P. O. Johnson and J. Neyman (1936) proposed a general linear hypothesis testing procedure for testing the null hypothesis of no treatment difference in the presence of some covariates. This is generally known as the Johnson-Neyman (JN) technique. The need for the hypothesis testing step (often omitted) as originally presented and the appropriateness of making simultaneous inferences after the slope homogeneity assumption test were investigated. Three regression settings were used to simulate the conditions of slight, moderate, and severe slope heterogeneity. Within each setting, 3 sample size ratios (10:10, 20:20, and 30:30, respectively) were considered with 10,000 simulated experiments in each sample size ratio. Within 9 artificially generated data conditions, the total number of simulated experiments was 90,000. Simulation results indicate that the hypothesis testing procedure as originally presented was unnecessary, whereas the slope homogeneity test was important for making simultaneous inference. When the slope homogeneity test was rejected, the simultaneous error rate was found to approximate the nominal alpha level as set forth prior to conducting the research. A caution is issued against applying the JN technique when sample sizes are small. Seven tables present analysis results, and there is a nine-item list of references. (SLD)