In statistics, Welch's t test is an adaptation of Student's t-test intended for use with two samples having possibly unequal variances.

Therefore, it implies that the t -statistic being used should be based on unequal variances for the two samples.

Bartlett's test for unequal variances, which is derived from the likelihood ratio test under the normal distribution.

All data were tested for significance using two-sample Student's t-test with unequal variances.

Alternative estimators have been proposed in MacKinnon & White (1985) that correct for unequal variances of regression residuals due to different leverage.

In their paper, they applied Welch tests on a leukemia dataset [ 11 ] and demonstrated the importance of allowing for unequal variances.

Under the assumption of unequal variances, the associated degrees of freedom are variable, and the strict monotonic decreasing relationship between p values and test statistic values no longer holds.

Statistical comparisons using T-test (two-sample assuming unequal variances) were performed (significance level: 0.05).

Classical statistical methods do not provide exact tests to many statistical problems such as testing Variance Components and ANOVA under unequal variances.

If the sample sizes in the two groups being compared are equal, Student's original t-test is highly robust to the presence of unequal variances.