Tauchmann H, Yurkevich E (2026)
Publication Language: English
Publication Type: Journal article, Original article
Publication year: 2026
Book Volume: 26
Pages Range: 325-366
Article Number: st0805
Journal Issue: 3
DOI: 10.1177/1536867X261477503
Open Access Link: https://dx.doi.org/10.1177/1536867X261477503
This article introduces the new community-contributed Stata commands xtdhazard and cfbinout. The former implements the own-differences instrumental variables estimator proposed by Farbmacher and Tauchmann (2023, Econometric Reviews 42(8): 635–654) for dealing with time-invariant unobserved heterogeneity in the discrete-time hazard model. cfbinout is called by xtdhazard if a nonlinear rather than a linear discrete-time hazard model is specified. cfbinout can also be used as a stand-alone command that generalizes ivprobit, twostep by allowing discrete endogenous regressors and different link functions than the normal link, specifically logit and cloglog. In terms of the underlying econometric theory, cfbinout is guided by Wooldridge (2015, Journal of Human Resources 50(2): 420–445). An Empirical example illustrates the use of xtdhazard in applied empirical work.
APA:
Tauchmann, H., & Yurkevich, E. (2026). xtdhazard and cfbinout: Using Internal Instruments for Addressing Unobserved Heterogeneity in the Discrete-Time Hazard Model. Stata Journal, 26(3), 325-366. https://doi.org/10.1177/1536867X261477503
MLA:
Tauchmann, Harald, and Elena Yurkevich. "xtdhazard and cfbinout: Using Internal Instruments for Addressing Unobserved Heterogeneity in the Discrete-Time Hazard Model." Stata Journal 26.3 (2026): 325-366.
BibTeX: Download