Application of SAS macro to evaluated multiplicative and additive interaction in logistic and Cox regression in clinical practices / 中华流行病学杂志

ABSTRACT

Conditional logistic regression analysis and unconditional logistic regression analysis are commonly used in case control study,but Cox proportional hazard model is often used in survival data analysis.Most literature only refer to main effect model,however,generalized linear model differs from general linear model,and the interaction was composed of multiplicative interaction and additive interaction.The former is only statistical significant,but the latter has biological significance.In this paper,macros was written by using SAS 9.4 and the contrast ratio,attributable proportion due to interaction and synergy index were calculated while calculating the items of logistic and Cox regression interactions,and the confidence intervals of Wald,delta and profile likelihood were used to evaluate additive interaction for the reference in big data analysis in clinical epidemiology and in analysis of genetic multiplicative and additive interactions.