Factor Analysis

Factor Analysis is interdependence

technique. In interdependence techniques
the variables are not classified as
independent or dependent variable, but
their interrelationship is studied.
Factor analysis is general name for
Principle Component Analysis
Common Factor Analysis.
 An Example

Imagine a restaurant chain wants to understand the factors

affecting customer perceptions of its service quality. After
collecting survey data, factor analysis might reveal the following
factors:
Food Quality: Variables such as "taste of food," "presentation
of food," and "portion size."
Staff Interaction: Variables like "politeness of servers,"
"knowledge of the menu," and "speed of service."
Atmosphere: Variables such as "cleanliness," "comfort," and
"overall ambiance."
Value for Money: Variables like "price relative to quality,"
"portions worth the price," and "overall satisfaction with value.“

The restaurant can now use this information to improve specific

areas. If "Staff Interaction" is identified as a critical factor for
customer satisfaction, the restaurant might focus on staff training
to improve customer interactions.
Imagine a restaurant chain wants to understand the factors
affecting customer perceptions of its service quality. After
collecting survey data, factor analysis might reveal the
following factors:
Food Quality: Variables such as "taste of food,"
"presentation of food," and "portion size."
Staff Interaction: Variables like "politeness of servers,"
"knowledge of the menu," and "speed of service."
Atmosphere: Variables such as "cleanliness," "comfort,"
and "overall ambiance."
Value for Money: Variables like "price relative to quality,"
"portions worth the price," and "overall satisfaction with
value."
The restaurant can now use this information to improve
specific areas. If "Staff Interaction" is identified as a critical
factor for customer satisfaction, the restaurant might focus
on staff training to improve customer interactions.
The factor analysis is done principally for two
reasons
To identify a new, smaller set of uncorrelated
variables to be used in subsequent multiple
regression analysis. In this situation the Principle
Component Analysis is performed on the data. PCA
considers the total variance in the data while finding
principle components from a given set of variables
To identify underlying dimensions / factors that are
unobservable but explain correlations among a set
of variables. In this situation the Common Factor
Analysis is performed on the data. FA considers only
the common variance while finding common factors
from a given set of variables. The common factor
analysis is also termed as Principle Axis
Factoring.
The essential purpose of factor analysis is to
describe, if possible, the covariance
relationships among many variables in terms of
few underlying, but unobservable, random
quantities called factors. Basically, the factor
model is motivated by the following argument.
Suppose variables can be grouped by their
correlations. That is, all variables, within a
particular group are highly correlated among
themselves but have relatively small
correlations with variables in a different group.
In that case, it is conceivable that each group of
variables represents a single underlying
construct, or factor, that is responsible for the
correlations.
 Principal components factor analysis

Obtaining a factor solution through principal

components analysis is an iterative process
that usually requires repeating the SPSS factor
analysis procedure a number of times to reach
a satisfactory solution.

We begin by identifying a group of variables

whose variance we believe can be represented
more parsimoniously by a smaller set of factors,
or components. The end result of the principal
components analysis will tell us which variables
can be represented by which components, and
which variables should be retained as individual
variables because the factor solution does not
adequately represent their information.
 Principal components factor analysis

Technique for forming set of new variables that

are linear combinations of the original set of
variables, and are uncorrelated. The new
variables are called Principal
Components.
These variables are fewer in number as
compared to the original variables, but they
extract most of the informant provided by the
original variables.
 Applications

One could identify several financial parameters

and ratios exceeding ten for determining the
financial health of a company. Obviously, it
would be extremely taxing to interpret all such
pieces of information for assessing the financial
health of a company. However, the task could
be much simpler if these parameters and ratios
could be reduced to a few indices, say two or
three, which are linear combinations of the
original parameters and ratios.
 Applications

A multiple regression model may be derived to

forecast a parameter like sales, profit, price,
etc. However, the variables under consideration
could be correlated among themselves
indicating multicollinearity in the data.
This could lead to misleading interpretation of
regression coefficients as also increase in the
standard errors of the estimates of parameters.
It would be very useful, if the new uncorrelated
variables could be formed which are linear
combinations of the original variables. These
new variables could then be used for
developing the regression model, for
appropriate interpretation and better forecast.
 Common Factor Analysis (CFA)

It is a statistical approach that is used to

analyse inter- relationships among a large
number of variables(indicators) and to explain
these variables(indicators) in terms of a few
unobservable constructs (factors). In fact, these
factors impact the variables, and are reflective
indicators of the factors. The statistical
approach involves finding a way of condensing
the information contained in a number of
original variables into a smaller set of
constructs (factors) - mostly one or two- with a
minimum loss of information.
 Common Factor Analysis (CFA)

Identifies the smallest number of common

factors that best explain or account for most of
the correlation among the indicators. For
example, intelligence quotient of a student
might explain most of the marks obtained in
Mathematics, Physics, Statistics, etc. As yet
another example, when two variables x and y
are highly correlated, only one of them could be
used to represent the entire data
 Common Factor Analysis (CFA)

CFA Helps in assessing

the image of a company/enterprise
attitudes of sales personnel and customers
preference or priority for the
characteristics of
- product like television, mobile phone, etc.
- a service like TV program, air travel etc.
 Key Terms

Exploratory Factor Analysis (EFA)

This technique is used when a researcher has
no prior knowledge about the number of factors
the variables will be indicating. In such cases
computer based techniques are used to indicate
appropriate number of factors.
Confirmatory Factor Analysis (CFA)
This technique is used when the researcher has
the prior knowledge(on the basis of some pre-
established theory) about the number of factors
the variables will be indicating. This makes it
easy as there is no decision to be taken about the
number of factors and the number is indicated in
the computer based tool while conducting
analysis.
 Key Terms

Correlation Matrix
This is the matrix showing simple correlations
between all possible pairs of variables. The
diagonal element of this matrix is 1 and this is
a symmetric matrix, since correlation between
two variables x and y is same as between y
and x.
Communality
The amount of variance, an original variable
shares with all other variables included in the
analysis. A relatively high communality
indicates that a variable has much in common
with the other variables taken as a group.
 Key Terms

Eigenvalue
Eigenvalue for each factor is the total variance
explained by each factor.
Factor
A linear combination of the original variables.
Factor also represents the underlying
dimensions( constructs) that summarise or
account for the original set of observed
variables
 Key Terms

Factor Loadings
The factor loadings, or component loadings in
PCA, are the correlation coefficients between
the variables (given in output as rows ) and
factors (given in output columns) These
loadings are analogous to Pearson’s correlation
coefficient r, the squared factor loading is
defined as the percent of variance in the
respective variable explained by the factor.
Factor Matrix
This contains factor loadings on all the
variables on all the factors extracted
 Key Terms

Factor Plot or Rotated Factor Space

This is a plot where the factors are on different axis and
the variables are drawn on these axes. This plot can be
interpreted only if the number of factors are 3 or less
Factor Scores
Each individual observation has a score, or value,
associated with each of the original variables. Factor
analysis procedures derive factor scores that represent
each observation’s calculated values, or score, on each of
the factors. The factor score will represent an individual’s
combined response to the several variables representing
the factor.
The component scores may be used in subsequent
analysis in PCA. When the factors are to represent a new
set of variables that they may predict or be dependent on
some phenomenon, the new input may be factor scores.
 Key Terms

Goodness of a Factor
How well can a factor account for the
correlations among the indicators ? One could
examine the correlations among the indicators
after the effect of the factor is removed. For a
good factor solution, the resulting partial
correlations should be near zero, because once
the effect of the common factor is removed ,
there is nothing to link the indicators.
Bartlett’s Test of specificity This is the test
statistics used to test the null hypothesis that
there is no correlation between the variables.
 Key Terms

Kier Meyer Olkin (KMO) Measure of Sampling

Adequacy
This is an index used to test appropriateness of
the factor analysis. High values of this index,
generally, more than 0.5 , may indicate that
the factor analysis is an appropriate measure,
where as the lower values (less than 0.5)
indicate that factor analysis may not be
appropriate.
 Key Terms

Scree Plot A plot of Eigen values against the

factors in the order of their extraction.
Trace
The sum of squares of the values on the
diagonal of the correlation matrix used in the
factor analysis. It represents the total amount
of variance on which the factor solution is
based.
 PCA

Suppose, in a particular situation, k variables are

required to explain the entire system under study.
Through PCA, the original variables are
transformed into a new set of variables called
principal components, numbering much less
than k. These are formed in such a manner that
they extract almost the entire information
provided by the original variables. Thus, the
original data of n observations on each of the k
variables is reduced to a new data of n
observations on each of the principal components.
That is how; PCA is referred to as one of the data
reduction and interpretation techniques. Some
indicative applications are given below.
 PCA

There are a number of financial

parameters/ratios for predicting health of a
company. It would be useful if only a couple of
indicators could be formed as linear
combination of the original parameters/ratios in
such a way that the few indicators extract most
of the information contained in the data on
original variables.
 PCA

In regression model, if independent variables

are correlated implying there is
multicollinearity, then new variables could be
formed as linear combinations of original
variables which themselves are uncorrelated.
The regression equation can then be derived
with these new uncorrelated independent
variables, and used for interpreting the
regression coefficients as also for predicting the
dependant variable with the help of these new
independent variables. This is highly useful
in marketing and financial applications
involving forecasting, sales, profit, price,
etc. with the help of regression equations.
 PCA

Analysis of principal components often reveals

relationships that were not previously
suspected and thereby allows interpretations
that would not be ordinarily understood. A good
example of this is provided by stock market
indices.
PCA is a means to an end and not the end
in itself. PCA can be used for inputting
principal components as variables for
further analysing the data using other
techniques such as cluster analysis,
regression and discriminant analysis.
 Common Factor Analysis

Data reduction and summarization technique. It

is a statistical approach that is used to analyse
inter relationships among a large number of
variables (e.g., test scores, test items,
questionnaire responses) and then explaining
these variables in terms of their common
underlying dimensions (factors). For example, a
hypothetical survey questionnaire may consist of
20 or even more questions, but since not all of
the questions are identical, they do not all
measure the basic underlying dimensions to the
same extent. By using factor analysis, we can
identify the separate dimensions being measured
by the survey and determine a factor loading for
each variable (test item) on each factor.
 Common Factor Analysis

Common Factor analysis is an interdependence

technique in which all variables are
simultaneously considered. In a sense, each of
the observed (original) variables is considered
as a dependant variable that is a function of
some underlying, latent, and
hypothetical/unobserved set of factors
(dimensions). One could also consider the
original variables as reflective indicators of the
factors. For example, marks( variable) in an
examination reflect the intelligence( factor).
 Common Factor Analysis
The statistical approach followed in factor analysis involves
finding a way of condensing the information contained in a
number of original variables into a smaller set of dimensions
(factors) with a minimum loss of information.
Common Factor Analysis was originally developed to
explain students’ performance in various subjects and to
understand the link between grades and intelligence. Thus,
the marks obtained in an examination reflect the student’s
intelligence quotient. A salesman’s performance in term of
sales might reflect his attitude towards the job, and efforts
made by him.
One of the studies relating to marks obtained by students in
various subjects, led to the conclusion that students’ marks
are a function of two common factors viz. Quantitative and
Verbal abilities. The quantitative ability factor explains marks
in subjects like Mathematics, Physics and Chemistry, and
verbal ability explains marks in subjects like Languages and
History.
 Common Factor Analysis

In general, the factor analysis performs

the following functions:
Identifies the smallest number of common
factors that best explain or account for the
correlation among the indicators
Identifies a set of dimensions that are latent
( not easily observed) in a large number of
variables
Devises a method of combining or condensing a
large number of consumers with varying
preferences into distinctly different number of
groups.
 Strategy for solving problems - 1

A principal component factor analysis requires:

The variables included must be metric level or
dichotomous (dummy-coded) nominal level
The sample size must be greater than 50 (preferably
100)
The ratio of cases to variables must be 5 to 1 or larger
The correlation matrix for the variables must contain 2
or more correlations of 0.30 or greater
Variables with measures of sampling adequacy less than
0.50 must be removed
The overall measure of sampling adequacy is 0.50 or
higher
The Bartlett test of sphericity is statistically significant.

The first phase of a principal component analysis

is devoted to verifying that we meet these
requirements. If we do not meet these
requirements, factor analysis is not appropriate.
 Strategy for solving problems - 2

The second phase of a principal component

factor analysis focuses on deriving a factor
model, or pattern of relationships between
variables and components, that satisfies the
following requirements:
The derived components explain 50% or more of the
variance in each of the variables, i.e. have a
communality greater than 0.50
None of the variables have loadings, or correlations,
of 0.40 or higher for more than one component, i.e.
do not have complex structure
None of the components has only one variable in it

To meet these requirements, we remove

problematic variables from the analysis and
repeat the principal component analysis.
 Strategy for solving problems - 3
If, at the conclusion of this process, we have
components that have more than one variable
loading on them, have components that explain at
least 50% of the variance in the included variables,
and have components that collectively explain
more than 60% of the variance in the set of
variables, we can substitute the components for
the variables in further analyses.

Variables that were removed in the analysis should

be included individually in further analyses.

Substitution of components for individual variables

is accomplished by using only the highest loading
variable, or by combining the variables loading on
each component to create a new variable.
 Notes - 1

When evaluating measures of sampling

adequacy, communalities, or factor loadings,
we ignore the sign of the numeric value and
base our decision on the size or magnitude of
the value.

The sign of the number indicates the direction

of the relationship.

A loading of -0.732 is just as strong as a loading

of 0.732. The minus sign indicates an inverse
or negative relationship; the absence of a sign
is meant to imply a plus sign indicating a direct
or positive relationship.
 Notes - 2

If there are two or more components in the

component matrix, the pattern of loadings is
based on the SPSS Rotated Component Matrix.
If there is only one component in the solution,
the Rotated Component Matrix is not computed,
and the pattern of loadings is based on the
Component Matrix.

It is possible that the analysis will break down

and we will have too few variables in the
analysis to support the use of principal
component analysis.
Sample size requirement:minimum
number of cases
Descriptive Statistics

Mean Std. Deviation Analysis N

ENVIRONMENTAL
THREATS 3.31 .988 67
EXAGGERATED
HOW DANGEROUS
MODIFYING GENES IN 3.09 .949 67
CROPS
AMERICAN DOING
ENOUGH TO PROTECT 2.40
The number of valid cases for this .605 67
ENVIRONMENT
set of variables is 67.
While principal
INTL AGREEMENTS FOR component analysis
can be conducted on 1.97
ENVIRONMENT a sample that.674 67
has fewer than 100 cases, but
PROBLEMS
more than 50 cases, we should be
POOR COUNTRIES LESS
cautious about its interpretation.
THAN RICH FOR 3.73 .898 67
ENVIRONMENT
ECONOMIC PROGRESS
DEPENDENT ON 2.69 .839 67
ENVIRONMENT
LIKELIHOOD OF
NUCLEAR MELTDOWN 2.49 .894 67
IN 5 YEARS
RESPONDENT'S
49.757 18.9651 67
SOCIOECONOMIC INDEX
Sample size requirement:ratio of cases to
variables
Descriptive Statistics

Mean Std. Deviation Analysis N

ENVIRONMENTAL
THREATS 3.31 .988 67
EXAGGERATED
HOW DANGEROUS
MODIFYING GENES IN 3.09 .949 67
CROPS
AMERICAN DOING
ENOUGH TO PROTECT 2.40 to
The ratio of cases .605 67
ENVIRONMENT variables in a principal
component
INTL AGREEMENTS FOR analysis
ENVIRONMENT should be at least
1.97 5 to 1. .674 67
PROBLEMS
With 67 and 8 variables,
the ratio of cases to
POOR COUNTRIES LESS is 8.4 to 1,
variables
THAN RICH FORwhich exceeds3.73the .898 67
ENVIRONMENT requirement for the ratio
of cases to variables.
ECONOMIC PROGRESS
DEPENDENT ON 2.69 .839 67
ENVIRONMENT
LIKELIHOOD OF
NUCLEAR MELTDOWN 2.49 .894 67
IN 5 YEARS
RESPONDENT'S
49.757 18.9651 67
SOCIOECONOMIC INDEX
 Appropriateness of factor analysis:
Presence of substantial correlations

Correlation Matrix

AMERICAN INTL POOR ECONOMIC

ENVIRON HOW DOING AGREEMEN COUNTRIES Principal
PROGRESS components
MENTAL DANGEROUS ENOUGH TO TS FOR LESS THANanalysis
DEPENDENrequires that there
LIKELIHOOD RESPONDEN
THREATS MODIFYING PROTECT ENVIRONME RICH FORbe some
T ON correlations
OF NUCLEAR greaterT'S
EXAGGER GENES IN ENVIRONME NT ENVIRONMEthan 0.30 between
ENVIRONME MELTDOWNtheSOCIOECON
ATED CROPS NT PROBLEMS NT variablesNT IN 5 YEARS
included OMIC INDEX
in the
Correlation ENVIRONMENTAL
analysis.
THREATS 1.000 -.240 .394 -.305 .301
EXAGGERATED
For this-.117 -.126
set of variables, .069
there are 10 correlations in
HOW DANGEROUS
MODIFYING GENES IN
the matrix greater than
-.240 1.000 -.301 .146 -.149 .340 .394 .208
CROPS 0.30, satisfying this
AMERICAN DOING
requirement. The
ENOUGH TO PROTECT .394 -.301 1.000 -.305
correlations
.258 -.136
greater
-.401
than .054
ENVIRONMENT 0.30 are highlighted in
INTL AGREEMENTS FOR
yellow.
ENVIRONMENT -.305 .146 -.305 1.000 -.289 .117 .151 .094
PROBLEMS
POOR COUNTRIES LESS
THAN RICH FOR .301 -.149 .258 -.289 1.000 -.194 -.003 .114
ENVIRONMENT
ECONOMIC PROGRESS
DEPENDENT ON -.117 .340 -.136 .117 -.194 1.000 .310 -.018
ENVIRONMENT
LIKELIHOOD OF
NUCLEAR MELTDOWN -.126 .394 -.401 .151 -.003 .310 1.000 .341
IN 5 YEARS
RESPONDENT'S
.069 .208 .054 .094 .114 -.018 .341 1.000
SOCIOECONOMIC INDEX
Appropriateness of factor analysis:Sampling
adequacy of individual variables

Principal component analysis requires

that the Kaiser-Meyer-Olkin Measure of
Sampling Adequacy be greater than
0.50 for each individual variable as well
as the set of variables.
The Measure of Sampling Adequacy
(MSA) is described at marvelous if it is
0.90 or greater, meritorious if it is in the
0.80's, middling if in the 0.70's,
mediocre if in the in the 0.60's ,
miserable if in the 0.50's, and
unacceptable if below 0.50.

There are two anti-image

matrices: the anti-image
covariance matrix and the
anti-image correlation
matrix. We are interested
in the anti-image
correlation matrix.
Appropriateness of factor analysis:Sampling
adequacy of individual variables

SPSS locates the Measures

of Sampling Adequacy are
on the diagonal of the anti-
image correlation matrix,
highlighted in yellow.

On iteration 1, the MSA for

the variable "respondent's
socioeconomic index" [sei]
was 0.410 which was less
than 0.50, so it was
removed from the analysis.
Excluding a variable from the factor
analysis

To remove the variable

"respondent's
socioeconomic index" [sei]
from the analysis, click on
the Dialog Recall tool
button to access the drop
down menu.
Repeating the factor analysis

In the drop down menu,

select Factor Analysis to
reopen the factor analysis
dialog box.
Removing the variable from the list of
variables

First, highlight
the sei
variable.

Second, click on the

left arrow button to
remove the variable
from the Variables list
box.
Replicating the factor analysis

The dialog recall command

opens the dialog box with all of
the settings that we had
selected the last time we used
factor analysis.
To replicate the analysis without
the variable that we just
removed, click on the OK button.
Appropriateness of factor analysis:Sample
adequacy for revised factor analysis

In the factor analysis with the sei

variable removed, we see that
the measures of sampling
adequacy for the remaining
variables are all greater than
0.50.

On iteration 2, the MSA for all of

the individual variables still
included in the analysis was
greater than 0.5, supporting
their retention in the analysis.
 Appropriateness of factor analysis:
Sample adequacy for set of variables

KMO and Bartlett's Test

Kaiser-Meyer-Olkin Measure of Sampling
Adequacy. .734

Bartlett's Test of Approx. Chi-Square 69.350

Sphericity df 21
Sig. .000 In addition, the overall
MSA for the set of
variables included in the
analysis was 0.734,
which exceeds the
minimum requirement of
0.50 for overall MSA.

The seven variables

remaining in the analysis
satisfy the criteria for
appropriateness of factor
analysis.
Appropriateness of factor analysis:
Bartlett test of sphericity

KMO and Bartlett's Test

Kaiser-Meyer-Olkin Measure of Sampling
Adequacy. .642

Bartlett's Test of Approx. Chi-Square 84.006

Sphericity df 28
Sig. .000

Principal component analysis

requires that the probability
associated with Bartlett's Test of
Sphericity be less than the level of
significance.
The probability associated with the
Bartlett test is <0.001, which
satisfies this requirement.
The next step is to determine the
number of factors that should be
included in the factor solution.
 Number of factors to extract:Latent root
criterion

Total Variance Explained

Initial Eigenvalues Extraction Sums of Squared Loadings Rotation Sums of Squared Loadings
Component Total % of Variance Cumulative % Total % of Variance Cumulative % Total % of Variance Cumulative %
1 2.461 35.164 35.164 2.461 35.164 35.164 1.849 26.408 26.408
2 1.229 17.557 52.721 1.229 17.557 52.721 1.842 26.313 52.721
3 .889 12.695 65.415
4 .722 10.313 75.728
5 .621 8.878 84.606
6 .572 8.174 92.780
7 .505 7.220 100.000
Extraction Method: Principal Component Analysis.

Using the output from iteration 2,

there were 2 eigenvalues greater
than 1.0.
The latent root criterion for
number of factors to derive would
indicate that there were 2
components to be extracted for
these variables.
Number of factors to extract: Percentage
of variance criterion

Total Variance Explained

Initial Eigenvalues Extraction Sums of Squared Loadings Rotation Sums of Squared Loadings
Component Total % of Variance Cumulative % Total % of Variance Cumulative % Total % of Variance Cumulative %
1 2.461 35.164 35.164 2.461 35.164 35.164 1.849 26.408 26.408
2 1.229 17.557 52.721 1.229 17.557 52.721 1.842 26.313 52.721
3 .889 12.695 65.415
4 .722 10.313 75.728
5 .621 8.878 84.606
6 .572 8.174 92.780
7 .505 7.220 100.000
Extraction Method: Principal Component Analysis. In contrast, the cumulative
proportion of variance criteria
would require 3 components to
satisfy the criterion of explaining
60% or more of the total
variance.
A 3 components solution would
explain 65.415% of the total
Since the SPSS default is to extract variance.
the number of components
indicated by the latent root
criterion, our initial factor solution
was based on the extraction of 2
components.
 Evaluating communalities

Communalities

Initial Extraction
ENVIRONMENTAL
Communalities represent the THREATS 1.000 .526
proportion of the variance in EXAGGERATED
the original variables that is HOW DANGEROUS
accounted for by the factor MODIFYING GENES IN 1.000 .582
solution. CROPS
The factor solution should
explain at least half of each AMERICAN DOING
original variable's variance, ENOUGH TO PROTECT 1.000 .521
so the communality value for ENVIRONMENT
each variable should be 0.50 INTL AGREEMENTS FOR
or higher. ENVIRONMENT 1.000 .491
PROBLEMS
POOR COUNTRIES LESS
THAN RICH FOR 1.000 .494
ENVIRONMENT
ECONOMIC PROGRESS
DEPENDENT ON 1.000 .437
ENVIRONMENT
LIKELIHOOD OF
NUCLEAR MELTDOWN 1.000 .640
IN 5 YEARS
Extraction Method: Principal Component Analysis.
Communality requiring variable removal
Communalities

Initial Extraction
ENVIRONMENTAL
THREATS 1.000 .526
EXAGGERATED On iteration 2, the
HOW DANGEROUS communality for the
MODIFYING GENES IN 1.000 .582 variable "economic
CROPS progress in America will
slow down without more
AMERICAN DOING concern for
ENOUGH TO PROTECT 1.000 .521 environment" [econgrn]
ENVIRONMENT was 0.437 which was
INTL AGREEMENTS FOR less than 0.50.
ENVIRONMENT
The variable was
1.000 .491 removed and the
PROBLEMS principal component
POOR COUNTRIES LESS analysis was computed
THAN RICH FOR 1.000 .494 again.
ENVIRONMENT
ECONOMIC PROGRESS
DEPENDENT ON 1.000 .437
ENVIRONMENT
LIKELIHOOD OF
NUCLEAR MELTDOWN 1.000 .640
IN 5 YEARS
Extraction Method: Principal Component Analysis.
In this iteration, there are actually
three variables that have
communalities less than 0.50. The
variable with the smallest communality
is selected for removal.
Repeating the factor analysis

In the drop down menu,

select Factor Analysis to
reopen the factor analysis
dialog box.
Removing the variable from the list of
variables

First, highlight
the econgrn
variable.

Second, click on the

left arrow button to
remove the variable
from the Variables list
box.
Replicating the factor analysis

The dialog recall command

opens the dialog box with all of
the settings that we had
selected the last time we used
factor analysis.
To replicate the analysis without
the variable that we just
removed, click on the OK button.
Communality requiring variable removal

Communalities

Initial Extraction
ENVIRONMENTAL On iteration 3, the
THREATS 1.000 .517 communality for the
EXAGGERATED variable "should be
international
HOW DANGEROUS agreements for
MODIFYING GENES IN 1.000 .573 environment problems"
CROPS [grnintl] was 0.486
AMERICAN DOING which was less than
ENOUGH TO PROTECT 1.000 .576
0.50.
The variable was
ENVIRONMENT
removed and the
INTL AGREEMENTS principal component
FOR ENVIRONMENT 1.000 .486 analysis was computed
PROBLEMS again.
POOR COUNTRIES
LESS THAN RICH FOR 1.000 .573
ENVIRONMENT
LIKELIHOOD OF
NUCLEAR MELTDOWN 1.000 .716
IN 5 YEARS
Extraction Method: Principal Component Analysis.
Repeating the factor analysis

In the drop down menu,

select Factor Analysis to
reopen the factor analysis
dialog box.
Removing the variable from the list of
variables

First, highlight
the grnintl
variable.

Second, click on the

left arrow button to
remove the variable
from the Variables list
box.
Replicating the factor analysis

The dialog recall command

opens the dialog box with all of
the settings that we had
selected the last time we used
factor analysis.
To replicate the analysis without
the variable that we just
removed, click on the OK button.
 Communality satisfactory for all
variables
Communalities

Initial Extraction Once any variables with

ENVIRONMENTAL communalities less than
THREATS 1.000 .591 0.50 have been
EXAGGERATED removed from the
analysis, the pattern of
HOW DANGEROUS factor loadings should
MODIFYING GENES IN 1.000 .568 be examined to identify
CROPS variables that have
AMERICAN DOING complex structure.
ENOUGH TO PROTECT 1.000 .582
ENVIRONMENT
POOR COUNTRIES
LESS THAN RICH FOR 1.000 .679
ENVIRONMENT
LIKELIHOOD OF
Complex structure occurs when
one variable has high loadings or
NUCLEAR MELTDOWN 1.000 .725 correlations (0.40 or greater) on
IN 5 YEARS more than one component. If a
Extraction Method: Principal Component Analysis. variable has complex structure, it
should be removed from the
analysis.
Variables are only checked for
complex structure if there is more
than one component in the
solution. Variables that load on
only one component are
described as having simple
structure.
 Identifying complex structure
If only one component has been
extracted, each variable can
only load on that one factor, so
complex structure is not an
issue.
On iteration 4, the
variable "America doing
Rotated Component Matrixa enough to protect
environment" [amprogrn]
Component was found to have
1 2 complex structure.
ENVIRONMENTAL Specifically, the variable
THREATS -.265 .722 had a loading of -0.581 on
EXAGGERATED
component 1 and a
loading of 0.495 on
HOW DANGEROUS component 2.
MODIFYING GENES IN .732 -.182 The variable should be
CROPS removed and the principal
AMERICAN DOING component analysis
should be repeated.
ENOUGH TO PROTECT -.581 .495
ENVIRONMENT
POOR COUNTRIES
LESS THAN RICH FOR .092 .819
ENVIRONMENT
LIKELIHOOD OF
NUCLEAR MELTDOWN .847 .087
IN 5 YEARS
Extraction Method: Principal Component Analysis.
Rotation Method: Varimax with Kaiser Normalization.
a. Rotation converged in 3 iterations.
Repeating the factor analysis

In the drop down menu,

select Factor Analysis to
reopen the factor analysis
dialog box.
Removing the variable from the list of
variables

First, highlight
the amprogrn
variable.

Second, click on the

left arrow button to
remove the variable
from the Variables list
box.
Replicating the factor analysis

The dialog recall command

opens the dialog box with all of
the settings that we had
selected the last time we used
factor analysis.
To replicate the analysis without
the variable that we just
removed, click on the OK button.
Checking for single-variable components

Rotated Component Matrixa On iteration 5, none of the

variables demonstrated
Component complex structure.
1 2 It is not necessary to remove
ENVIRONMENTAL any additional variables
THREATS -.207 .756 because of complex structure.
EXAGGERATED
HOW DANGEROUS
MODIFYING GENES IN .801 -.229
CROPS
POOR COUNTRIES
LESS THAN RICH FOR .051 .830
ENVIRONMENT
LIKELIHOOD OF After variables have been
NUCLEAR MELTDOWN .861 .059 removed for low communalities
IN 5 YEARS and complex structure, the
factor solution is examined to
Extraction Method: Principal Component Analysis. remove any components that
Rotation Method: Varimax with Kaiser Normalization. have only a single variable
a. Rotation converged in 3 iterations. loading on them.
If a component has only a
single variable loading on it,
the variable should be removed
from the next iteration of the
principal component analysis.
 Variable loadings on components

On iteration 5, the 2 Communalities

components in the
analysis had more than Initial Extraction
one variable loading on ENVIRONMENTAL
each of them. THREATS 1.000 .615
EXAGGERATED
HOW DANGEROUS
MODIFYING GENES IN 1.000 .694
Rotated Component Matrixa CROPS
POOR COUNTRIES
Component
LESS THAN RICH FOR 1.000 .691
1 2 ENVIRONMENT
ENVIRONMENTAL
LIKELIHOOD OF
THREATS -.207 .756
NUCLEAR MELTDOWN 1.000 .744
EXAGGERATED
IN 5 YEARS
HOW DANGEROUS
MODIFYING GENES IN .801 -.229 Extraction Method: Principal Component Analysis.
CROPS
POOR COUNTRIES The communalities for all of
LESS THAN RICH FOR .051 .830 the variables included on the
ENVIRONMENT components were greater
than 0.50 and all variables
LIKELIHOOD OF had simple structure.
NUCLEAR MELTDOWN .861 .059 The principal component
IN 5 YEARS analysis has been completed.
Extraction Method: Principal Component Analysis.
Rotation Method: Varimax with Kaiser Normalization.
a. Rotation converged in 3 iterations.
 Interpreting the principal components

The information in 4 of the

variables can be represented
by 2 components.
Component 1 includes the
variables "danger to the
environment from modifying genes
in crops" [genegen] and "likelihood
of nuclear power station damaging
Rotated Component Matrixa environment in next 5 years"
[nukeacc]. We can substitute one
Component component variable for this
1 2 combination of variables in further
ENVIRONMENTAL analyses.
THREATS -.207 .756
EXAGGERATED
HOW DANGEROUS
MODIFYING GENES IN .801 -.229
CROPS
POOR COUNTRIES Component 2 includes the
LESS THAN RICH FOR .051 .830 variables "claims about
ENVIRONMENT environmental threats are
LIKELIHOOD OF exaggerated" [grnexagg] and
NUCLEAR MELTDOWN .861 .059
"poorer countries should be
expected to do less for the
IN 5 YEARS
environment" [ldcgrn]. We can
Extraction Method: Principal Component Analysis. substitute one component variable
Rotation Method: Varimax with Kaiser Normalization. for this combination of variables in
a. Rotation converged in 3 iterations.
further analyses.
Variance explained in individual
variables

The components explain at

least 50% of the variance in
each of the variables included
in the final analysis.

Communalities

Initial Extraction
ENVIRONMENTAL
THREATS 1.000 .615
EXAGGERATED
HOW DANGEROUS
MODIFYING GENES IN 1.000 .694
CROPS
POOR COUNTRIES
LESS THAN RICH FOR 1.000 .691
ENVIRONMENT
LIKELIHOOD OF
NUCLEAR MELTDOWN 1.000 .744
IN 5 YEARS
Extraction Method: Principal Component Analysis.
 Total variance explained

Total Variance Explained

Initial Eigenvalues Extraction Sums of Squared Loadings Rotation Sums of Squared Loadings
Component Total % of Variance Cumulative % Total % of Variance Cumulative % Total % of Variance Cumulative %
1 1.626 40.651 40.651 1.626 40.651 40.651 1.428 35.699 35.699
2 1.119 27.968 68.619 1.119 27.968 68.619 1.317 32.921 68.619
3 .694 17.341 85.960
4 .562 14.040 100.000
Extraction Method: Principal Component Analysis.

The 2 components explain

68.619% of the total
variance in the variables
which are included on the
components.