Lecture 17 - Exploratory Factor Analysis Theory Flashcards

1
Q

What is a latent variable?

A

A variable which cannot be measured directly but that has aspects which may be measured

E.g. You can’t measure cognitive function directly, but you can measure things such as word comprehension and spatial imagination

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

What does EFA stand for

A

Exploratory factor analysis

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

What does EFA aim to do

A

To understand the structure of a set of variables

To reduce a large set of variables to a smaller set of variables, without losing information

To explain correlations between variables in terms of common factors and cross loadings

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

What is the R-Matrix in EFA and what does it do?

A

It is a table showing correlations between variables

1 means each variable is completely correlated with itself, of course

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

What does a scree plot show?

A

Eigenvalue vs factor

Helps us decide how many factors to use in EFA

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

What is the K1 rule in EFA

A

Using all factors with an eigenvalue greater than 1

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

What is the scree test (Catell) in EFA

A

The cutoff point for what factors to use is the point of inflection

So one line comes at a different angle to the other, and this has something to do with it

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

What is the parallel analysis (Horn) approach to deciding factors in EFA

A

Compare eigenvalues to randomly produced ones. Use those factors that have eigenvalues bigger than the random produced eigenvalues

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

How do we graphically represent factors in EFA

A

A graph from -1 to +1 on both axis, meeting in the middle like a +. These two axis represent factors

Then we plot the variables onto this graph

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

What’s a problem with graphically representing factors in EFA

A

Loadings are highest on the first factor so interpretation is difficult

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

Why do we do rotation in EFA

A

We rotate the axis to maximise the loading of a cluster onto one factor

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

What are the three types of rotation in EFA?

A

Orthogonal (varimax)
Oblique (direct oblimin)
Parameter (o with a weird devil tail coming out of it)

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

What is the absolute minimum number of participants needed for EFA

A

100

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

What does communality mean?

A

The proportion of variance that is common to each variable

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

What does RIT stand for?

A

Recaptured item technique

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