Estimation of Sample Selection Models With Two Selection Mechanisms
Phillip Li ()
University of California Transportation Center, Working Papers from University of California Transportation Center
This paper focuses on estimating limited dependent variable models with incidentally truncated data and two selection mechanisms. While typical sample selection models have been widely estimated, extensions to multiple selection mechanisms have been sparse due to intractable likelihood functions or estimation algorithms with slow convergence. This paper extends the sampling algorithm from Chib et al. (2009) and proposes a computationally-ecient Markov chain Monte Carlo (MCMC) estimation algorithm with data augmentation. The algorithm only augments the posterior with a small subset of the total missing data caused by the selection mechanisms, which improves convergence of the MCMC chain and decreases computational load relative to standard algorithms. The resulting sampling densities are well-known despite not having the "complete" data. The methods are applied to estimate the e�ects of residential density on vehicle usage and holdings in California.
Keywords: Social; and; Behavioral; Sciences (search for similar items in EconPapers)
References: View references in EconPapers View complete reference list from CitEc
Citations: Track citations by RSS feed
Downloads: (external link)
Journal Article: Estimation of sample selection models with two selection mechanisms (2011)
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:cdl:uctcwp:qt0h97w9x2
Access Statistics for this paper
More papers in University of California Transportation Center, Working Papers from University of California Transportation Center Contact information at EDIRC.
Bibliographic data for series maintained by Lisa Schiff ().