Factor Analysis

Factor analysis attempts to bring inter-correlated

variables together under more general, underlying
variables.

More specifically, the goal of factor analysis is to

reduce “the dimensionality of the original space and
to give an interpretation to the new space, spanned
by a reduced number of new dimensions which are
supposed to underlie the old ones” (Rietveld & Van
Hout 1993:254).
Rietveld, T. & Van Hout, R. (1993). Statistical Techniques for the Study of Language and
Language Behaviour. Berlin – New York: Mouton de Gruyter.
1
Thursday 4 February 2021 05:17 AM
 Factor Analysis
Or to explain the variance in the observed variables
in terms of underlying latent factors” (Habing
2003).

Thus, factor analysis offers not only the possibility

of gaining a clear view of the data, but also the
possibility of using the output in subsequent
analyses (Field 2000; Rietveld & Van Hout 1993).
Field, A. (2000). Discovering Statistics using SPSS for Windows. London – Thousand Oaks
– New Delhi: Sage publications.

Rietveld, T. & Van Hout, R. (1993). Statistical Techniques for the Study of Language and
Language Behaviour. Berlin – New York: Mouton de Gruyter.
2
Thursday 4 February 2021 05:17 AM
 Factor Analysis
The starting point of factor analysis is a correlation
matrix, in which the inter-correlations between the
studied variables are presented. The dimensionality
of this matrix can be reduced by “looking for
variables that correlate highly with a group of other
variables, but correlate very badly with variables
outside of that group” (Field 2000: 424). These
variables with high inter-correlations could well
measure one underlying variable, which is called a
‘factor’.
Field, A. (2000). Discovering Statistics using SPSS for Windows. London – Thousand Oaks
– New Delhi: Sage publications.

3
Thursday 4 February 2021 05:17 AM
 Factor Analysis
Factor analysis is a method of dimension reduction.

It does this by seeking underlying unobservable

(latent) variables that are reflected in the observed
variables (manifest variables).

4
Thursday 4 February 2021 05:17 AM
 Factor Analysis
There are many different methods that can be used
to conduct a factor analysis

There are many different types of rotations that

can be done after the initial extraction of factors.

You also need to determine the number of factors

that you want to extract.

5
 Factor Analysis
Given the number of factor analytic techniques and
options, it is not surprising that different analysts
could reach very different results analysing the
same data set.

6
 Factor Analysis
However, all analysts are looking for a simple
structure.

Simple structure is a pattern of results such that

each variable loads highly onto one and only one
factor.

7
 Factor Analysis
Factor analysis is a technique that requires a large
sample size.

Factor analysis is based on the correlation matrix of

the variables involved, and correlations usually need
a large sample size before they stabilize.

8
 Factor Analysis
As a rule of thumb, a bare minimum of 10 observations
per variable is necessary to avoid computational
difficulties.
Number of Cases Prospects

50 very poor

100 poor

200 fair

300 good

500 very good

1000 excellent

Comrey and Lee (1992) A First Course In Factor Analysis

9
 Factor Analysis
In this example I have included many options, while
you may not wish to use all of these options, I have
included them here to aid in the explanation of the
analysis.

10
 Factor Analysis
In this example we examine students assessment of
academic courses. We restrict attention to 12 variables.
Item 13 INSTRUCTOR WELL PREPARED
Item 14 INSTRUCTOR SCHOLARLY GRASP
Item 15 INSTRUCTOR CONFIDENCE
Item 16 INSTRUCTOR FOCUS LECTURES
Item 17 INSTRUCTOR USES CLEAR RELEVANT EXAMPLES
Item 18 INSTRUCTOR SENSITIVE TO STUDENTS
Item 19 INSTRUCTOR ALLOWS ME TO ASK QUESTIONS
Item 20 INSTRUCTOR IS ACCESSIBLE TO STUDENTS OUTSIDE CLASS
Item 21 INSTRUCTOR AWARE OF STUDENTS UNDERSTANDING
Item 22 I AM SATISFIED WITH STUDENT PERFORMANCE EVALUATION
Item 23 COMPARED TO OTHER INSTRUCTORS, THIS INSTRUCTOR IS
Item 24 COMPARED TO OTHER COURSES THIS COURSE WAS

Scored on a five point Likert scale, seven is better. 11

 Factor Analysis
In this example we examine students assessment of
academic courses. We restrict attention to 12 variables.

Scored on a five point Likert scale.

12
 Factor Analysis
Analyze > Dimension Reduction > Factor

13
 Factor Analysis
Select variables 13-24 that is “instructor well
prepared” to “compared to other courses this course
was”. By using the arrow button.

Use the buttons at the side of the screen to set additional options.
14
 Factor Analysis
Use the buttons at the side of the previous screen to set
the Descriptives. Employ the Continue button to return to
the main Factor Analysis screen.

Note the request for a determinant.

15
 Factor Analysis
Use the buttons at the side of the main screen to set the
Extraction. Employ the Continue button to return to the
main Factor Analysis screen.

Note the request for Principal axis factoring, 3 factors

and a scree plot. 16
 Factor Analysis
Use the buttons at the side of the main screen to set the
Rotation (Varimax). Employ the Continue button to return
to the main Factor Analysis screen.

17
 Factor Analysis
Varimax rotation tries to maximize the variance of each of
the factors, so the total amount of variance accounted for
is redistributed over the three extracted factors.

18
 Factor Analysis
Select the OK button to proceed with the analysis, or
Paste to preserve the syntax.

Syntax for varimax and 3 factors, alternatives promax and 2

factor
/variables item13 item14 item15 item16 item17 item18 item19 item20
item21 item22 item23 item24
/print initial det kmo repr extraction rotation fscore univaratiate
/format blank(.30)
/plot eigen rotation
/criteria factors(3)
/extraction paf
/rotation varimax
/method = correlation. 19
 Factor Analysis
Descriptive Statistics

The descriptive statistics

Mean Std. Deviation Analysis N
INSTRUC WELL
4.46 .729 1365
PREPARED

table is output because we INSTRUC SCHOLARLY

GRASP
4.53 .700 1365

used the univariate option.

INSTRUCTOR
4.45 .732 1365
CONFIDENCE
INSTRUCTOR FOCUS
4.28 .829 1365
LECTURES
INSTRUCTOR USES

Mean - These are the means CLEAR RELEVANT

EXAMPLES
4.17 .895 1365

of the variables used in the INSTRUCTOR SENSITIVE

TO STUDENTS 3.93 1.035 1365

factor analysis. INSTRUCTOR ALLOWS

ME TO ASK QUESTIONS
4.08 .964 1365
INSTRUCTOR IS
ACCESSIBLE TO
3.78 .909 1365
Are they meaningful for a
STUDENTS OUTSIDE
CLASS

Likert scale!
INSTRUCTOR AWARE OF
STUDENTS 3.77 .984 1365
UNDERSTANDING
I AM SATISFIED WITH
STUDENT
3.61 1.116 1365
Norman, G. (2010). Likert scales, levels of PERFORMANCE
EVALUATION
measurement and the “laws” of statistics. COMPARED TO OTHER

Advances in health sciences education, 15(5),

INSTRUCTORS, THIS 3.81 .957 1365
INSTRUCTOR IS
625-632. COMPARED TO OTHER
COURSES THIS 3.67 .926 1365
COURSE WAS 20
 Factor Analysis
Descriptive Statistics

Mean Std. Deviation Analysis N

INSTRUC WELL
4.46 .729 1365
PREPARED

The descriptive statistics INSTRUC SCHOLARLY

GRASP
4.53 .700 1365

table is output because we INSTRUCTOR

CONFIDENCE
4.45 .732 1365

used the univariate option.

INSTRUCTOR FOCUS
4.28 .829 1365
LECTURES
INSTRUCTOR USES
CLEAR RELEVANT 4.17 .895 1365
EXAMPLES

Std. Deviation - These INSTRUCTOR SENSITIVE

TO STUDENTS 3.93 1.035 1365

are the standard INSTRUCTOR ALLOWS

ME TO ASK QUESTIONS
4.08 .964 1365

deviations of the variables INSTRUCTOR IS

ACCESSIBLE TO

used in the factor

3.78 .909 1365
STUDENTS OUTSIDE
CLASS

analysis.
INSTRUCTOR AWARE OF
STUDENTS 3.77 .984 1365
UNDERSTANDING
I AM SATISFIED WITH
STUDENT
3.61 1.116 1365
Are they meaningful for a
PERFORMANCE
EVALUATION

Likert scale!
COMPARED TO OTHER
INSTRUCTORS, THIS 3.81 .957 1365
INSTRUCTOR IS
COMPARED TO OTHER
COURSES THIS 3.67 .926 1365
COURSE WAS 21
 Factor Analysis
Descriptive Statistics

Mean Std. Deviation Analysis N

INSTRUC WELL
4.46 .729 1365
PREPARED

The descriptive statistics INSTRUC SCHOLARLY

GRASP
4.53 .700 1365

table is output because we INSTRUCTOR

CONFIDENCE
4.45 .732 1365

used the univariate option.

INSTRUCTOR FOCUS
4.28 .829 1365
LECTURES
INSTRUCTOR USES
CLEAR RELEVANT 4.17 .895 1365
EXAMPLES

Analysis N - This is the INSTRUCTOR SENSITIVE

TO STUDENTS 3.93 1.035 1365

number of cases used in INSTRUCTOR ALLOWS

ME TO ASK QUESTIONS
4.08 .964 1365

the factor analysis. INSTRUCTOR IS

ACCESSIBLE TO
3.78 .909 1365
STUDENTS OUTSIDE
CLASS

Note N is 1365.
INSTRUCTOR AWARE OF
STUDENTS 3.77 .984 1365
UNDERSTANDING
I AM SATISFIED WITH
STUDENT
3.61 1.116 1365
PERFORMANCE
EVALUATION
COMPARED TO OTHER
INSTRUCTORS, THIS 3.81 .957 1365
INSTRUCTOR IS
COMPARED TO OTHER
COURSES THIS 3.67 .926 1365
COURSE WAS 22
 Factor Analysis

The correlation matrix is included in the output

because we used the determinant option.

All we want to see in this table is that the

determinant is not 0.

If the determinant is 0, then there will be

computational problems with the factor analysis, and
SPSS may issue a warning message or be unable to
complete the factor analysis.

Correlation Matrixa

a. Determinant = .002
23
 Factor Analysis

Kaiser-Meyer-Olkin Measure of Sampling Adequacy

This measure varies between 0 and 1, and values closer
to 1 are better. A value of 0.6 is a suggested minimum.

KMO and Bartlett's Test

Kaiser-Meyer-Olkin Measure of Sampling
Adequacy. .934

Bartlett's Test of Approx. Chi-Square 8676.712

Sphericity df 66
Sig. .000

24
 Factor Analysis

Bartlett's Test of Sphericity (see the ANOVA

slides) - This tests the null hypothesis that the
correlation matrix is an identity matrix. An identity
matrix is matrix in which all of the diagonal elements
are 1 and all off diagonal elements are 0 (indicates a
lack of correlation). You want to reject this null
hypothesis.
KMO and Bartlett's Test
Kaiser-Meyer-Olkin Measure of Sampling
Adequacy. .934

Bartlett's Test of Approx. Chi-Square 8676.712

Sphericity df 66
Sig. .000
25
 Factor Analysis

Taken together, these tests provide a minimum

standard, which should be passed before a factor
analysis (or a principal components analysis) should be
conducted.

KMO and Bartlett's Test

Kaiser-Meyer-Olkin Measure of Sampling
Adequacy. .934

Bartlett's Test of Approx. Chi-Square 8676.712

Sphericity df 66
Sig. .000

26
 Factor Analysis
Communalities

Initial Extraction
INSTRUC WELL
.564 .676
PREPARED

Communalities - This INSTRUC SCHOLARLY

GRASP
.551 .619

is the proportion of INSTRUCTOR

CONFIDENCE
.538 .592

each variable's
INSTRUCTOR FOCUS
.447 .468
LECTURES

variance that can be

INSTRUCTOR USES
CLEAR RELEVANT .585 .623
EXAMPLES

explained by the INSTRUCTOR SENSITIVE

TO STUDENTS .572 .679

factors (e.g., the INSTRUCTOR ALLOWS

ME TO ASK QUESTIONS
.456 .576

underlying latent INSTRUCTOR IS

ACCESSIBLE TO

continua).
.326 .369
STUDENTS OUTSIDE
CLASS
INSTRUCTOR AWARE OF
STUDENTS .516 .549
UNDERSTANDING
I AM SATISFIED WITH
STUDENT
.397 .444
PERFORMANCE
EVALUATION
COMPARED TO OTHER
INSTRUCTORS, THIS .662 .791
INSTRUCTOR IS
COMPARED TO OTHER
COURSES THIS .526 .632
COURSE WAS
27
Extraction Method: Principal Axis Factoring.
 Factor Analysis
Communalities

Initial Extraction
INSTRUC WELL
.564 .676
PREPARED

Initial - With principal INSTRUC SCHOLARLY

GRASP
.551 .619

factor axis factoring, the INSTRUCTOR

CONFIDENCE
.538 .592

initial values on the diagonal

INSTRUCTOR FOCUS
.447 .468
LECTURES

of the correlation matrix

INSTRUCTOR USES
CLEAR RELEVANT .585 .623
EXAMPLES

are determined by the INSTRUCTOR SENSITIVE

TO STUDENTS .572 .679

squared multiple correlation INSTRUCTOR ALLOWS

ME TO ASK QUESTIONS
.456 .576

of the variable with the INSTRUCTOR IS

ACCESSIBLE TO

other variables. For

.326 .369
STUDENTS OUTSIDE
CLASS

example, if you regressed

INSTRUCTOR AWARE OF
STUDENTS .516 .549
UNDERSTANDING

items 14 through 24 on item I AM SATISFIED WITH

STUDENT

13, the squared multiple

.397 .444
PERFORMANCE
EVALUATION

correlation coefficient
COMPARED TO OTHER
INSTRUCTORS, THIS .662 .791
INSTRUCTOR IS

would be 0.564. COMPARED TO OTHER

COURSES THIS .526 .632
COURSE WAS
28
Extraction Method: Principal Axis Factoring.
 Factor Analysis
Communalities

Initial Extraction
INSTRUC WELL
.564 .676
PREPARED
INSTRUC SCHOLARLY

Extraction - The values in

.551 .619
GRASP
INSTRUCTOR

this column indicate the

.538 .592
CONFIDENCE
INSTRUCTOR FOCUS
.447 .468

proportion of each
LECTURES
INSTRUCTOR USES
CLEAR RELEVANT .585 .623
variable's variance that can EXAMPLES
INSTRUCTOR SENSITIVE

be explained by the retained TO STUDENTS .572 .679

factors. Variables with high

INSTRUCTOR ALLOWS
.456 .576
ME TO ASK QUESTIONS
INSTRUCTOR IS
values are well represented ACCESSIBLE TO
STUDENTS OUTSIDE
.326 .369

in the common factor space,

CLASS
INSTRUCTOR AWARE OF

while variables with low

STUDENTS .516 .549
UNDERSTANDING
I AM SATISFIED WITH

values are not well STUDENT

PERFORMANCE
.397 .444

represented. (In this

EVALUATION
COMPARED TO OTHER

example, we don't have any

INSTRUCTORS, THIS .662 .791
INSTRUCTOR IS
COMPARED TO OTHER

particularly low values.) COURSES THIS

COURSE WAS
.526 .632

29
Extraction Method: Principal Axis Factoring.
 Factor Analysis
Factor - The initial number of factors is the same as
the number of variables used in the factor analysis.
However, not all 12 factors will be retained. In this
example, only the first three factors will be retained
(as we requested).

Total Variance Explained

Initial Eigenvalues Extraction Sums of Squared Loadings Rotation Sums of Squared Loadings
Factor Total % of Variance Cumulative % Total % of Variance Cumulative % Total % of Variance Cumulative %
1 6.249 52.076 52.076 5.851 48.759 48.759 2.950 24.583 24.583
2 1.229 10.246 62.322 .806 6.719 55.478 2.655 22.127 46.710
3 .719 5.992 68.313 .360 3.000 58.478 1.412 11.769 58.478
4 .613 5.109 73.423
5 .561 4.676 78.099
6 .503 4.192 82.291
7 .471 3.927 86.218
8 .389 3.240 89.458
9 .368 3.066 92.524
10 .328 2.735 95.259
11 .317 2.645 97.904
12 .252 2.096 100.000
Extraction Method: Principal Axis Factoring.
30
 Factor Analysis
Initial Eigenvalues - Eigenvalues are the variances of the
factors. Because we conducted our factor analysis on the
correlation matrix, the variables are standardized, which
means that the each variable has a variance of 1, and the
total variance is equal to the number of variables used in
the analysis, in this case, 12.
Total Variance Explained

Initial Eigenvalues Extraction Sums of Squared Loadings Rotation Sums of Squared Loadings
Factor Total % of Variance Cumulative % Total % of Variance Cumulative % Total % of Variance Cumulative %
1 6.249 52.076 52.076 5.851 48.759 48.759 2.950 24.583 24.583
2 1.229 10.246 62.322 .806 6.719 55.478 2.655 22.127 46.710
3 .719 5.992 68.313 .360 3.000 58.478 1.412 11.769 58.478
4 .613 5.109 73.423
5 .561 4.676 78.099
6 .503 4.192 82.291
7 .471 3.927 86.218
8 .389 3.240 89.458
9 .368 3.066 92.524
10 .328 2.735 95.259
11 .317 2.645 97.904
12 .252 2.096 100.000
Extraction Method: Principal Axis Factoring.
31
 Factor Analysis
Initial Eigenvalues - Total - This column contains the
eigenvalues. The first factor will always account for the
most variance (and hence have the highest eigenvalue), and
the next factor will account for as much of the left over
variance as it can, and so on. Hence, each successive factor
will account for less and less variance.
Total Variance Explained

Initial Eigenvalues Extraction Sums of Squared Loadings Rotation Sums of Squared Loadings
Factor Total % of Variance Cumulative % Total % of Variance Cumulative % Total % of Variance Cumulative %
1 6.249 52.076 52.076 5.851 48.759 48.759 2.950 24.583 24.583
2 1.229 10.246 62.322 .806 6.719 55.478 2.655 22.127 46.710
3 .719 5.992 68.313 .360 3.000 58.478 1.412 11.769 58.478
4 .613 5.109 73.423
5 .561 4.676 78.099
6 .503 4.192 82.291
7 .471 3.927 86.218
8 .389 3.240 89.458
9 .368 3.066 92.524
10 .328 2.735 95.259
11 .317 2.645 97.904
12 .252 2.096 100.000
Extraction Method: Principal Axis Factoring.
32
 Factor Analysis
Initial Eigenvalues - % of Variance - This column contains
the percent of total variance accounted for by each factor
(6.249/12 = .52 or 52%).

Total Variance Explained

Initial Eigenvalues Extraction Sums of Squared Loadings Rotation Sums of Squared Loadings
Factor Total % of Variance Cumulative % Total % of Variance Cumulative % Total % of Variance Cumulative %
1 6.249 52.076 52.076 5.851 48.759 48.759 2.950 24.583 24.583
2 1.229 10.246 62.322 .806 6.719 55.478 2.655 22.127 46.710
3 .719 5.992 68.313 .360 3.000 58.478 1.412 11.769 58.478
4 .613 5.109 73.423
5 .561 4.676 78.099
6 .503 4.192 82.291
7 .471 3.927 86.218
8 .389 3.240 89.458
9 .368 3.066 92.524
10 .328 2.735 95.259
11 .317 2.645 97.904
12 .252 2.096 100.000
Extraction Method: Principal Axis Factoring.
33
 Factor Analysis
Initial Eigenvalues - Cumulative % - This column contains
the cumulative percentage of variance accounted for by
the current and all preceding factors. For example, the
third row shows a value of 68.313. This means that the
first three factors together account for 68.313% of the
total variance.
Total Variance Explained

Initial Eigenvalues Extraction Sums of Squared Loadings Rotation Sums of Squared Loadings
Factor Total % of Variance Cumulative % Total % of Variance Cumulative % Total % of Variance Cumulative %
1 6.249 52.076 52.076 5.851 48.759 48.759 2.950 24.583 24.583
2 1.229 10.246 62.322 .806 6.719 55.478 2.655 22.127 46.710
3 .719 5.992 68.313 .360 3.000 58.478 1.412 11.769 58.478
4 .613 5.109 73.423
5 .561 4.676 78.099
6 .503 4.192 82.291
7 .471 3.927 86.218
8 .389 3.240 89.458
9 .368 3.066 92.524
10 .328 2.735 95.259
11 .317 2.645 97.904
12 .252 2.096 100.000
Extraction Method: Principal Axis Factoring.
34
 Factor Analysis
Extraction Sums of Squared Loadings - The number of
rows in this panel of the table correspond to the number
of factors retained. The values are based on the common
variance (of the retained factors). The values in this panel
of the table will always be lower than the values in the left
panel of the table, because they are based on the common
variance, which is always smaller than the total variance.
Total Variance Explained

Initial Eigenvalues Extraction Sums of Squared Loadings Rotation Sums of Squared Loadings
Factor Total % of Variance Cumulative % Total % of Variance Cumulative % Total % of Variance Cumulative %
1 6.249 52.076 52.076 5.851 48.759 48.759 2.950 24.583 24.583
2 1.229 10.246 62.322 .806 6.719 55.478 2.655 22.127 46.710
3 .719 5.992 68.313 .360 3.000 58.478 1.412 11.769 58.478
4 .613 5.109 73.423
5 .561 4.676 78.099
6 .503 4.192 82.291
7 .471 3.927 86.218
8 .389 3.240 89.458
9 .368 3.066 92.524
10 .328 2.735 95.259
11 .317 2.645 97.904
12 .252 2.096 100.000
Extraction Method: Principal Axis Factoring. 35
 Factor Analysis
Rotation Sums of Squared Loadings - The values in this
panel of the table represent the distribution of the
variance after the varimax rotation. Varimax rotation
tries to maximize the variance of each of the factors, so
the total amount of variance accounted for is
redistributed over the three extracted factors.
Note the more even split.
Total Variance Explained

Initial Eigenvalues Extraction Sums of Squared Loadings Rotation Sums of Squared Loadings
Factor Total % of Variance Cumulative % Total % of Variance Cumulative % Total % of Variance Cumulative %
1 6.249 52.076 52.076 5.851 48.759 48.759 2.950 24.583 24.583
2 1.229 10.246 62.322 .806 6.719 55.478 2.655 22.127 46.710
3 .719 5.992 68.313 .360 3.000 58.478 1.412 11.769 58.478
4 .613 5.109 73.423
5 .561 4.676 78.099
6 .503 4.192 82.291
7 .471 3.927 86.218
8 .389 3.240 89.458
9 .368 3.066 92.524
10 .328 2.735 95.259
11 .317 2.645 97.904
12 .252 2.096 100.000 36
Extraction Method: Principal Axis Factoring.
 Factor Analysis
The scree plot graphs the eigenvalue (variance) against the
factor number. You can see these values in the first two
columns of the variance explained table.

37
 Factor Analysis
From the third factor on, you can see that the line is almost
flat, meaning the each successive factor is accounting for
smaller and smaller amounts of the total variance.

You need to locate this,

so called, elbow!

In other words, when

the drop ceases and the
curve makes an elbow
toward a less steep
decline.

38
 Factor Analysis
Factor Matrixa

Factor
1 2 3
INSTRUC WELL
.713 -.398
PREPARED
INSTRUC SCHOLARLY
.703 -.339

Factor Matrix - This table

GRASP
INSTRUCTOR
.721
CONFIDENCE
contains the unrotated INSTRUCTOR FOCUS
LECTURES
.648

factor loadings, which are INSTRUCTOR USES

CLEAR RELEVANT .783

the correlations between the

EXAMPLES
INSTRUCTOR SENSITIVE

variable and the factor.

TO STUDENTS .740 .345

INSTRUCTOR ALLOWS

Because these are

.616 .415
ME TO ASK QUESTIONS
INSTRUCTOR IS

correlations, possible values

ACCESSIBLE TO
.550
STUDENTS OUTSIDE
CLASS

range from -1 to +1. It is INSTRUCTOR AWARE OF

STUDENTS .732

usual to not report any UNDERSTANDING

I AM SATISFIED WITH

correlations that are less

STUDENT
.613
PERFORMANCE
EVALUATION

than |.3|. As shown. COMPARED TO OTHER

INSTRUCTORS, THIS .819 -.345
INSTRUCTOR IS
COMPARED TO OTHER
COURSES THIS .695 -.386
COURSE WAS
Extraction Method: Principal Axis Factoring.
a. 3 factors extracted. 7 iterations required.
39
 Factor Matrixa

Factor Analysis
Factor
1 2 3
INSTRUC WELL
.713 -.398
PREPARED
INSTRUC SCHOLARLY
.703 -.339
GRASP

Factor - The columns under INSTRUCTOR

CONFIDENCE
.721

this heading are the

INSTRUCTOR FOCUS
.648
LECTURES
INSTRUCTOR USES
unrotated factors that have CLEAR RELEVANT
EXAMPLES
.783

been extracted. As you can INSTRUCTOR SENSITIVE

TO STUDENTS .740 .345

see by the footnote provided INSTRUCTOR ALLOWS

ME TO ASK QUESTIONS
.616 .415

by SPSS, three factors were INSTRUCTOR IS

ACCESSIBLE TO

extracted (the three

.550
STUDENTS OUTSIDE
CLASS

factors that we requested).

INSTRUCTOR AWARE OF
STUDENTS .732
UNDERSTANDING
I AM SATISFIED WITH
STUDENT
.613
PERFORMANCE
EVALUATION
COMPARED TO OTHER
INSTRUCTORS, THIS .819 -.345
INSTRUCTOR IS
COMPARED TO OTHER
COURSES THIS .695 -.386
COURSE WAS
Extraction Method: Principal Axis Factoring.
a. 3 factors extracted. 7 iterations required.

40
 Factor Analysis
The plot shows the
items (variables) in
the rotated factor
space.
While this picture
may not be
particularly
helpful, when you
get this graph in
the SPSS output,
you can
interactively
rotate it.
41
 Factor Analysis

Rotation may help

you to see how the
items (variables)
are organized in
the common factor
space.

42
 Factor Analysis
Another run of the factor analysis program is conducted
with a promax rotation. It is included to show how
different the rotated solutions can be, and to better
illustrate what is meant by simple structure.
As you will see with an oblique rotation, such as a promax
rotation, the factors are permitted to be correlated with
one another. With an orthogonal rotation, such as the
varimax shown above, the factors are not permitted to
be correlated (they are orthogonal to one another).
Oblique rotations, such as promax, produce both factor
pattern and factor structure matrices. For orthogonal
rotations, such as varimax and equimax, the factor
structure and the factor pattern matrices are the same.
43
 Factor Analysis
Use the buttons at the bottom of the screen to set the
alternate Rotation, employ the Continue button to return to
the main Factor Analysis screen.

44
 Factor Analysis
The resulting plot with a “simple” structure is shown.

45
 Factor Analysis
For a recent review see Factor Analysis at 100. Historical
Developments and Future Directions. By Robert Cudeck,
and Robert C. MacCallum (Eds.). Lawrence Earlbaum
Associates, Mahwah, NJ, 2007, xiii+381 pp., ISBN:978-0-
8058-5347-6 (hardcover), and, ISBN 978-0-8058-6212-6
(paperback).

46
 Factor Analysis
Summary

Factor Analysis like principal components is used to

summarise the data covariance structure in a smaller
number of dimensions. The emphasis is the
identification of underlying “factors” that might explain
the dimensions associated with large data variability.

A Beginner’s Guide to Factor Analysis: Focusing on

Exploratory Factor Analysis
An Gie Yong and Sean Pearce
Tutorials in Quantitative Methods for Psychology 2013
9(2) 79-94
47
 Factor Analysis
Principal Components Analysis and Factor Analysis share the search for
a common structure characterized by few common components, usually
known as “scores” that determine the observed variables contained in
matrix X.

However, the two methods differ on the characterization of the

scores as well as on the technique adopted for selecting their true
number.

In Principal Components Analysis the scores are the orthogonalised

principal components obtained through rotation, while in Factor
Analysis the scores are latent variables determined by unobserved
factors and loadings which involve idiosyncratic error terms.

The dimension reduction of matrix X implemented by each method

produces a set of fewer homogenous variables – the true scores –
which contain most of the model’s information.
48
 Factor Analysis
Summary

Principal Components is used to help understand the

covariance structure in the original variables and/or to
create a smaller number of variables using this
structure.

For Principal Components, see next weeks lecture.

49
Factor Analysis

Overview of the steps in a

factor analysis. From: Rietveld
& Van Hout (1993: 291).

Rietveld, T. & Van Hout, R. (1993).

Statistical Techniques for the Study of
Language and
Language Behaviour. Berlin – New York:
Mouton de Gruyter.

50
 Factor Analysis
After having obtained the correlation matrix, it is time to decide which
type of analysis to use: factor analysis or principal component analysis. The
main difference between these types of analysis lies in the way the
communalities are used. In principal component analysis it is assumed that
the communalities are initially 1. In other words, principal component
analysis assumes that the total variance of the variables can be accounted
for by means of its components (or factors), and hence that there is no
error variance. On the other hand, factor analysis does assume error
variance. This is reflected in the fact that in factor analysis the
communalities have to estimated, which makes factor analysis more
complicated than principal component analysis, but also more conservative.

For further details see "Factor Analysis" Kootstra 2004

51
 SPSS Tips
Now you should go and try for yourself.

Each week our cluster (5.05) is booked for 2 hours

after this session. This will enable you to come and go
as you please.

Obviously other timetabled sessions for this module

take precedence.

52