Lecture 4 talked about a two-sample hypothesis test for the cell-means model (i.e., i=1,2 ). The same procedure can be used for testing the null hypothesis H0:1=2 against the alternative HA:1=2 under the effects model. (a) (1 point) Re-state H0 and HA in terms of the estimable function 12. (b) (1 point) Assuming we have to estimate 2, state the test-statistic and its null distribution. Hint: This will be the same as for the test under the cell-means model. (c) (1 point) State the distribution of the test statistic under the alternative hypothesis. Be as specific as possible. Hint: Your answer should closely resemble the answer for the cell-means model in the lecture slides but the noncentrality parameter should involve 1 and 2, not 1 and 2. Lecture 4 talked about a two-sample hypothesis test for the cell-means model (i.e., i=1,2 ). The same procedure can be used for testing the null hypothesis H0:1=2 against the alternative HA:1=2 under the effects model. (a) (1 point) Re-state H0 and HA in terms of the estimable function 12. (b) (1 point) Assuming we have to estimate 2, state the test-statistic and its null distribution. Hint: This will be the same as for the test under the cell-means model. (c) (1 point) State the distribution of the test statistic under the alternative hypothesis. Be as specific as possible. Hint: Your answer should closely resemble the answer for the cell-means model in the lecture slides but the noncentrality parameter should involve 1 and 2, not 1 and 2