Home > Research > Publications & Outputs > On the equivalence of posterior inference based...
View graph of relations

On the equivalence of posterior inference based on retrospective and prospective likelihoods

Research output: Working paper

Published

Standard

On the equivalence of posterior inference based on retrospective and prospective likelihoods. / Ghosh, M.; Song, J.; Forster, Jonathan J. et al.
2010.

Research output: Working paper

Harvard

APA

Vancouver

Author

Bibtex

@techreport{ea94d58e4ded4048937fe363d1de29cd,
title = "On the equivalence of posterior inference based on retrospective and prospective likelihoods",
abstract = "The paper develops a class of priors which leads to equivalent posterior inference for odds ratio parameters based on prospective and retrospective models for categorical response data. The results are applicable to both unmatched and matched case-control studies. The proposed method can accommodate multiple and possibly ordered disease status as well as any arbitrary link function and is not restricted to the conventional logit link. The results are applied to the analysis of an ongoing case-control study on colorectal cancer.",
keywords = "case-control, colorectal cancer, multiplicative intercept, stereotype, stratification",
author = "M. Ghosh and J. Song and Forster, {Jonathan J.} and Robin Mitra and B. Mukherjee",
year = "2010",
language = "English",
type = "WorkingPaper",

}

RIS

TY - UNPB

T1 - On the equivalence of posterior inference based on retrospective and prospective likelihoods

AU - Ghosh, M.

AU - Song, J.

AU - Forster, Jonathan J.

AU - Mitra, Robin

AU - Mukherjee, B.

PY - 2010

Y1 - 2010

N2 - The paper develops a class of priors which leads to equivalent posterior inference for odds ratio parameters based on prospective and retrospective models for categorical response data. The results are applicable to both unmatched and matched case-control studies. The proposed method can accommodate multiple and possibly ordered disease status as well as any arbitrary link function and is not restricted to the conventional logit link. The results are applied to the analysis of an ongoing case-control study on colorectal cancer.

AB - The paper develops a class of priors which leads to equivalent posterior inference for odds ratio parameters based on prospective and retrospective models for categorical response data. The results are applicable to both unmatched and matched case-control studies. The proposed method can accommodate multiple and possibly ordered disease status as well as any arbitrary link function and is not restricted to the conventional logit link. The results are applied to the analysis of an ongoing case-control study on colorectal cancer.

KW - case-control, colorectal cancer, multiplicative intercept, stereotype, stratification

M3 - Working paper

BT - On the equivalence of posterior inference based on retrospective and prospective likelihoods

ER -