Event Dependence and Heterogeneity in Duration Models: The Conditional Frailty Model

Suzanna De Boef and Kyle A. Joyce Department of Political Science, 219 Pond Laboratory, The Pennsylvania State University, University Park, PA 16802 e-mail: sdeboef{at}psu.edu e-mail: kjoyce{at}psu.edu e-mail: jboxstef+{at}osu.edu (corresponding author) We introduce the conditional frailty model, an event historymodel that separates and accounts for both event dependenceand heterogeneity in repeated events processes. Event dependenceand heterogeneity create within-subject correlation in eventtimes thereby violating the assumptions of standard event historymodels. Simulations show the advantage of the conditional frailtymodel. Specifically they demonstrate the model's ability todisentangle the sources of within-subject correlation as wellas the gains in both efficiency and bias of the model when comparedto the widely used alternatives, which often produce conflictingconclusions. Two substantive political science problems illustratethe usefulness and interpretation of the model: state policyadoption and terrorist attacks. Authors' note: Three anonymous reviewers gave valuable advice.Replication materials and an online appendix are available onthe Political Analysis Web site. Any errors are our own responsibility.     

Veto Players and Civil War Duration

Civil wars show a remarkable variation in how long they last. Some end within days; others continue for decades. What explains the extreme intractability of some wars while others are resolved quickly? This article argues that conflicts with multiple actors who must approve a settlement (veto players) are longer because there are fewer acceptable agreements, information asymmetries are more acute, and shifting alliances and incentives to hold out make negotiation more difficult. This veto player approach to explaining variation in civil war duration is tested using a new dataset containing monthly data on all parties to each civil war begun since World War II. The statistical analysis shows a strong correlation between the number of veto players and the duration of civil war.     

Reference Dependence in Political Primaries

This research considers how reference dependence impacts choice in a primary election. The normative advice is to weigh personal political preference against the greater ability of a more electable candidate to win the later general election. Here a behavioral view of primary elections is developed by adding reference dependence to a Hotelling model of political competition. The model details the impact of references on voter choice and generates recommendations as to the reference marketers for any candidate would like primary voters to employ. The advice to a more electable, that is, moderate, candidate is to encourage voters to compare the primary candidates to the extremes of the opposite party. A less electable candidate should encourage voters to compare the candidates to positions within their own party.     

从路径依赖到情境依赖:宗族乡村治理格局的适应性演化——基于广东省3个宗族村庄案例的实证分析

宗族乡村本质上是国家社会关系转变的产物,其治理格局的演化与国家社会发展同步互动。因此,认识宗族乡村治理格局的演化逻辑,必须在我国的历史传承与乡村治理的当下实践中建构分析框架。“路径依赖——情境依赖”分析框架正是一种认识宗族乡村治理格局演化逻辑的尝试,它把路径依赖具体划分为延续性与变革性两个方面,延续性代表着历史传承,变革性则依赖于当下情境。而当下情境又具体化为制度情境、本土情境、事件情境三种类型,治理格局常常因任意一类型情境变迁而做出适应性改变,便是发生了情境依赖。路径依赖的延续性和变革性所催生的情境依赖,成就了历史传承在当下的互动形式,宗族乡村治理格局便在这种互动关系中渐进演化。     

The Potential of Path Dependence in Political Studies

This article explores the difficulties with both the theoretical content and application of the concept of 'path dependence' in political studies, but suggests that, by combining it with insights from morphogenetic social theory, we can provide a coherent framework for its use. After providing a brief survey of the literature on path dependence, it presents a summary of the most significant criticisms made of the approach. The article then moves on to examine morphogenetic social theory and its potential to meet these criticisms before concluding by characterising the elements of a path-dependent system incorporating insights from both new institutionalism and morphogenetic social theory.     

Party System Polarisation and Government Duration in Central and Eastern Europe

Since the transition to democracy in the early 1990s, more than 60 per cent of governments in Central and Eastern Europe have terminated prematurely. This article argues that the character of party system development in the region has facilitated the emergence of a polarised pattern of party competition and that competition for government now takes place in distinct ideological blocs. Parties seek to form governments within these blocs but not across them and therefore there is little incentive to defect from a governing coalition due to the lack of viable alternatives. As a result, more polarised party systems produce more durable governments. The empirical evidence shows that polarisation and ideological diversity of the government are significant indicators of government duration in Central and Eastern Europe. Ideologically compact governments formed within narrow blocs in the party system survive longer than ideologically diverse coalitions that emerge from less polarised party systems.     

Path Dependence and Public Sector Innovation in Regulatory Regimes

The overarching theme of this article is institutional analysis of modernization and innovation in the regulatory state, and in pursuing this, the concepts of ‘path dependence’ and ‘administrative traditions’ are used throughout. Self‐reinforcing or positive feedback processes in political systems represent a basic framework. The empirical point of departure is the EU public procurement directive linked to OECD data concerning use of outsourcing among Member States. The question is asked: What has caused the Nordic countries, traditionally not belonging to the Anglo‐Saxon market‐centred administrative tradition, to be ranked so high as users of the Market‐Type Mechanism (MTM) of outsourcing in the public sector versus inhouse provision of services? The reason may be complex, but might be found in an innovative Scandinavian regulatory approach rooted in a ‘small is beautiful’, small and medium‐seized businesses, and local and regional development planning tradition.     

Selection Bias and Continuous-Time Duration Models: Consequences and a Proposed Solution

This article analyzes the consequences of nonrandom sample selection for continuous-time duration analyses and develops a new estimator to correct for it when necessary. We conduct a series of Monte Carlo analyses that estimate common duration models as well as our proposed duration model with selection. These simulations show that ignoring sample selection issues can lead to biased parameter estimates, including the appearance of (nonexistent) duration dependence. In addition, our proposed estimator is found to be superior in root mean-square error terms when nontrivial amounts of selection are present. Finally, we provide an empirical application of our method by studying whether self-selectivity is a problem for studies of leaders' survival during and following militarized conflicts.     

Single-Family Housing Market Segmentation,Post-Foreclosure Resale Duration,and Neighborhood Attributes

During the recent economic recession, the foreclosure crisis drew vast attention from scholars and policymakers. Numerous studies focused on factors resulting in foreclosures, the impact of foreclosures, and the relationship between neighborhood attributes and foreclosures. Fewer studies investigated the foreclosure resale mechanism by focusing on buyer characteristics and the market duration of foreclosed properties. This research uses foreclosed residential properties in Broward County, Florida, between 2007 and 2011 to explore how market segmentation by assessed value relates to time on market of foreclosed properties. This research finds that extremely low-value properties and very high-value properties generally take longer to sell. Mid-value properties take a shorter time to sell. After controlling for housing attributes and market segmentation, certain neighborhood characteristics, such as lower percentage black population, lower percentage Hispanic population, lower educational attainment, and higher homeownership rate, are associated with increased likelihood of a real estate owned property being sold. These results will help policymakers determine better strategies for the foreclosure resale process. Special attention should focus on properties taking longer to sell or not able to sell during certain time frames to alleviate the negative effects of these properties on neighborhoods.     

Local Ownership as Dependence Management: Inviting the Coloniser Back

This article challenges the tendency to understand local ownership of statebuilding processes chiefly as a product of how international donors plan and implement reforms rather than of how such efforts are appropriated by local actors. Local ownership is typically described as a quality which is ‘supported’, ‘fostered’, ‘granted’ or ‘stifled’ by foreigners rather than something which is simply taken by the hosts of such interventions. Drawing on the case of British-led police reform in Sierra Leone, the article argues that local authorities exercised ownership by actively drawing their former colonizer into the security sector, thus deepening and prolonging the intervention. This contradicts two common assumptions about local ownership: (i) it is aimed at reducing international influence and (ii) it will be scarcer and more difficult to achieve the weaker the host state. Rather than to control how the police reform was designed and implemented, the principal function of local ownership was to secure a powerful ally in the ongoing civil war and to achieve an outward reorientation of national security.     

Fiscal Coordination and Financial Dependence of State Governments in Mexico

This paper presents evidence of the effects on subnational financial dependence of the intergovernmental fiscal agreement implemented in 1980. In contrast with a previous study that uses annual time series national data, we use a panel of annual time series (1975–1995) of 31 Mexican states. We propose and estimate three different empirical models using the fixed effects panel data approach. In concordance with previous literature, we find strong statistical evidence that the implementation of the agreement increased financial dependence. The main contribution of this paper is to distinguish the effect of the 1980 fiscal arrangement on every state's degree of financial dependence.     

Institutional Inconsistency and Political Instability: Polity Duration, 1800–2000

This article examines how political institutional structures affect political instability. It classifies polities as autocracies or democracies based on three institutional dimensions: election of the executive, constraints on executive decision-making authority, and extent of political participation. It hypothesizes that strongly autocratic and democratic regimes will exhibit the greatest stability resulting from self-enforcing equilibria, whereby the maintenance of a polity's institutional structure is in the interest of political elites, whether through autocratic or democratic control. Institutionally inconsistent regimes (those exhibiting a mix of institutional characteristics of both democracy and autocracy) lack these self-enforcing characteristics and are expected to be shorter-lived. Using a log-logistic duration model, polity survival time ratios are estimated. Institutionally consistent polities are significantly more stable than institutionally inconsistent polities. The least stable political systems are dictatorships with high levels of political participation. The most unstable configuration for polities with an elected executive is one where the executive is highly constrained, but the electorate is very small.     

Delaying Justice(s): A Duration Analysis of Supreme Court Confirmations

Presidents traditionally have had great success when nominating justices to the Supreme Court, with confirmation being the norm and rejection being the rare exception. While the confirmation process usually ends with the nominee taking a seat on the Court, however, there is a great deal of variance in the amount of time it takes the Senate to act. To derive a theoretical explanation of this underlying dynamic in the confirmation process, we draw on a spatial model of presidential nominations to the Court. We then employ a hazard model to test this explanation, using data on all Supreme Court nominations and confirmations since the end of the Civil War. Our primary finding is that the duration of the confirmation process increases as the ideological distance between the president and the Senate increases. We also find evidence that suggests that the duration increases for critical nominees and chief justices and decreases for older nominees, current and previous senators, and nominees with prior experience on state and federal district courts .     

Path Dependence in Settlement Processes: Explaining Settlement in Northern Ireland

The recent literature on path dependence provides a model that can be used in explanation of ethnic conflict and settlement processes. Using Northern Ireland as a case study, this article identifies path dependent patterns of conflict embedded in long-term processes of political development whose change may interrupt these patterns. It highlights the importance of long-term state trajectories in constituting and reproducing these patterns, the generation of 'endogenous' processes of change and the impact of wider geopolitical processes in strengthening these. It shows how and why factors such as power, perception, networks and institutions vary in their impact on conflict and explains when they work together to produce settlement.     

Lessons from Resource Dependence Theory for Contemporary Public and Nonprofit Management

The fiscal landscape continues to challenge public and nonprofit managers. Against this backdrop, public and nonprofit managers look for new strategies to address the challenges associated with limited resources. Resource dependence theory provides valuable guidance for managers who want to understand the considerations and consequences relevant to different types of interorganizational partnering. In this article, the theory's core ideas are described, along with three common strategies or tactics that organizations use to obtain critical resources from the environment: merging, forming alliances, and co‐opting. For each strategy, the authors derive a set of practical lessons for busy public and nonprofit managers.     

The Cost of Ruling,Cabinet Duration,and the “Median-Gap” Model

In a recent article Paldam and Skott (1995) provide atheoretical explanation for an important empirical phenomenonin democratic countries: incumbent governments tend to losevotes. In this paper, I show that Paldam and Skott'stheoretical explanation for this ``cost of ruling'' ispotentially much stronger than they recognize. Specifically,when generalized in a straightforward way, their modelexplains not only the cost of ruling itself, but also a secondwell established empirical fact: that the longer an incumbentgovernment has been in power, the more votes it loses.Further, this generalization of the model produces twoadditional empirical hypotheses that have not yet been testedin the empirical literature.     

Matching as Nonparametric Preprocessing for Reducing Model Dependence in Parametric Causal Inference

Kosuke Imai Department of Politics, Princeton University, Princeton, NJ 08544 e-mail: kimai{at}princeton.edu Gary King Department of Government, Harvard University, 1737 Cambridge Street, Cambridge, MA 02138 Elizabeth A. Stuart Departments of Mental Health and Biostatistics, Johns Hopkins Bloomberg School of Public Health, 624 North Broadway, Room 804, Baltimore, MD 21205 e-mail: estuart{at}jhsph.edu e-mail: king{at}harvard.edu (corresponding author) Although published works rarely include causal estimates frommore than a few model specifications, authors usually choosethe presented estimates from numerous trial runs readers neversee. Given the often large variation in estimates across choicesof control variables, functional forms, and other modeling assumptions,how can researchers ensure that the few estimates presentedare accurate or representative? How do readers know that publicationsare not merely demonstrations that it is possible to find aspecification that fits the author's favorite hypothesis? Andhow do we evaluate or even define statistical properties likeunbiasedness or mean squared error when no unique model or estimatoreven exists? Matching methods, which offer the promise of causalinference with fewer assumptions, constitute one possible wayforward, but crucial results in this fast-growing methodologicalliterature are often grossly misinterpreted. We explain howto avoid these misinterpretations and propose a unified approachthat makes it possible for researchers to preprocess data withmatching (such as with the easy-to-use software we offer) andthen to apply the best parametric techniques they would haveused anyway. This procedure makes parametric models producemore accurate and considerably less model-dependent causal inferences. Authors' note: Our thanks to Dan Carpenter and Jeff Koch fordata; Alberto Abadie, Neal Beck, Sam Cook, Alexis Diamond, BenHansen, Guido Imbens, Olivia Lau, Gabe Lenz, Paul Rosenbaum,Don Rubin, and Jas Sekhon for many helpful comments; and theNational Institutes of Aging (P01 AG17625-01), the NationalInstitute of Mental Health (MH066247), the National ScienceFoundation (SES-0318275, IIS-9874747, SES-0550873), and thePrinceton University Committee on Research in the Humanitiesand Social Sciences for research support. Software to implementthe methods in this paper is available at http://GKing.Harvard.edu/matchitand a replication data file is available as Ho et al. (2006).