Ch5: Five ANOVA Assumptions

Question 1

Three fundamental assumptions

Answer 1

a) the error components associated with the scores of the dependent variable are independent of one another
b) these errors are normally distributed
c) the variances across the levels of groups of the independent variable are equal

Question 2

the first assumption

Answer 2

the residual or error component of the Yi scores (the difference between these scores and the group mean) is random and independent across individual observations

Question 3

autocorrelation

Answer 3

the propinquity of the cases to each other in time

Question 4

the second assumption

Answer 4

the error components associated with Yi are normally distributed

Question 5

leptokurtic distribution

Answer 5

tends to have tails that are higher than the normal curve is and bunched in the middle, producing a peak look

Question 6

platykurtic distribution

Answer 6

has a flatter, more evenly distributed look than the normal curve

Question 7

Outliers

Answer 7

Standarized values exceeding +- 2.5 can be designated outliers

Question 8

Central limit theorem

Answer 8

as increase the sample size (n), the resulting sample mean Y bar will increasingly approximate a normal distribution

Question 9

homogeneity of variance or homoscedasticity

Answer 9

the distribution of residual errors for each group have equal variances

Question 10

Three causes of heteroscedasticity

Answer 10

Classfication independent variables such as gender or ethnicity may have unique variances associated with the scores on the dependent variable

an experimental manupulation of an independent variable can encourage participants to behave more similariry or differently than a control condition.

variability on some dependent variables may be related to group size

Question 11

floor or ceiling effect

Answer 11

where participants cannot score any lower or higher on the dependent measure because of intrinsic or extrinsic constraints