Testing for Proportional Hazards with Unrestricted Univariate Unobserved Heterogeneity

Arnab Bhattacharjee

Testing for Proportional Hazards with Unrestricted Univariate Unobserved Heterogeneity

Arnab Bhattacharjee

Research output: Working paper/Preprint › Discussion paper

85 Downloads (Pure)

Abstract

We develop tests of the proportional hazards assumption, with respect to a continuous covariate, in the presence of unobserved heterogeneity with unknown distribution at the individual observation level. The proposed tests are specially powerful against ordered alternatives useful for modeling non-proportional hazards situations. By contrast to the case when the heterogeneity distribution is known up to â€¦nite dimensional parameters, the null hypothesis for the current problem is similar to a test for absence of covariate dependence. However, the two testing problems diÂ¤er in the nature of relevant alternative hypotheses. We develop tests for both the problems against ordered alternatives. Small sample performance and an application to real data highlight the usefulness of the framework and methodology.

Original language	English
Place of Publication	St. Andrews
Publisher	Scottish Institute for Research in Economics
Number of pages	46
Publication status	Published - 2009

Publication series

Name	SIRE Discussion Papers
Publisher	Scottish Institute for Research in Economics
No.	2009-22

Keywords

Two-sample tests
Increasing hazard ratio
Trend tests
Partial orders
Mixed proportional hazards model
Time varying coefficients

Access to Document

SIRE DP 2009 22Final published version, 1.11 MB

Testing for Proportional Hazards with Unrestricted Univariate Unobserved Heterogeneity
Bhattacharjee, A., 2009, St. Andrews: Department of Economics, University of St. Andrews, 46 p. (Discussion Paper Series; no. 0904).
Research output: Working paper/Preprint › Discussion paper

Open Access
File

Cite this

@techreport{28147880c21440d09d25b5d45b0bb620,

title = "Testing for Proportional Hazards with Unrestricted Univariate Unobserved Heterogeneity",

abstract = "We develop tests of the proportional hazards assumption, with respect to a continuous covariate, in the presence of unobserved heterogeneity with unknown distribution at the individual observation level. The proposed tests are specially powerful against ordered alternatives useful for modeling non-proportional hazards situations. By contrast to the case when the heterogeneity distribution is known up to {\^a}€¦nite dimensional parameters, the null hypothesis for the current problem is similar to a test for absence of covariate dependence. However, the two testing problems di{\^A}¤er in the nature of relevant alternative hypotheses. We develop tests for both the problems against ordered alternatives. Small sample performance and an application to real data highlight the usefulness of the framework and methodology.",

keywords = "Two-sample tests, Increasing hazard ratio, Trend tests, Partial orders, Mixed proportional hazards model, Time varying coefficients",

author = "Arnab Bhattacharjee",

year = "2009",

language = "English",

series = "SIRE Discussion Papers",

publisher = "Scottish Institute for Research in Economics ",

number = "2009-22",

type = "WorkingPaper",

institution = "Scottish Institute for Research in Economics ",

}

TY - UNPB

T1 - Testing for Proportional Hazards with Unrestricted Univariate Unobserved Heterogeneity

AU - Bhattacharjee, Arnab

PY - 2009

Y1 - 2009

N2 - We develop tests of the proportional hazards assumption, with respect to a continuous covariate, in the presence of unobserved heterogeneity with unknown distribution at the individual observation level. The proposed tests are specially powerful against ordered alternatives useful for modeling non-proportional hazards situations. By contrast to the case when the heterogeneity distribution is known up to â€¦nite dimensional parameters, the null hypothesis for the current problem is similar to a test for absence of covariate dependence. However, the two testing problems diÂ¤er in the nature of relevant alternative hypotheses. We develop tests for both the problems against ordered alternatives. Small sample performance and an application to real data highlight the usefulness of the framework and methodology.

AB - We develop tests of the proportional hazards assumption, with respect to a continuous covariate, in the presence of unobserved heterogeneity with unknown distribution at the individual observation level. The proposed tests are specially powerful against ordered alternatives useful for modeling non-proportional hazards situations. By contrast to the case when the heterogeneity distribution is known up to â€¦nite dimensional parameters, the null hypothesis for the current problem is similar to a test for absence of covariate dependence. However, the two testing problems diÂ¤er in the nature of relevant alternative hypotheses. We develop tests for both the problems against ordered alternatives. Small sample performance and an application to real data highlight the usefulness of the framework and methodology.

KW - Two-sample tests

KW - Increasing hazard ratio

KW - Trend tests

KW - Partial orders

KW - Mixed proportional hazards model

KW - Time varying coefficients

M3 - Discussion paper

T3 - SIRE Discussion Papers

BT - Testing for Proportional Hazards with Unrestricted Univariate Unobserved Heterogeneity

PB - Scottish Institute for Research in Economics

CY - St. Andrews

ER -

Testing for Proportional Hazards with Unrestricted Univariate Unobserved Heterogeneity

Abstract

Publication series

Keywords

Access to Document

Fingerprint

Research output

Testing for Proportional Hazards with Unrestricted Univariate Unobserved Heterogeneity

Cite this