In: Statistics and Probability
The following scores are from an independent-measures study comparing two treatment conditions. (Be sure to include your critical values)
a. Use an independent -measures t-test with a = 0.05 to determine whether there is a significant mean difference between the two treatments.
b. Use an ANOVA with a = 0.05 to determine whether there is a significant mean difference between the two treatments. You should find that F = t2.
Treatment I Treatment II
| 10 | 7 | n=16 | 
| 8 | 4 | g=120 | 
| 7 | 9 | Σx2 = 1036 | 
| 9 | 3 | |
| 13 | 7 | |
| 7 | 6 | |
| 6 | 10 | |
| 12 | 2 | 
Hypotheses are:

a)
Following is the output of independent sample t test:
| Hypothesis Test: Independent Groups (t-test, pooled variance) | ||||
| T1 | T2 | |||
| 9.00 | 6.00 | mean | ||
| 2.51 | 2.83 | std. dev. | ||
| 8 | 8 | n | ||
| 14 | df | |||
| 3.000 | difference (T1 - T2) | |||
| 7.143 | pooled variance | |||
| 2.673 | pooled std. dev. | |||
| 1.336 | standard error of difference | |||
| 0 | hypothesized difference | |||
| 2.24 | t | |||
| .0414 | p-value (two-tailed) | |||
| F-test for equality of variance | ||||
| 8.00 | variance: T2 | |||
| 6.29 | variance: T1 | |||
| 1.27 | F | |||
| .7585 | p-value | |||
The p-vaue of t test is; 0.0414
Since p-value is less than 0.05 so we reject the null hypothesis. That is we can conclude that there is a significant mean difference between the two treatments.
Critical values:
Degree of freedom: df=n-1=14
Test is two tailed so critical values of t test using excel function "=TINV(0.05,14)" are: +/- 2.145
Rejection region:
If t < -2.145 or t > 2.145, reject H0
b)
Following is the output of ANOVA:
| Anova: Single Factor | ||||||
| SUMMARY | ||||||
| Groups | Count | Sum | Average | Variance | ||
| T1 | 8 | 72 | 9 | 6.285714 | ||
| T2 | 8 | 48 | 6 | 8 | ||
| ANOVA | ||||||
| Source of Variation | SS | df | MS | F | P-value | F crit | 
| Between Groups | 36 | 1 | 36 | 5.04 | 0.041443 | 4.60011 | 
| Within Groups | 100 | 14 | 7.142857 | |||
| Total | 136 | 15 | ||||
The p-value of F test is: 0.0414
Since p-value is less than 0.05 so we reject the null hypothesis. That is we can conclude that there is a significant mean difference between the two treatments.
Here we have F = 5.04 and t = 2.24
t^2 = 2.24*2.24 = 5.0176
That is F = t^2 verified.
Critical values:
Using excel function "=FINV(0.05,1,14)" is: 4.600
Rejection region:
If F > 4.600, reject H0