Using Large Sample Variance Instead of Pooled Variance in Samples Taken From Different Distributions Comparing Groups in Unblance Designs

In this study, t‐test and using high variance group t‐test were comparedin terms of type i error rate and power of the test. in the experiments, the samplesincluding unequal observations were drawn from populations, z(0, 1), studentt(10), x² (³) distributions. type i error rate and power of the test were obtained from the samples of 100000 simulation trials. as a result, new test provided more reliable results than the other for both small sample size and heterogeneous variances. but new test is more high with regard to type i error rate than 0.05 error rate.