Variable selection and Bayesian model averaging in case-control studies

• Published in: Statistics in medicine Vol. 20; no. 21; pp. 3215 - 3230
• Main Authors: Viallefont, Valerie, Raftery, Adrian E., Richardson, Sylvia
• Format: Journal Article
• Language: English
• Published: Chichester, UK John Wiley & Sons, Ltd 15.11.2001; Wiley
• Subjects: Analysis of Variance; Bayes Theorem; Biological and medical sciences; Biometry; Case-Control Studies; Female; Female genital diseases; Gynecology. Andrology. Obstetrics; Humans; Medical sciences; Odds Ratio; Risk Factors; Tumors; Uterine Cervical Neoplasms - epidemiology; Bayes estimation; Human; Statistical analysis; Average; Uterine cervix; Case control study; Malignant tumor; Epidemiology; Female genital diseases; Statistical method; Risk factor; Female; Uterine cervix diseases

Covariate and confounder selection in case‐control studies is often carried out using a statistical variable selection method, such as a two‐step method or a stepwise method in logistic regression. Inference is then carried out conditionally on the selected model, but this ignores the model uncertai...