Question

When Comparing means using the 2 Sample t Test:

(A) How many tails are appropriate for this test and why?

(B) What assumptions are made by your test?

(C) In general, what form of data model is this analysis most appropriate for? (How many IVs and DVs?)

Answer 1

We can use two tailed test for this situation . Here in null hypothesis we will state both the means are same and for alternative hypothesis will state both the means are different . The value of t critical varies for one tailed or two tailed test .

We are using two tailed test here because by that we get bigger confidence interval and hence the probability of getting the t score within the interval increases .

The populations from which the samples have been drawn should be normal

• The standard deviation of the populations should be equal i.e. σX2 = σY2 = σ2, where σ2 is unknown. This assumption can be tested by the F-test.
• Samples have to be randomly drawn independent of each other. There is however no requirement that the two samples should be of equal size - often times they would be unequal though the odd case of equal size cannot be ruled out.
• C. For this test we need two independent population means and two independent population variances.