7: Factor Analysis Mechanics, Validity and Reliablity Flashcards

1
Q

Which output matrices follow principal axis factoring and oblimin rotation?

A

Factor, pattern and structure matrices.

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

Which output matrices follow principal components factoring and varimax rotation?

A

Component and rotation component matrices.

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

Which output matrices follow principal axis factoring and varimax rotation?

A

Factor and rotated factor matrices.

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

Describe simple indicators.

A

Highs indicate only one factor.

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

What is acquiescence bias?

A

Where some (e.g. uninterested) participants response positively to all items, no matter how they are worded.

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

Which factor extraction includes the full correlation matrix, with error?

A

Principal component analysis.

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

Which factor extraction is only interested in the common variance between factors?

A

Principal axis factoring.

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

What is the extraction communality?

A

The estimate of how much is shared by one variable and the extracted factors.

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

What is the initial communality?

A

1.0 for PCA and estates for FA.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

How is the initial communality estimated for factor analysis?

A

Using the squared multiple correlation between as given variable and all other variables in a set, and updating it each time through the iteration process to find the optimal extraction.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

In FA, when is a large sample needed?

A

To analyses complex patterns, more items and less clear factors.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What does it mean if a variable has low SMC/initial communality?

A

It is an outlier and another similar variable must be found, or this one must be dropped.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What does it mean if a variable has low MSA?

A

It does not share enough variance to be a reliable factor, and more must be found, or this one must be dropped.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What does it mean if a variable has low KMO?

A

The whole matrix has poor definition of factors and the solution will be poor and unstable.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What do individual cells in the AIC represent?

A

The negative of the partial correlation of the respective row and column with all other variables partialled out.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

How many items should a factor be measured by?

A

At least 3.

17
Q

What does MSA summarise?

A

The AIC elements for each variable.

18
Q

Is MSA is near 1, what does that mean?

A

A variable does covary with at least 2 others, and so it belongs.

19
Q

What does KMO summarise?

A

The individual items MSAs.

20
Q

What should you do if KMO is middling to low?

A

Look at individual MSAs to see if the sample variable is wrong.

21
Q

What is in a reproduced correlations matrix?

A

The implied correlations in a factor model and the residuals.

22
Q

What do small residuals in reproduced correlations mean?

A

They are close to the original correlations and the factor model captures the constructs well.

23
Q

What do large residuals in reproduced correlations mean?

A

Some aspect of the data has not been captured by the factor model.

24
Q

What 3 things may cause large residuals?

A

Wrong interpretation, too many unreliable measures, or a methodological problem distorting the solution.

25
Q

When is PAF most appropriate?

A

When trying to understand an underlying construct that cannot be directly measured.

26
Q

When is PCA most appropriate?

A

When trying to reduce a data set to a smaller number of independent measures it when things of interest can be measured directly.

27
Q

What are factor scores?

A

Estimates of what the “score” might be on some latent variable.

28
Q

What analysts commonly used factor scores?

A

Principal components.

29
Q

What is content validity?

A

Does the variable measure what we think it does?

30
Q

How can we check content validity?

A

Face validity and manipulation checks.

31
Q

How is predictive validity usually measured?

A

Regression.

32
Q

How is convergent and discriminant validity usually measured?

A

Correlations.

33
Q

How do factor loadings act as a measure of reliability in a simple latent variable model?

A

When squared, they capture how much of the variance of the factors are predicted from the latent variable they measure.

34
Q

What can artificially inflate Cronbach’s alpha?

A

Using a large number of items and items that are only trivially different.