Sample size determination for logistic regression on a logit-normal distribution. (June 2017)

• Record Type: Journal Article
• Authors: Kim, Seongho; Heath, Elisabeth; Heilbrun, Lance
• Is Part Of: Statistical methods in medical research. Volume 26:Number 3(2017)
• Page Start: 1237
• Page End: 1247
• Publication Date: 2017-06
• Subjects: Logistic regression -- logit-normal distribution -- power calculation -- sample size determination -- transformation; Medicine -- Research -- Statistical methods -- Periodicals; Research -- Periodicals; Review Literature -- Periodicals; Statistics -- methods -- Periodicals; Médecine -- Recherche -- Méthodes statistiques -- Périodiques; 610.727
• DOI: 10.1177/0962280215572407
• Languages: English
• ISSNs: 0962-2802

Abstract

Although the sample size for simple logistic regression can be readily determined using currently available methods, the sample size calculation for multiple logistic regression requires some additional information, such as the coefficient of determination (R cov 2 ) of a covariate of interest with other covariates, which is often unavailable in practice. The response variable of logistic regression follows a logit-normal distribution which can be generated from a logistic transformation of a normal distribution. Using this property of logistic regression, we propose new methods of determining the sample size for simple and multiple logistic regressions using a normal transformation of outcome measures. Simulation studies and a motivating example show several advantages of the proposed methods over the existing methods: (i) no need forR cov 2 for multiple logistic regression, (ii) available interim or group-sequential designs, and (iii) much smaller required sample size.