Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Accounting for covariate measurement error in a Cox model analysis of recurrence of depression
Autore:
Liu, K; Mazumdar, S; Stone, RA; Dew, MA; Houck, PR; Reynolds, CF;
Indirizzi:
Univ Pittsburgh, Grad Sch Publ Hlth, Dept Biostat, Pittsburgh, PA 15261 USA Univ Pittsburgh Pittsburgh PA USA 15261 Biostat, Pittsburgh, PA 15261 USA Univ Pittsburgh, Sch Med, Dept Psychiat, Mental Hlth Intervent Res Ctr, Pittsburgh, PA 15261 USA Univ Pittsburgh Pittsburgh PA USA 15261 Res Ctr, Pittsburgh, PA 15261 USA
Titolo Testata:
JOURNAL OF PSYCHIATRIC RESEARCH
fascicolo: 3, volume: 35, anno: 2001,
pagine: 177 - 185
SICI:
0022-3956(200105/06)35:3<177:AFCMEI>2.0.ZU;2-Q
Fonte:
ISI
Lingua:
ENG
Soggetto:
NORTRIPTYLINE; LIKELIHOOD;
Keywords:
clinical trials; recurrent late life depression; regression calibration; maximum likelihood;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Social & Behavioral Sciences
Clinical Medicine
Life Sciences
Citazioni:
14
Recensione:
Indirizzi per estratti:
Indirizzo: Mazumdar, S Univ Pittsburgh, Grad Sch Publ Hlth, Dept Biostat, Pittsburgh,PA 15261 USA Univ Pittsburgh Pittsburgh PA USA 15261 tsburgh, PA 15261 USA
Citazione:
K. Liu et al., "Accounting for covariate measurement error in a Cox model analysis of recurrence of depression", J PSYCH RES, 35(3), 2001, pp. 177-185

Abstract

When a covariate measured with error is used as a predictor in a survival analysis using the Cox model, the parameter estimate is usually biased. In clinical research, covariates measured without error such as treatment procedure or sex are often used in conjunction with a covariate measured with error. In a randomized clinical trial of two types of treatments, we accountfor the measurement error in the covariate, log-transformed total rapid eye movement (REM) activity counts, in a Cox model analysis of the time to recurrence of major depression in an elderly population. Regression calibration and two variants of a likelihood-based approach are used to account for measurement error. The likelihood-based approach is extended to account farthe correlation between replicate measures of the covariate. Using the replicate data decreases the standard error of the parameter estimate for log(total REM) counts while maintaining the bias reduction of the estimate. We conclude that covariate measurement error and the correlation between replicates can affect results in a Cox model analysis and should be accounted for. In the depression data, these methods render comparable results that have less bias than the results when measurement error is ignored. (C) 2001 Elsevier Science Ltd. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 02/04/20 alle ore 21:30:20