This treatise is an introduction to the Cox Proportional Hazards technique for researchers who want to use in social science. It brings a new approach and method for researchers. This technique provides a statistical model for survival analysis. This statistical model can be used to explore the effect of several variables upon the time a specific event takes to occur. In addition, this model assists the researcher in making predictions about the effect of the treatment and the risk on the sample. Cox Proportional Hazards models are similar to logistic regression models as it is addressing the probability of survival. The interpretation of Cox regression’s statistic outputs is also similar to logistic regression models. The Cox regression can be attained in many statistical software applications. This paper applies the Cox regression model to the data set from the 1996 GSS on breast cancer, in order to demonstrate how it is used and interpreted. For the purposes of this paper, the Cox regression model includes estrogen reception, age, positive auxiliary lymph nodes and pathological tumor size (cm). I also discuss the assumptions that must be met in order to use this statistical method.
Cox Proportional Hazards, Survival Analysis, Probability of Survival, Variable, Covariate