In this paper we consider the analysis of models for univariate and multivariate ordinal outcomes in the context of the latent variable inferential framework of Albert and Chib (1993). We review several alternative modeling and identification schemes and evaluate how each aids or hampers estimation by Markov chain Monte Carlo simulation methods. For each identification scheme we also discuss the question of model comparison by marginal likelihoods and Bayes factors. In addition, we develop a simulation-based framework for analyzing covariate effects that can provide interpretability of the results despite the non-linearities in the model and the different identification restrictions that can be implemented. The methods are employed to analyze problems in labor economics (educational attainment), political economy (voter opinions), and health economics (consumers' reliance on alternative sources of medical information).

This paper explores rich longitudinal data to gain a better understanding of the importance of spatial mismatch in lower-paid workers' job search. The data infrastructure at our disposal allows us to investigate the impact on a variety of job search-related outcomes of localized and individual-specific job accessibility measures using identification strategies that mitigate the impact of residential self-selection. Our results suggest that better access to jobs causes a statistically significant, but modest decrease in the duration of joblessness among lowerpaid displaced workers, while an abundance of competing searchers for those jobs increases duration modestly. Search durations for older workers, Hispanic workers, and those displaced from manufacturing jobs are especially sensitive to job accessibility. * NOTE: An earlier version of this paper was prepared for the American Real Estate and Urban Economics Association meetings, January 2011. Any opinions and conclusions expressed herein are those of the authors and do not necessarily represent the views of the Office of the Comptroller of the Currency, the Department of Treasury or the U.S. Census Bureau. All results have been reviewed to ensure that no confidential information is disclosed. The authors want to thank Sheharyar Bokhari for his valuable research assistance, participants at various seminars and conferences for their suggestions, and Kevin McKinney and Ron Jarmin for their comments on an earlier draft.

NBER working papers are circulated for discussion and comment purposes. They have not been peerreviewed or been subject to the review by the NBER Board of Directors that accompanies official NBER publications.

We study the responsiveness of individuals' employment and earnings to the damages and disruption caused by Hurricanes Katrina and Rita, which struck the U.S. Gulf Coast in 2005. Our analysis is based on individual-level survey and administrative data that tracks workers over time, both in the immediate aftermath of the storm and over a seven-year period. For individuals who were employed at the time of the storm, we estimate models that compare the evolution of earnings for individuals who resided in storm-affected areas and individuals who resided in a set of control counties with pre-storm characteristics similar to those of the storm-affected areas prior to the storm. We find that, on average, the storms reduced the earnings of affected individuals during the first year after the storm. These losses reflect various aspects of the shortrun disruption caused by the hurricanes, including job separations, migration to other areas, and business contractions. Starting in the third year after the storms, however, we estimate that the storms increased the quarterly earnings of affected individuals. We provide evidence that the long-term earnings gains experienced by affected individuals were the result of differences in wage growth between the affected areas and the control areas, due to reduced labor supply and increased labor demand, especially in sectors related to rebuilding. Despite short-term earnings losses due to an increased rate of non-employment, we find a net increase in average quarterly earnings among affected individuals over the entire post-storm period. However, subgroups with large and persistent earnings losses after the storms had a net decrease in average quarterly earnings over the seven-year period due to the storms.