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.     

The Influence of Unobserved Factors on Position Timing and Content in the NAFTA Vote

e-mail: boehmke{at}umich.edu A variety of factors have been shown to influence position timingand the content of positions taken by legislators on importantissues. In addition to these observed factors, I argue thatunobserved factors such as behind-the-scenes lobbying and partyloyalty may also influence position timing and position content.Although hypotheses about observed factors can be tested usingtraditional methods, hypotheses about unobserved factors cannot.To test for systematic effects of unobserved factors on positiontiming and content, I develop a seemingly unrelated discrete-choiceduration estimator and apply it to data from the vote for theNorth American Free Trade Agreement. The results indicate thateven after controlling for observed factors, there is stillevidence that unobserved factors such as Presidential lobbyingand/or party loyalty influence both choices.     

Using Auxiliary Data to Estimate Selection Bias Models, with an Application to Interest Group Use of the Direct Initiative Process

Recent work in survey research has made progress in estimatingmodels involving selection bias in a particularly difficultcircumstance—all nonrespondents are unit nonresponders,meaning that no data are available for them. These models arereasonably successful in circumstances where the dependent variableof interest is continuous, but they are less practical empiricallywhen it is latent and only discrete outcomes or choices areobserved. I develop a method in this article to estimate thesemodels that is much more practical in terms of estimation. Themodel uses a small amount of auxiliary information to estimatethe selection equation parameters, which are then held fixedwhile estimating the equation of interest parameters in a maximum-likelihoodsetting. After presenting Monte Carlo analyses to support themodel, I apply the technique to a substantive problem: Whichinterest groups are likely to to be involved in support of potentialinitiatives to achieve their policy goals?