Steven H. answered 08/18/20
Former teacher with 10yrs experience
This question can be answered in one of two ways, depending on whether or not the variances are equal.
If they are equal, then you would use standard error pooled. If they are unequal, then you would use standard error un-pooled.
If equal, the t-statistic will look like this:
t = (x1-x2)/sqrt(((n1-1)*s1^2 +(n2-1)s2^2)/(n1+n2-2))
If unequal, the t-statistic will look like this:
t = (x1-x2)/sqrt((s1^2/n1 + s2^2/n2))