Chapter 14 Problems

2. For an independent measures design, the variability within treatments is the appropriate error term. For repeated measures, however, you must subtract individual differences from the variability within treatments to obtain a measure of experimental error.

4. a. k = 4
   b. n = 13 subjects.

6. The null hypothesis states that the mean number of errors does not change across sessions, Ho: mu-1 = mu-2 = mu-3 = mu-4. The critical value is 4.76.

     Source              SS     df          MS
___________________________________________________________________
Between Treatments       18      3         6.00     F(3,6) = 8.96
Within Treatments        12      8
   Between Subjects       8      2
   Error                  4      6         0.67
Total                    30     11

Reject Ho and conclude that there is a significant practice effect.

8. a. The null hypothesis states that there is no difference between treatments, Ho: u-1 = u-2. For an independent-measures design, the critical value is 4.26.

     Source              SS     df          MS
_____________________________________________________________________
Between Treatments        8      2           4      F(2,9) = 1.06
Within Treatments        34      9           3.78
Total                    42     11

Fail to reject Ho. There are no significant differences with the independent ANOVA.

b. The null hypothesis states that there is no difference between treatments, Ho: mu-1 = mu-2. For a repeated-measures design, the critical value is 5.14.

     Source              SS     df          MS
___________________________________________________________________
Between Treatments        8      2           4     F(2,6) = 5.97
Within Treatments        34      9
   Between Subjects      30      3
   Error                  4      6         0.67
Total                    42     11

c. The repeated measures design removes error variability due to individual differences and therefore is more likely to detect a treatment effect.

10. a. First mean is equal 3, second mean is equal to 5, and third mean is equal to 1.

b. The null hypothesis states that the position in the list has no effect on the number of errors, Ho, mu-1 = mu-2 = mu-3. The critical value is 5.14.

     Source              SS     df          MS
___________________________________________________________________
Between Treatments       32      2           6     F(2,10) = 8.00
Within Treatments        24      9
   Between Subjects      12      3
   Error                 12      6           2
Total                    56     11

Reject Ho and conclude that the number of errors differes significantly with the position in the list. Most errors are made in the middle of the list, with fewer errors at the beginning, and fewest errors on the last items in the list.

12. a. The null hypothesis states that there is no difference between the two treatments, Ho: mu-D = 0. The critical region consists of t values beyond plus/minus 3.182. The mean difference is +4. SS for the difference scores is 48, and t(3) = 2.00. Faile to reject Ho.

b. The null hypothesis states that there is no difference between treatments, Ho: mu-1 = mu-2. The critical value is F = 10.13.

     Source              SS     df          MS
___________________________________________________________________
Between Treatments       32      1          32     F(1,3) = 4.00
Within Treatments        36      6
   Between Subjects      12      3
   Error                 24      3           8
Total                    68      7

Fail to reject Ho. Note that F = t-squared.

14. a. k = 3

b. n = 15

16. Answer found below

     Source              SS     df          MS
___________________________________________________________________
Between Treatments       48      2          24    F(2,28) = 8.00
Within Treatments       120     42
   Between Subjects      36     14
   Error                 84     28           3
Total                   168     44

18. Answer below

     Source              SS     df          MS
___________________________________________________________________
Between Treatments      270      3          90    F = 9.00
Within Treatments       410     28
   Between Subjects     200      7
   Error                210     21          10
Total                   680     31

20. a. Means are 6, 4, and 2.

b. The null hypothesis states that there is no change in motivation across the three grade levels, Ho: mu-1 = mu-2 = mu-3. The critical value is 4.46.

     Source              SS     df          MS
___________________________________________________________________
Between Treatments     40.00     2          20    F(2,8) = 0.79
Within Treatments     240.00    12
   Between Subjects    37.33     4
   Error              202.67     8          25.33
Total                 280.00    14

Fail to reject Ho. There are no significant differences among the three grade levels.

c. The date in problem 9 have substantially more variability within treatments which increases the error variability. As a result, the sample mean differences are not significant.

22. The null hypothesis states that there are no differences in adaptation among the four regions, Ho: mu-1 = mu-2 = mu-3 = mu-4. The critical value is 8.65.

     Source              SS     df          MS
___________________________________________________________________
Between Treatments    225.96     3         75.32    F(3,18) = 215.20
Within Treatments      20.22    24
   Between Subjects    13.91     6
   Error                3.31    18          0.35
Total                 246.19    27