparable measure of ideological position, but whether different citizens are using consistent criteria for assessing and reporting their ideology is largely unknown. To better understand the relationship between issue positions and ideology in the electorate, I develop a item-response model for self-reported ideology as a function of issue positions. I find that political information is required for voters to self-report ideology consistently with their issue positions. Groups which are less attuned to the terminology of the national political discourse tend to self-report ideology in ways that are less informative about their issue positions on the primary political axis defined by that discourse.

403

Mon, 01 Jan 0001 00:00:00 +0000

Sorry, you don’t have permission to do that.

404: File not found

Mon, 01 Jan 0001 00:00:00 +0000

Sorry, that doesn’t seem to be here. Try the home page.

Citizen Attitudes Towards National and International Problems (CATNIP)

Mon, 01 Jan 0001 00:00:00 +0000

From September 2025 through August 2030, I am the primary investigator for a European Research Council Advanced Grant project Citizen Attitudes Towards National and International Problems (CATNIP). The initial stage of the project will seek to improve how political science measures which problems citizens think are most severe and most in need of their governments’ attention. The resulting advances in measurement will enable later stages of the project which will focus on improving our scientific understanding of where these attitudes come from and how they shape citizens’ views of media and politicians. One important application of this work will be characterising how (and which) voters prioritise international problems versus national problems, and the implications of this for how national political leaders engage internationally on questions of climate change, security, migration, and trade. As the project develops, I will post further details on this page.