Causal mediation analysis is concerned with statistical inference about the mechanisms of causal effects, especially for observational data in which confounding variables are present. For example, is a gene responsible for causing lung cancer directly or only through its influence on smoking behavior? Is a youth community program effective in reducing juvenile crime rates because of its intermediate effect on changing the moral values of youngsters? In causal mediation analysis, a treatment T is assumed to have a causal effect on an outcome Y through two causal pathways. One is a direct pathway, T->Y. Another is a mediated or indirect pathway, T->M->Y, where M is called a mediator variable. Causal mediation analysis quantifies the direct and mediated causal effects on Y and provides unbiased estimation of these effects. This talk introduces the CAUSALMED procedure, new in SAS/STAT 15.1, for estimating causal mediation effects by the regression approach. Under the counterfactual outcome framework, the talk defines various causal mediation effects and describes the assumptions of causal mediation analysis. Numerical examples are used to illustrate the applications of the CAUSALMED procedure and the interpretations of various causal mediation effects.