Template-Type: ReDIF-Paper 1.0
Author-Name: Hilary W. Hoynes
Author-Name-First: Hilary W.
Author-Name-Last: Hoynes
Author-Name: Kenneth Y. Chay
Author-Name-First: Kenneth Y.
Author-Name-Last: Chay
Author-Name: Dean Hyslop
Author-Name-First: Dean
Author-Name-Last: Hyslop
Author-Workplace-Name: Department of Economics, University of California Davis
Title: TRUE STATE DEPENDENCE IN MONTHLY WELFARE PARTICIPATION:A NONEXPERIMENTAL ANALYSIS
Abstract: This paper provides an empirical evaluation of true state dependence in welfare participationusing unique administrative data from California that is measured at the monthly frequency,which coincides with the welfare eligibility period and so is free of time aggregation bias. Theanalysis uses first- and second-order dynamic conditional logit models that non-parametricallycontrol for permanent unobserved heterogeneity to test for state dependence in welfare behavior.The second-order model also absorbs individual-specific first-order Markov chains, and providesa more robust test for state dependence in high frequency data. The results using the first-ordermodel show substantial first-order state dependence in monthly welfare participation. Absorbingheterogeneous first-order effects, the hypothesis of no second-order state dependence is alsoeasily rejected. This suggests that past welfare participation predicts future participation, givenunrestricted effects of both the present state and unobserved heterogeneity, and providessubstantive evidence of duration dependence at the individual level.
Length: 24
File-URL: https://repec.dss.ucdavis.edu/files/Vyn2yxV2Wt26pHtuoQVzVy2R/05-33.pdf
File-Format: application/pdf
Number: 2
Classification-JEL: C14, C24, C25
KeyWords: Binary response panel data, state dependence, unobserved heterogeneity, initialconditions, conditional logit models
Creation-Date: 20040331
Handle: RePEc:cda:wpaper:2