Nonparametric identification of the mixed hazards model with time-varying covariates

被引：45

作者：

Brinch, Christian N. ^{[1
]}

机构：

[1] Univ Oslo, Dept Biol, Ctr Ecol & Evolutionary Synth, N-0316 Oslo, Norway

来源：

ECONOMETRIC THEORY | 2007年 / 23卷 / 02期

关键词：

D O I：

10.1017/S0266466607070144

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

Most nonparametric identification results for the mixed proportional hazards model for single spell duration data depend crucially on the proportional hazards assumption. Here, it is shown that variation in covariates over time, combined with variation across observations, is sufficient to ensure identification without the proportional hazards assumption. The required variation over time is minimal, and the mixed hazards model is identified without the proportional hazards assumption in the presence of standard time-varying covariates.

引用

页码：349 / 354

页数：6

共 17 条

[1]

[Anonymous], IDENTIFICATION RESUL

[2]

COX DR, 1972, J R STAT SOC B, V34, P187

[3]

Elbers C., 1982, REV ECON STUD, V49, P402

[4] ON MUNTZ THEOREM AND COMPLETELY MONOTONE FUNCTIONS [J].

FELLER, W .

AMERICAN MATHEMATICAL MONTHLY, 1968, 75 (04) :342-&

[5]

Feller W., 1991, An Introduction to Probability Theory and Its Applications, VII

[6] THE IDENTIFIABILITY OF THE PROPORTIONAL HAZARD MODEL [J].

HECKMAN, J ;

SINGER, B .

REVIEW OF ECONOMIC STUDIES, 1984, 51 (02) :231-241

[7]

Heckman J J, 1994, Stat Methods Med Res, V3, P279, DOI 10.1177/096228029400300306

[8]

HECKMAN JJ, 1991, AM ECON REV, V81, P75

[9] ECONOMETRIC DURATION ANALYSIS [J].

HECKMAN, JJ ;

SINGER, B .

JOURNAL OF ECONOMETRICS, 1984, 24 (1-2) :63-132

[10] IDENTIFICATION RESULTS FOR DURATION MODELS WITH MULTIPLE SPELLS [J].

HONORE, BE .

REVIEW OF ECONOMIC STUDIES, 1993, 60 (01) :241-246

← 1 2 →