356 Chapter 11 Simple Analysis of Variance
Key Terms
Analysis of variance (ANOVA)
(Introduction)
One-way analysis of variance
(Introduction)
Structural model (11.2)
Homogeneity of variance (11.2)
Homoscedasticity (11.2)
Error variance (11.2)
Heterogeneity of variance (11.2)
Heteroscedasticity (11.2)
(11.3)
(11.3)
(11.3)Treatment effect (11.3)
Expected value (11.3)
Sums of squares (11.4)
(11.4)
(11.4)
(11.4)
Summary table (11.4)
(11.4)
(11.4)
(11.4)
Balanced designs (11.7)
Heavy-tailed distributions (11.9)
Winsorized samples (11.9)
Resampling statistics (11.9)
Replicate (11.10)
Fixed-model analysis of variance (11.10)Random-model analysis of variance
(11.10)
Magnitude of the experimental effect
(11.11)
Eta-squared ( ) (11.11)
Correlation ratio (11.11)
Curvilinear regression (11.11)
Percent Reduction in Error (PRE) (11.11)
Omega-squared ( ) (11.11)
Root-mean-square standardized effect
(RMSSE) (11.11)
Noncentral Fdistribution (11.12)
Noncentrality Parameter (ncp) (11.12)v^2h^2dferrordftreatdftotalSSerrorSStreatSStotalMStreatment
MSwithin
MSerror
Exercises
11.1 To investigate the maternal behavior of laboratory rats, we move the rat pup a fixed distance
from the mother and record the time (in seconds) required for the mother to retrieve the pup
to the nest. We run the study with 5-, 20-, and 35-day old pups. The data are given below for
six pups per group.
5 days: 15 10 25 15 20 18
20 days: 30 15 20 25 23 20
35 days: 40 35 50 43 45 40
Run a one-way analysis of variance on the data.
11.2 Another aspect of the study by Eysenck (1974), referred to earlier, compared Younger and
Older subjects on their ability to recall material in the face of instructions telling them that
they would be asked to memorize the material for later recall—the Intentional group. (Pre-
sumably this task required a high level of processing.) The data follow, where the dependent
variable is the number of items recalled.
Younger: 21 19 17 15 22 16 22 22 18 21
Older: 101914 5101114151111
a. Run the analysis of variance comparing the means of these two groups.
b. Run an independent groups t test on the data and compare the results to those you
obtained in part (a).
11.3 Another way of looking at the data from Eysenck’s (1974) study is to compare four groups
of subjects. One group consisted of Younger subjects who were presented the words to be
recalled in a condition that elicited a Low level of processing. A second group involved
Younger subjects who were given a task requiring the Highest level of processing (as in
Exercise 11.2). The two other groups were Older subjects who were given tasks requiring
either Low or High levels of processing. The data follow.
Younger/Low: 8646765797
Younger/High: 21 19 17 15 22 16 22 22 18 21