Week 8 Flashcards

ANCOVA (8 cards)

1
Q

Running an ANCOVA allows researchers to…

a. reduce error variance
b. decrease systematic variance
c. increase systematic variance
d. increase error variance

A

a. reduce error variance

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

A non-significant effect of covariate and a significant effect of the IV in an ANCOVA indicates that…

a. the variance in the DV is accounted for by differences between the IV rather than the association between the covariate and DV
b. the error variance is accounted for by differences between the IV rather than the association between the covariate and DV
c. the variance in the DV is attributable to the association between the covariate and DV rather than due to differences across the IV
d. the variance in the DV is attributable to both the differences across the IV and the association between the covariate and DV

A

a. the variance in the DV is accounted for by differences between the IV rather than the association between the covariate and DV

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

ANCOVA controls for covariation…
a. by random allocation
b. statistically
c. by matching participants
d. by bootstrapping the data

A

b. statistically

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

When testing the independence of the covariate and the IV in an ANOVA you want the result to be…
a. have a large F value
b. non-significant
c. Have lots of degrees of freedom
d. Significant

A

b. non-significant

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

Covariate variables must be
a. range from positive to negative
b. continuous
c. associated with confounding variables
d. categorical

A

b. continuous

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is ANCOVA

A

Analysis of covariance. Includes one or more continuous variable (covariates) within the ANOVA. It allows you to test differences in group means and interactions, just like ANOVA, while controlling for (partialling out) effects of the covariates.

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

Can anything be a covariate?

A

Covariates should be continuous, and there should be a theoretical reason for including covariate (based on theories or previous literature)

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