This paper considers models for unobservables in duration models. It demonstrates how cross-section and time-series variation in regressors facilitates identification of single-spell, competing risks and multiple spell duration models. We also demonstrate the limited value of traditional identification studies by considering a case in which a model is identified in the conventional sense but cannot be consistently estimated.
Get full access to this article
View all access options for this article.
References
1.
David HA, Moeschberger MLThe theory of competing risks. High Wycombe: Griffin, 1978.
2.
Kalbfleisch JD, Prentice RLThe statistical analysis of failure time data. New York : Wiley, 1980.
3.
Cox DR, Oakes D.Analysis of survival data. London: Chapman and Hall, 1984.
4.
Flinn CJ, Heckman JJAre unemployment and out of the labor force behaviorally distinct labor force states?Journal of Labor Economics1983; 1: 28-42.
5.
Cox DRRenewal theory. London: Methuen , 1962.
6.
Tsiatis A.A nonidentifiability aspect of the problem of competing risks. Proceedings of the National Academy of Sciences1975; 72: 20-2.
7.
Yashin AI, Manton KG, Stallard E.Dependent competing risks: a stochastic process model. Journal of MathematicalBiology1986; 24: 119-64.
8.
Flinn CJ, Heckman JJModels for the analysis of labor force dynamics. In Advances in econometrics, 1, Ed. Bassman R, Rhodes G, 35-95, Greenwich, CT: JAI Press, 1982.
9.
Basu AP, Ghosh JKIdentifiability of the multinormal and other distributions under competing risks model. Journal of MultivariateAnalysis1978; 8: 413-29.
10.
Arnold B., Brockett P.Identifiability for dependent multiple decrement/competing risk models. Scandinavian Actuarial Journal1983; 10: 117-27.
11.
Heckman JJ, Honoré B.The identifiability of the competing risks model. Biometrika1989; 76: 325-30.
12.
Cox DRRegression models and life-tables (with discussion). Journal of the Royal Statistical Society Series B 1972; 34: 187-202.
13.
Flinn CJ, Heckman JJThe likelihood function for the multistate-multiepisode model in 'Models for the analysis of labor force dynamics'. In Advances in econometrics , 3, Ed. Bassman R, Rhodes G. pp. 225-31, Greenwich, CT: JAI Press, 1983.
14.
Clayton D., Cuzick J.Multivariate generalizations of the proportional hazard model. Journal of the Royal Statistical Society Series A 1985; 148: 82-117.
15.
Manton KG, Stallard E., Woodbury M.Chronic disease evolution and human aging: a general model for assessing the impact of chronic disease in human populations. International Journal ofMathematical Modelling1986; 17: 406-52.
16.
Elbers C., Ridder G.True and spurious duration dependence: the identifiability of the proportional hazard model. Review of Economic Studies1982 ; 49: 403-10.
17.
Heckman JJ, Singer B.The identifiability of the proportional hazard model. Review of Economic Studies1984; 51(2): 231-43.
18.
Honoré B.Identification of duration models with unobserved heterogeneity. Unpublished manuscript, Northwestern University, 1990.
19.
Feller W.An introduction to probability theory and its applications. New York: Wiley, Vol. II, 1971.
20.
Heckman JJ, Singer B.Social science duration analysis. In Longitudinal analysis of labor market data. Ed. Heckman JJ, Singer B.New York: Cambridge University Press, 1985.
21.
Ridder G.The non-parametric identification of generalized hazard models. Review of Economic Studies1990; 57: 167-82.
22.
Heckman JJIdentifying the hand of past: distinguishing state dependence from heterogeneity. American Economic Review. Papers and Proceedings1991; 106(3): 75-79.
23.
Yashin AI, Arjas A.A note on random intensities and conditional survivor functions. Journal of Applied Probability1988; 25: 630-35.
24.
McCall B.Identifying state dependence in duration models with time-varying regressors, Industrial Relations Section. University of Minnesota, 1993.
25.
McCall B.The identifiability of the mixed proportional hazards model with time-coefficients, unpublished manuscript, Industrial Relations Section, University of Minnesota, 1993.
26.
Honoré B.Identification results for duration models with multiple spells. Review of Economic Studies1993; 60(1): 241-46.
27.
Heckman JJ, Hotz VJ, Walker JRNew evidence on the timing and spacing of births. American Economic Review1985; 72: 179-84.
28.
Heckman JJ, Borjas GJDoes unemployment cause future unemployment? Definitions, questions and answers for a continuous time model of heterogeneity and state dependence. Economica1980; 47: 247-83.
29.
Kiefer J., Wolfowitz J.Consistency of the maximum likelihood estimator in the presence of infinitely many incidental parameters. Annals of Mathematical Statistics1956; 27: 363-66.
30.
Heckman JJ, Singer B.A method for minimizing the impact of distributional assumptions in econometric models for duration data. Econometrica1984 ; 52(2): 271-320.
31.
Meyer B.Semiparametric estimation of hazard models. Econometrica1992; 60(3): 64-67.
32.
Honoré 1993. Rates of convergence in Weibull mixture models , unpublished manuscript, Northwestern, 1993 .
33.
Ishwaran H.Rates of convergence in semiparametric mixture models, published Ph.D. Thesis , Yale University, Department of Statistics, 1993.
34.
Lindsey B.The geometry of mixture likelihoods, Part I. Annals of Statistics1983; 11: 86-94.
35.
Lindsey B.The geometery of mixture likelihoods, Part II. Annals of Statistics1983; 11(3): 783-92.
36.
Heckman JJ, Robb R., Walker J.Testing the mixture of exponentials hypothesis and estimating the mixing distribution by the method of moments. Journal of The American Statistical Association1990; 85: 410, 582-89.
37.
Honoré B.Simple estimation of a duration model with unobserved heterogeneity. Econometrica1990; 58: 453-74.
38.
Heckman JJ, Walker J.The relationship between wages and income and the timing and spacing of births: evidence from Swedish longitudinal data. Econometrica1990; 58(6): 1411-41.
39.
Steinberg D., Colla P. "CTM" A supplementary module for SYSTA T. Evanston, Illinois: SYSTAT, 1994.
40.
Heckman JJ, Taber C.Identification in binary choice models and their extensions, unpublished manuscript , University of Chicago, 1994.
