PSYCH 100B Lecture Notes - Analysis Of Variance, Bonferroni Correction
Results
Figure 1 presents the average degree of compliance to requests when they were presented
in the form of unusual versus typical requests and depending on the subjects’ relationship to the
asker. Looking at the pattern of the results displayed in Figure 1, it appears that requests, in
general, had a higher degree of compliance when asked in an unusual manner than when they
were asked in a typical manner and when given by a friend rather than a stranger. The extent to
which the degree of compliance was affected by the request type, however, appears to depend on
the relationship to the asker. More specifically, when requests were given by strangers, the type
of request appears to have had a large effect on their degree of compliance; whereas, when those
same requests were given by friends, the type of request appears to have had little or no effect on
their compliance.
To test these apparent effects, the data were analyzed using a two-way within-subject
ANOVA, which revealed a significant main effect of request type, such that the average degree
of compliance was significantly higher when requests were given in an unusual form (M = 4, SD
= x) than when they were given in a typical form (M = 2.75, SD = x), regardless of who was
giving the request, F (x, x) = x, MSE = x, p = x. A significant main effect of the relationship to
the asker was also revealed, such that the average degree of compliance was significantly higher
when items were presented by friends (M = 4.5, SD = x), than when they were presented by
strangers (M = 2.25, SD = x), regardless of the type of request made, F (x, x) = x, MSE = x, p =
x. Additionally, the apparent interaction between the relationship to the asker and request type
that is indicated in Figure 1 was also revealed to be significant F (x, x) = x, MSE = x, p = x.
To compare individual condition means, multiple post-hoc t-tests, with a Bonferroni
correction to maintain an alpha level of 0.5, were conducted. When given by a stranger, the
average degree of compliance for requests was revealed to be significantly higher when they
were presented in an unusual form (M = 3.2, SD = x) than when they were presented in a typical
form (M = 1.3, SD = x), t (x) = x, p = x. In contrast, when given by a friend, the difference in
average degree of compliance for requests presented in an unusual form (M = 4.8, SD = x) versus
a typical form (M = 4.2, SD = x) was not found to be significant, t (x) = x, p = x. Thus, as
indicated in Figure 1, whereas the request type significantly affected the compliance of requests
given by a stranger, it did not have a significant effect on the compliance of requests given by
friends.
Furthermore, when requests were presented in an unusual form, the average degree of
compliance for requests was found to be significantly higher when they were given by a friend
(M = 4.8, SD = x) than when they were given by a stranger (M = 3.2, SD = x), t (x) = x, p = x.
When requests were given in a typical form, similarly, the average degree of compliance for
requests was found to be significantly greater when they were presented by friends (M = 4.2, SD
= x) than by strangers (M = 1.3, SD = x), t (x) = x, p = x.
find more resources at oneclass.com
find more resources at oneclass.com
Document Summary
To test these apparent effects, the data were analyzed using a two-way within-subject. Figure 1 presents the average degree of compliance to requests when they were presented in the form of unusual versus typical requests and depending on the subjects relationship to the asker. The extent to which the degree of compliance was affected by the request type, however, appears to depend on the relationship to the asker. Anova, which revealed a significant main effect of request type, such that the average degree of compliance was significantly higher when requests were given in an unusual form (m = 4, sd. = x) than when they were given in a typical form (m = 2. 75, sd = x), regardless of who was giving the request, f (x, x) = x, mse = x, p = x. To compare individual condition means, multiple post-hoc t-tests, with a bonferroni correction to maintain an alpha level of 0. 5, were conducted.
