This article compares 14 methods for testing the statistical significance of an intervening variable effect. An intervening variable (mediator) transmits the effect of an independent variable to a dependent variable. The commonly used Baron and Kenny (1986) approach has low statistical power. Two methods based on the distribution of the product and two difference-in-coefficients methods have the most accurate Type I error rates and greatest statistical power, except in one case where Type I error rates are too high. The best balance of Type I error and statistical power is the test of the joint significance of the two effects comprising the intervening variable effect. The article discusses methods for testing the effect of an intervening variable in models where an independent variable (X) causes an intervening variable (I), which in turn causes the dependent variable (Y). These models are used in various disciplines, with differing terminology and assumptions. The article evaluates the statistical performance of each method for testing the effect of an intervening variable. The study uses a Monte Carlo simulation to compare the statistical performance of the 14 methods. The simulation considers different effect sizes, sample sizes, and variable types (continuous and binary). The results show that the test of the joint significance of the two effects (α and β) has the most accurate Type I error rates and greatest statistical power. The difference-in-coefficients methods, particularly the Clogg et al. (1992) and Freedman and Schatzkin (1992) methods, also perform well. The product of coefficients methods, especially the distribution of products tests (P = zαzβ and z' = αβ/σαβ), also show high statistical power and accurate Type I error rates. The study concludes that the test of the joint significance of the two effects (α and β) is the most accurate and powerful method for testing the effect of an intervening variable. The difference-in-coefficients methods and the product of coefficients methods also perform well, but the joint significance test is the best overall. The results suggest that the joint significance test is the most reliable method for testing the effect of an intervening variable.This article compares 14 methods for testing the statistical significance of an intervening variable effect. An intervening variable (mediator) transmits the effect of an independent variable to a dependent variable. The commonly used Baron and Kenny (1986) approach has low statistical power. Two methods based on the distribution of the product and two difference-in-coefficients methods have the most accurate Type I error rates and greatest statistical power, except in one case where Type I error rates are too high. The best balance of Type I error and statistical power is the test of the joint significance of the two effects comprising the intervening variable effect. The article discusses methods for testing the effect of an intervening variable in models where an independent variable (X) causes an intervening variable (I), which in turn causes the dependent variable (Y). These models are used in various disciplines, with differing terminology and assumptions. The article evaluates the statistical performance of each method for testing the effect of an intervening variable. The study uses a Monte Carlo simulation to compare the statistical performance of the 14 methods. The simulation considers different effect sizes, sample sizes, and variable types (continuous and binary). The results show that the test of the joint significance of the two effects (α and β) has the most accurate Type I error rates and greatest statistical power. The difference-in-coefficients methods, particularly the Clogg et al. (1992) and Freedman and Schatzkin (1992) methods, also perform well. The product of coefficients methods, especially the distribution of products tests (P = zαzβ and z' = αβ/σαβ), also show high statistical power and accurate Type I error rates. The study concludes that the test of the joint significance of the two effects (α and β) is the most accurate and powerful method for testing the effect of an intervening variable. The difference-in-coefficients methods and the product of coefficients methods also perform well, but the joint significance test is the best overall. The results suggest that the joint significance test is the most reliable method for testing the effect of an intervening variable.