i could be wrong, but i think you got the formulas for unequal and equal variances mixed up. I checked a fair number of online sources and they all have used "pooled standard deviation",i.e., Sp for equal or similar variances. But you have taken it the other way around. Please have a look and correct me if I'm wrong
If the confidence interval includes zero (e.g., the lower limit is negative and the upper limit is positive), this indicates that the difference between group means is not statistically significant at the chosen confidence level. In other words, zero is a plausible value for the true mean difference, which implies that any observed difference in the sample could be due to sampling error rather than a true difference in the population.
Hi thanks for great content, what if salary is highly skewed in both genders? Like if there is a male and female employee earns 3 times (outlier) higher than the others within their group?