Jan Box-Steffensmeier
Ohio State University
“Conditional Frailty Models and the Onset of Civil War”
Tuesday, May 10, 2005
Paper (in PDF)
Conditional Frailty Models (in PDF)
Data Appendix (in PDF)
Kristian Gleditsch
University of California, San Diego
“Transnational Dimensions of Civil War”
Tuesday, April 26, 2005
Presentation (in PDF)
Abstract: Existing research has tended to relate civil war to country-specific factors or processes
within individual states. Many contemporary civil wars, however, display a transna-
tional character, where key actors, resources, and events span national boundaries.
In this paper, I examine how interaction and processes between states influence the
risk of conflict within states. Previous research has shown that the risk of conflict
is strongly influenced by conflicts in a state’s regional context. However, existing
research has not distinguished between different transnational linkages that may
underlie geographic contagion, not properly accounted for the spatial dependence
between observations, and has failed to consider the potential influences of domestic
attributes. In this paper, I evaluate a series of hypotheses on how transnational
factors influence the risk of conflict and the prospects for maintaining peace in a
conditional autologistic model, including country-specific factors often associated
with civil wars. The empirical findings indicate that transnational linkages between
states and regional factors strongly influence the risk of conflict. The risk of civil war
differs fundamentally depending on a country’s linkages to other states, and analyses
of civil war must take into account transnational factors and regional differences in
the risk of war.
Bio: Kristian Gleditsch’s (Ph.D., Colorado) research interests include conflict and cooperation, international aspects of democratization and political change, applied statistics, and mathematical models. Gleditsch's recent research focuses on local interaction and regional differentiation in conflict, peace, and democratization. His book, All International Politics is Local: The Diffusion of Conflict, Integration, and Democratization, was published by the University of Michigan Press in 2002. Gleditsch’s research has appeared in the American Political Science Review, the American Journal of Political Science, International Studies Quarterly, the Journal of Conflict Resolution, Political Analysis, the Annals of the Association of American Geographers, and several edited volumes. He has been the recipient of the Rudolf Wildenmann prize in 2001, APSA's Helen Dwight Reid award in 2000, and the 2002 Warren Miller prize for the best article in Political Analysis.
William Greene
Stern School of Business, New York University
“Modeling Heterogeneity in Discrete Choice: Recent Developments and Contrasts with Bayesian estimation.”
Thursday, March 17, 2005
Presentation (in PDF)
Abstract: This study examines some aspects of mixed (random parameters) logit modeling. We present some familiar results in specification and classical estimation of the random parameters model. We then describe several extensions of the mixed logit model developed in recent papers. The relationship of the mixed logit model to Bayesian treatments of the simple multinomial logit model is noted, and comparisons and contrasts of the two methods are described. The techniques described here are applied to several data sets, two stated/revealed choice surveys of commuters and one simulated data set on brand choice.
Bio: William Greene is Professor of Economics and Faculty Fellow of Entertainment, Media and Technology at the Stern School of Busniess, New York University. He is well known throughout the social sciences for his textbook Econometric Analysis (5th edition, Prentice-Hall 2003) and his estimation software program LIMDEP. His research interests center on econometric methods and applications, particularly nonlinear optimization, panel data, discrete choice modeling and limited dependent variables, efficiency and productivity measurement, and the economics of the entertainment and sports businesses.
Renee Smith
Harris Interactive
“The State of Internet-Based Survey Research”
Tuesday, February 3, 2005
Bio: Reneé Smith received her Ph.D. in political science from Michigan State and is a Senior Research Scientist at Harris Interactive.
Dave Darmofal
Ohio State University
“Spatial Econometrics and Turnout in American Political Development”
Tuesday, November 30, 2004
Presentation (in PDF)
Abstract: Political science data are inherently spatial data: the political phenomena we seek to understand occur at specific geographic locations. And these locations are often central to our understanding of these phenomena. Many of our theories across a broad range of substantive concerns predict that units in close spatial proximity will be more likely to behave similarly, and thus exhibit spatial dependence. Modeling this spatial dependence is important for both substantive and methodological reasons. Substantively, identifying spatial dependence may indicate the existence of a diffusion process, in which units directly influence the behavior of their neighboring units. Methodologically, standard approaches to statistical inference, such as OLS, may produce biased or inefficient estimates in the presence of spatial dependence, depending on the particular form that this dependence takes.
Recent advances in spatial econometrics now allow for a more generalized, rigorous, and systematic modeling of spatial dependence than has previously been possible. This talk will examine the foundations of spatial econometrics, classes of spatial econometric models, and the process of modeling spatial dependence. It will then apply spatial econometric models to the question of how elite-mass interactions have shaped voter participation in the United States.
Bio: David Darmofal holds a Ph.D. from the University of Illinois and is the PRISM Senior Methods Fellow at Ohio State University for the 2004-05 academic year. He has research interests in political behavior and quantitative methods.
Caroline Tolbert
Kent State University
“Mobilizing Voters: Ballot Measures and the 2004 Presidential Election”
Tuesday, October 26, 2004
Bio: Caroline Tolbert received her Ph.D. in political science from the University of Colorado and is coauthor (with Daniel Smith) of Educated by Initiative: The Effects of Direct Democracy on Citizens and Political Organizations in the American States (University of Michigan, 2004). She is also coauthor of Virtual Inequality: Beyond the Digital Divide (Georgetown University Press, 2003 with Karen Mossberger and Mary Stansbury) and co-editor (with Todd Donovan and Shaun Bowler) of Citizens as Legislators: Direct Democracy in the United States (Ohio State University Press, 1998). Her research is defined by an interest in strengthening American democracy, with an emphasis on participation, reforming political institutions and equality.
Speaker Series Archive
2003-04
