Question

1. Researchers hypothesized that boys’ aggressive behavior might be the consequence of their misattributing the intent of others (“actors”) in ambiguous situations. If the researchers were right, teaching these boys to interpret actors’ intent as something other than negative in ambiguous situations should ultimately lessen their aggressive behavior. To test this hypothesis, the researchers randomly assigned boys to one of three groups: (1) experimental (attribution retraining), (2) attention (simply paying attention to boys with no special training), and (3) control (no special attention given). After treatment, the boys were asked to rate actors’ intents in ambiguous situations. The hypothesis was that the average negative intent rating would be different among the groups. Data bearing on this hypothesis are presented in the table below. Analyze these data to test the researcher’s hypothesis. (From Shavelson, R. J., 1996). Use an ANOVA, follow-up procedures (if necessary), and effect size. (Make sure to check the assumptions.) Use a significance level of 0.05. Use SPSS for the analysis.
   

Group	Negative Intent Rating	Group	Negative Intent Rating
1	3	2	4
1	1	2	2
1	2	2	3
1	2	2	6
1	2	2	3
1	1	2	5
1	2	3	4
1	4	3	4
1	3	3	5
1	1	3	5
1	4	3	4
1	4	3	7
2	6	3	5
2	6	3	2
2	5	3	4
2	3	3	3
2	4	3	4
2	6	3	4

Answer 1

1. Assumption of independence

ANOVA assumes that the observations are random and that the samples taken from the populations are independent of each other. One event should not depend on another; that is, the value of one observation should not be related to any other observation.

2. Assumption of homogeneity of variance

ANOVA assumes that the variances of the distributions in the populations are equal.

3. Assumption of normality

ANOVA requires that the dependent variable is normally distributed in each group.

we don't bother about the first assumption as the experiment itself shows us

for the assumption of normality enter the data as shown here

now go to analyze<then to general linear model<then to univariate

now go to save option the u will get another dialogue box<choose standardised <click continue<click ok

now go to graphs<legacy dialogs<histogram<send standardised residual into variable panel<click ok

from the figure, we can observe that it is slightly skewed but overall normality assumption is clearly visible

now for homogeneity of variances

open analyze <then compare means<one-way anova<send the variables to respective panels

click options<homogenety of variance test< then continue<ok=======with this our anova test output will also be displayed

levene statistic significant value is greater than 0.05 hence our null hypothesis that the variances are equal is accepted

we can conclude that the variances are equal significantly at 0.05 level of significance

hence homogeneity assumption is also satisfied

now,
f statistic significant value is less than 0.05 hence we reject the null hypothesis that there is no significant difference between the groups

hence we can conclude that,

the average negative intent rating would be different among the groups.