Question

6. Weight measurements of 30 patients from two distinct

hospitals are listed as follows:

          (Hospital 1--sample size = 16):  

          159,    159,   159, ...,150

(Hospital 2--sample size = 14):  

          105,    105,   105, ...,140

4%          

(a) Which one of the following statistical tests is the               most appropriate technique to determine if there is a            significant difference in the mean weights between the            two patient populations?

          TYPE YOUR ANSWER HERE: ____    

            

4%

    (b) What is the purpose of conducting the F test in this

          study?

          TYPE YOUR ANSWER HERE: ____

4%

      (c) Please draw the appropriate conclusion based on t test

          using the significance level .05 and the p-value equals

          to .01?

          TYPE YOUR ANSWER HERE: ____

4%

      (d) Using this study as an example to describe the                   statistical term ‘Type I error’

          TYPE YOUR ANSWER HERE: ____

Answer 1

a) We want to test,

H0: u1=u2 vs H1: u1 not equals u2

Now, since sample dataset is given for the two groups, the most appropriate test is independent samples t test.

b) The F test is used to test the equality of variance between two groups. So here the researcher might want to know that the population variances of the two groups are same or not using the F test.

c) Since the p-value of this test is 0.01<significance level of 0.05, we have sufficient evidence to Reject H0 here. So we can conclude that the two means are significantly different.

d) Type I error is Rejection of a true null hypothesis. Here the probability that we have committed a type I error is the p-value of this test ie 0.01 is significantly low.