The Johnson-Neyman (J-N) technique (P. Johnson and N. Neyman, 1936) is used to determine areas of significant difference in a criterion variable between two or more groups in situations of linear regression. In using this technique, researchers have encountered difficulties with results, possibly related to the J-N technique's sensitivity to violations of certain assumptions and conditions. For this study, Monte Carlo simulations were performed to determine the effect that sample size and variance have on the J-N technique. The simulations examined the hypothesis that unequal ratios of sample size and variance between two groups may create anomalies in the results of the J-N computation. The results do not show anomalies in the output, and further show that the J-N technique produces wider regions of significance as the total sample size increases. The size of variance ratios, as well as the equality of variance and sample size ratios, did not seem to affect the results dramatically. Appendixes contain the Statistical Analysis System program for the simulations and the results of the simulations in table form. (Contains 17 references.) (Author/SLD)