statistics review 14 logistic regression统计评估14逻辑回归.pdf

Critical Care February 2005 Vol 9 No 1 Bewick et al. Review Statistics review 14: Logistic regression 1 1 2 Viv Bewick , Liz Cheek and Jonathan Ball 1Senior Lecturer, School of Computing, Mathematical and Information Sciences, University of Brighton, Brighton, UK 2Senior Registrar in ICU, Liverpool Hospital, Sydney, Australia Corresponding author: Viv Bewick, v.bewick@brighton.ac.uk Published online: 13 January 2005 Critical Care 2005, 9:112-118 (DOI 10.1186/cc3045) This article is online at /content/9/1/112 © 2005 BioMed Central Ltd Abstract This review introduces logistic regression, which is a method for modelling the dependence of a binary response variable on one or more explanatory variables. Continuous and categorical explanatory variables are considered. Keywords binomial distribution, Hosmer–Lemeshow test, likelihood, likelihood ratio test, logit function, maximum likelihood estimation, median effective level, odds, odds ratio, predicted probability, Wald test Introduction The logit function is defined as the natural logarithm (ln) of Logistic regression provides a method for modelling a binary the odds [1] of death. That is, response variable, which takes values 1 and 0. For example, we may wish to investigate how death (1) or survival (0) of p patients can be predicted by the level of one or