ANCOVA Flashcards

1
Q

What does ANCOVA stand for?

A

Analysis of covariance

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What does the ANCOVA test for?

A

whether there is a difference between groups while controlling for the effects of other continuous variables that are not of primary interest but could influence the results.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are these continuous variables known as?

A

Covariates

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is the effect if adding a covariate?

A

Reduces error in the model

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

How do the assumptions for the ANCOVA compare to the ANOVA?

A

The same but two additional assumptions:

  1. Independence of covariate and treatment conditions - the covariate is independent of the effect of the independent variable
  2. Homogeneity of regression slopes- The assumption that the relationship between the covariate and the dependent variable holds for all levels of the independent variable.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What does it mean if the independence of covariate and treatment conditions assumption is not met? What effect does this have on the f statistic?

A

A part of the experimental effect will be explained by the covariate, while it should explain part of the error variance. This will reduce the F statistic

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

How can the independence of covariate and treatment conditions assumption be controlled for?

A

Randomizing participants to experimental groups or by matching groups to the covariate

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

How can the assumption of homogeneity of regression slope be tested for?

A

using a scatterplot of the interaction effect or on SPSS by building terms and checking the interaction effect between the independent variable and the covariate.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is the partial eta squared?

A

the effect size which takes the covariates into account. It uses the proportion of variance that a variable explains that is not explained by other variables in the analysis.

SSmodel / SSmodel+SSerror

How well did you know this?
1
Not at all
2
3
4
5
Perfectly