CH 03

© 2019 Cengage 版權所有，為課本著作之延伸教材，亦受著作權法之規範保護，僅作為授課教學使用，禁止列印、影印、未經授權重製和公開散佈
Chapter 3:
Exploratory Factor Analysis
For use with Hair, Black, Babin and Anderson, Multivariate Data Analysis 8e © 2018 Cengage Learning EMEA
LEARNING OBJECTIVES
Upon completing this chapter, you should be able to do the following:

• Differentiate exploratory factor analysis techniques from other multivariate
techniques.
• Distinguish between exploratory and confirmatory uses of factor analytic techniques.
• Understand the seven stages of applying exploratory factor analysis.
• Distinguish between R and Q factor analysis.
• Identify the differences between principal component analysis and common factor
analysis models.
• Describe how to determine the number of factors to extract.
• Explain the concept of rotation of factors.
• Describe how to name a factor.
• Explain the additional uses of exploratory factor analysis.
• State the major limitations of exploratory factor analytic techniques. 2
Overview
What Is Exploratory Factor Analysis?

A Hypothetical Example of Exploratory Factor Analysis
Factor Analysis Decision Process
• Stage 1: Objectives of Exploratory Factor Analysis
• Stage 2: Designing an Exploratory Factor Analysis
• Stage 3: Assumptions in Exploratory Factor Analysis
• Stage 4: Deriving Factors and Assessing Overall Fit
• Stage 5: Interpreting the Factors
• Stage 6: Validation of Exploratory Factor Analysis
• Stage 7: Data Reduction—Additional Uses of Exploratory Factor Analysis Results
An Illustrative Example
3
WHAT IS EXPLORATORY FACTOR ANALYSIS?
4
Exploratory Factor Analysis Defined
An interdependence A primary element in

technique whose primary Variable Specification while
purpose is to define the Managing the Variate
underlying structure among
the variables in the analysis.
5
What is Exploratory Factor Analysis?
Exploratory Factor Analysis (EFA) . . .
• Examines the interrelationships among a large number of variables and

then attempts to explain them in terms of their common underlying
dimensions.
• These common underlying dimensions are referred to as factors or
components.
• EFA is a summarization and data reduction technique that does not have
independent and dependent variables, but is an interdependence
technique in which all variables are considered simultaneously.
6
A HYPOTHETICAL EXAMPLE OF EXPLORATORY

FACTOR ANALYSIS
7
Correlation Matrix for Store Image Elements

Situation: retailer would like to know whether consumers think in more general evaluative dimensions
rather than in just the specific items
Research Plan: nine store image elements, including measures of the product offering, store personnel,
price levels, and in-store service and experiences
V1 V2 V3 V4 V5 V6 V7 V8 V9
V1 Price Level 1.00
V2 Store Personnel .427 1.00
V3 Return Policy .302 .771 1.00
V4 Product Availability .470 .497 .427 1.00
V5 Product Quality .765 .406 .307 .472 1.00
V6 Assortment Depth .281 .445 .423 .713 .325 1.00
V7 Assortment Width .354 .490 .471 .719 .378 .724 1.00
V8 In-Store Service .242 .719 .733 .428 .240 .311 .435 1.00
V9 Store Atmosphere .372 .737 .774 .479 .326 .429 .466 .710 1.00 8
Correlation Matrix After Grouping Using Factor Analysis
Results: Shaded areas represent variables likely to be grouped together by

exploratory factor analysis.
V3 V8 V9 V2 V6 V7 V4 V1 V5
V3 Return Policy 1.00
V8 In-store Service .733 1.00
V9 Store Atmosphere .774 .710 1.00
V2 Store Personnel .741 .719 .787 1.00
V6 Assortment Depth .423 .311 .429 .445 1.00
V7 Assortment Width .471 .435 .468 .490 .724 1.00
V4 Product Availability .427 .428 .479 .497 .713 .719 1.00
V1 Price Level .302 .242 .372 .427 .281 .354 .470 1. 00
V5 Product Quality .307 .240 .326 .406 .325 .378 .472 .765 1.00
9
Interpreting the Factor Analysis Results

Variables Factors
V3 Return Policy
V8 In-store Service
In-store Experience
V9 Store Atmosphere
V2 store Personnel
V6 Assortment Depth
V7 Assortment Width Product Offerings
V4 Product Availability
V1 Price Level
Value
V5 Product Quality 10
EXPLORATORY FACTOR ANALYSIS DECISION

PROCESS
Stage 1: Objectives of Exploratory Factor Analysis (EFA)

Stage 2: Designing an Exploratory Factor Analysis
Stage 3: Assumptions in Exploratory Factor Analysis
Stage 4: Deriving Factors and Assessing Overall Fit
Stage 5: Interpreting the Factors
Stage 6: Validation of Exploratory Factor Analysis
Stage 7: Additional uses of Exploratory Factor Analysis Results
11
STAGE 1: OBJECTIVES OF
EXPLORATORY FACTOR ANALYSIS
 Specifying the Unit of Analysis
 Achieving Data Summarization Versus Data Reduction
 Variable Selection
 Using Factor Analysis with Other Multivariate Techniques
12
Types of Factor Analysis
Exploratory Factor Analysis (EFA)

• used to discover the factor structure of a construct and examine its
reliability. It is data driven.
Confirmatory Factor Analysis (CFA)

• used to confirm the fit of the hypothesized factor structure to the
observed (sample) data. It is theory driven.
13
EFA Unit of Analysis and Objectives
Unit of Analysis
• Variables – most common application, termed R-factor analysis.
• Cases – grouping cases, similar to cluster analysis, termed Q-factor analysis.
Data Summarization versus Data Reduction

• Data summarization – defining structure through underlying dimensions that,
when interpreted and understood, describe the data in a much smaller number of
concepts than the original individual variables. The basis for scale development.
• Data reduction – extends the process of data summarization by deriving an

empirical value (factor score or summated scale) for each dimension (factor) and
then substituting this value for the original variable values in subsequent analysis.
14
Variable Selection and Use with Other Techniques
Three Elements in variable selection

1. Variable specification – researcher must specifically designate variables to be
analyzed.
2. Factors are always produced – EFA always generates factors, researcher has the
responsibility to evaluate the usefulness and validity of the factors.
3. Factors require multiple variables – EFA must have at least two correlated
variables to form a factor. Thus, variables which are not included in a specified
factor are not “defective” in some manner, it is just that no other correlated
variables were included in the analysis.
Using Factor Analysis with Other Multivariate Techniques
• Factors may identify concepts more useful than individual variables.
• Factors help mitigate the impact of multicollinearity on the interpretation of
correlated variables.
15
STAGE 2: DESIGNING AN
 Variable Selection and Measurement Issues
 Sample Size
 Correlations among Variables or Respondents
16
EFA Research Design
Factor analysis is performed most often only on metric variables

• Specialized methods exist for the use of dummy variables, but a small number of
“dummy variables” can be included in a set of metric variables that are factor
analyzed.
• If a study is being designed to reveal factor structure, strive to have at least five
variables for each proposed factor.
For sample size:
• the sample must have more observations than variables.
• the minimum absolute sample size should be 50 observations.
• Maximize the number of observations per variable, with a minimum of five and
hopefully at least ten observations per variable.
Correlation matrix (“R analysis”) most often performed, although
similarity/distance matrix (“Q analysis”) also an option. 17
STAGE 3: ASSUMPTIONS IN FACTOR ANALYSIS
 Conceptual Issues
 Statistical Issues
18
Assumptions of EFA
Conceptual
• Before the factor analysis is performed, there must be a strong conceptual
foundation to support the assumption that a structure does exist.
• Assume a homogeneity of sub-sample factor solutions
Statistical Issues Addressing Multicollinearity
• A statistically significant Bartlett’s test of sphericity (sig. < .05) indicates that sufficient
correlations exist among the variables to proceed with an exploratory factor analysis.
• More diagnostic test is the MSA (measure of sampling adequacy).
• Measured by the Kaiser-Meyer-Olkin (KMO) statistic that indicates if a set of variables is likely
identify a good factor solution based on correlations/partial correlations.
• KMO statistic exists for each individual variable and an overall value that can vary from 0 to 1.0.
• KMO value must exceed .50 for both the overall test and each individual variable. Variables with
values less than .50 should be omitted from the factor analysis one at a time, with the smallest one
being omitted each time, until both overall and all individual values are above .50
19
STAGE 4: DERIVING FACTORS AND

ASSESSING OVERALL FIT
 Selecting the factor extraction method – common vs. component analysis.
 Stopping Rules: Criteria for the Number of Factors to Extract.
 Alternatives to Principal Components and Common Factor Analysis.
20
Selecting the factor extraction method
Partitioning the Variance

• Common variance
• Variance of a variable that is shared with all other variables in the analysis.
• Results from the variable’s correlations with all other variables in the analysis.
• Variable communality is the estimate of its shared, or common, variance among
the variables as represented by the derived factors.
• Unique variance – composed of Specific and Error variance
• Specific variance – cannot be explained by the correlations to the other variables
but reflects the unique characteristics of that variable apart from the other
variables in the analysis.
• Error variance – due to unreliability in the data-gathering process, measurement
error, or a random component in the measured phenomenon.
21
How do they differ?
Extraction Method Determines the Types of Variance

Carried into the Factor Matrix
22
Which One To Use?
Principal component analysis is most appropriate when:

• data reduction is a primary concern, focusing on the minimum number of factors
needed to account for the maximum portion of the total variance represented in
the original set of variables.
• prior knowledge suggests that specific and error variance represent a relatively
small proportion of the total variance.
• the principal component results are used as a preliminary step in the scale
development process.
Common factor analysis is most appropriate when:
• the primary objective is to identify the latent dimensions or constructs
represented in the common variance of the original variables, as typified in the
scale development process.
• the researcher has little knowledge about the amount of specific and error
variance and therefore wishes to eliminate this variance. 23
Stopping Rules: Criteria for the Number of Factors to Extract
A Priori Criterion
• researcher knows how many factors to extract and specifies for factor extraction.
Latent Root Criterion (aka Kaiser rule)
• most commonly used technique.
• factors having latent roots or eigenvalues greater than 1 are considered significant.
• most applicable to principal components analysis where the diagonal value
representing the amount of variance for each variable is 1.0.
• less accurate with a small number of variables or lower communalities.
Percentage of Variance
• Extract enough components to achieve a specified cumulative percentage of total
variance extracted.
24
Scree Test Criterion

• Identify the optimum number of factors that
can be extracted before the amount of
unique variance begins to dominate the
common variance structure.
• Plot of latent root (eigenvalues) defines
“elbow,” the point at which the curve first
begins to straighten out.
• Considered to represent those factors
containing more unique rather than
common variance.
• Most researchers do not include the elbow,
but rather retain all of the preceding factors.
25
Parallel Analysis
• Empirical measure based on the specific characteristics (i.e., number of variables and
sample size) of the dataset being analyzed.
Procedure
1. Generate a large number (e.g., 500 or 1000) simulated datasets with random values
for the same number of variables and sample size.
2. Apply either principal components or common factor analysis to each dataset.
3. Calculate average eigenvalue across datasets for each factor(i.e., first, second, . . . )
4. Compare to eigenvalues for original data and retain all factors that are greater than
average eigenvalues from random datasets
• Variants of this rule suggest taking the upper bound (95th percentile) of the simulated eigenvalues.
Applicable equally well to principal components or common factor methods

26
Rules of Thumb – Choosing Factor Models and Number of Factors

• While principal component and common factor analysis models yield similar results in
most research settings (30 or more variables or communalities of .60 for most variables):
 the principal component analysis model is most appropriate when data reduction is paramount.
 the common factor model is best in well-specified theoretical applications.
• A decision on the number of retained factors should be based on several considerations:
 Use several stopping criteria to determine the initial number of factors to retain.
 Factors With Eigenvalues greater than 1.0.
 A pre-determined number based on research objectives and/or prior research.
 Enough factors for a specified percentage of variance explained (e.g., usually 60%).
 Factors shown by the scree test to have substantial amounts of common variance (i.e, before inflection point).
 Factors which have eigenvalues greater than factors from randomly-generated data.
 Factors above the threshold established by parallel analysis.
 More factors when there is heterogeneity among sample subgroups.
• Consideration of several alternative solutions (one more and one less factor than the initial
solution) to ensure the best structure is identified. 27
Alternatives to Principal Components and Common Factor
Analysis
Factor Analysis of Categorical Data
• Optimal scaling is a process to derive interval measurement properties for
variables which were originally nominal or ordinal measures.
• Two issues
• optimal scaling works within the variable set specified (e.g., maximizes the correlations among
the variables in the analysis), but this scaling may change in other analyses.
• the researcher sets a series of allowable transformations (e.g., retain ordinality or not).
Variable Clustering
• Variant of PCA popularized in the PROC VARCLUS of SAS.
• Form of “sequential” factor extraction where factors are split to form new factors
• Benefits include:
• not impacted by the number of variables included like PCA.
• based on a hierarchical process of component formation.
• introduces additional diagnostics for selecting the most representative variable(s).
28
STEP 5: INTERPRETING THE FACTORS
 The Three Processes of Factor Interpretation

 Factor Extraction
 Rotation of Factors
 Judging the Significance of Factor Loadings
 Interpreting a Factor Matrix
29
The Three Processes of Factor Interpretation
1. Estimate the Factor matrix

• Compute unrotated factor loadings – correlation of variable and factor.
• If used strictly for data reduction, process can stop here.
2. Factor Rotation
• Employ a rotational method to achieve simpler and theoretically more meaningful
factor solutions.
• In most cases rotation of the factors improves the interpretation by reducing some
of the ambiguities that often accompany initial unrotated factor solutions.
3. Factor Interpretation and Respecification
• evaluate the (rotated) factor loadings for each variable in order to determine that
variable’s role and contribution in determining the factor structure.
• Respecification involves eliminating variables or extract different number of factors.
30
Rotation of Factors
Procedure
• The reference axes of the factors are turned about the origin until some other
position has been reached. Loadings of each variable remain fixed relative to other
loadings.
Impact
• The ultimate effect of rotating the factor matrix is to redistribute the variance
from earlier factors to later ones to achieve a simpler, theoretically more
meaningful factor pattern.
Alternative Methods
• Orthogonal rotation – simplest approach which maintains orthogonality of factors.
• Most common method – VARIMAX.
• Oblique rotation – allows for correlation among rotated factors.
31
Comparing the Two Rotation Methods
Orthogonal Rotation Oblique rotation
32
Rules of Thumb – Choosing Factor Rotation Methods
Orthogonal rotation methods . . .

• are the most widely used rotational methods.
• are the preferred method when the research goal is data reduction to
either a smaller number of variables or a set of uncorrelated measures for
subsequent use in other multivariate techniques.
Oblique rotation methods . . .
• best suited to the goal of obtaining several theoretically meaningful
factors or constructs because, realistically, very few constructs in the “real
world” are uncorrelated.
33
Judging the Significance of Factor Loadings

Practical Significance For Assessing Structure
• Equivalent to zero: less than +/- .10
• Minimal Level: in the range of +/- .30 to +/- .40
• Practically Significant: values of +/- .50 or greater
• Well-defined structure: exceeding +/- .70
Factor Structure
• A smaller loading is needed given either a larger
sample size or a larger number of variables.
• A larger loading is needed given a factor solution
with a larger number of factors.
Statistical Significance
• Ensuring adequate statistical power, significant
loadings can be identified by sample size.
34
Interpreting a Factor Matrix

Interpretation needed when factors used beyond solely data reduction
Objective is simple structure, characterized by two principles:

• each variable has a high/significant loading on one factor only, and
• each factor has high/significant loadings for only a subset of items.
Five step process

1. Examine the factor matrix of loadings.
2. Identify the significant loading(s) for each variable.
3. Assess the communalities of the variables.
4. Respecify the factor model if needed.
5. Label the factors.
35
Step 1: Examine the factor matrix of loadings
Starting Point:
• Factor matrix has loadings of every variable on every factor extracted.
• Examine each variable for the highest loading/significant loading on a factor.
• Cross-loading – when a variable has a significant loading on more than one factor.
Two Principles to Assist in Identifying Cross-loadings

• Compare variances, Not Loadings.
• Variance (i.e., squared loading) is ultimate objective of factor analysis, so use that measure.
• Compare ratios of variances.
• Relative magnitude expressed as the ratio of two variances (larger variance / smaller variance)
which “scales” the variance difference to the size of the two variances.
36
Process For Identifying Cross-Loadings
1. Identify potential cross-loadings

• Both loadings for a variable must be above the threshold for significance (e.g., .30
or .40).
2. Compute the ratio of the squared loadings
• Square each of the loadings and then compute the ratio of the larger loading to
the smaller loading.
3. Designate the pair of loadings as follows based on the ratio:
• Between 1.0 and 1.5 — problematic cross-loading and the variable with smaller
loading a strong candidate for elimination to achieve simple structure.
• Between 1.5 and 2.0 — potential cross-loading, with deletion of a variable based
on interpretability of resulting factors.
• Greater than 2.0 — ignorable cross-loading, where smaller loading, while
significant, can be ignored for purposes of interpretation. 37
Example for Identifying Cross-Loadings
38
Step 3: Assess the Communalities of the Variables
Communality
• Represents the amount of variance accounted for by the factor solution for each
variable.
• Calculated as the sum of the squared loadings across all retained factors.
Use as an Evaluative Measure

• view the communalities to assess whether the variables meet acceptable levels of
explanation.
• For example, a researcher may specify that at least one-half of the variance of
each variable must be taken into account. Using this guideline, the researcher
would identify all variables with communalities less than .50 as not having
sufficient explanation.
39
Step 4: Respecify the Factor Model if Needed
Three conditions indicating possible respecification

• a variable has no significant loadings.
• even with a significant loading, a variable’s communality is deemed too low.
• a variable has a cross-loading.
If respecification is needed, several options are available . . .

• Ignore the problematic variable.
• Deletion of variables from the analysis.
• Use a different rotational approach.
• Extract a different number of factors.
• Change the method of extraction.
40
Step 5: Label the Factors
Objective:
• Assign some meaning to the pattern of factor loadings.
• Variables with higher loadings are considered more important and have greater
influence on the name or label selected to represent a factor.
Considerations
• The signs are interpreted just as with any other correlation coefficients. For each
factor, like signs mean the variables are positively related, and opposite signs
mean the variables are negatively related.
• The label is intuitively developed by the researcher based on its appropriateness
for representing the underlying dimensions of a particular factor.
41
Rules of Thumb – Interpreting The Factors
• An optimal structure exists when all variables have high loadings only on a
single factor.
• Variables that cross-load (load highly on two or more factors) are usually deleted
unless theoretically justified or the objective is strictly data reduction.
• Variables should generally have communalities of greater than .50 to be
retained in the analysis.
• Respecification of a factor analysis can include options such as:
• deleting a variable(s),
• changing rotation methods, and/or
• increasing or decreasing the number of factors.
42
STAGE 6: VALIDATION OF
 Use of Replication or a Confirmatory Perspective

 Assessing Factor Structure Stability
 Detecting Influential Observations
43
Approaches to Validation
Use of Replication or a Confirmatory Perspective

• assess the replicability/generalizability of the results, either with a split sample in
the original dataset or with a separate sample.
• pursue a confirmatory analysis, most likely with structural equation modeling.
Assessing Factor Structure Stability

• Larger samples provide more confidence as to generalizability and stability.
Detecting Influential Observations

• estimate the model with and without observations identified as outliers to assess
their impact on the results. If omission of the outliers is justified, the results
should have greater generalizability.
44
STAGE 7: ADDITIONAL USES OF EFA RESULTS
 Selecting Surrogate Variables for Subsequent Analysis

 Creating Summated Scales
 Computing Factor Scores
 Selecting among the Three Methods
45
Selecting Surrogate Variables for Subsequent Analysis
A single variable selected to represent the factor in other analyses

• Typically, variable with highest loading is selected to represent a factor.
Advantages:
• simple to administer and interpret.
Disadvantages:
• does not represent all “facets” of a factor.
• prone to measurement error.
46
Creating Summated Scales

Composite value calculated (e.g., mean) from variables loading highly on
the factor
• only as good as the items used to represent the construct. While it may pass all
empirical tests, it is useless without theoretical justification.
Advantages:
• compromise between the surrogate variable and factor score options.
• reduces measurement error.
• represents multiple facets of a concept.
• easily replicated across studies.
Disadvantages:
• includes only the variables that load highly on the factor.
• not necessarily orthogonal.
• requires extensive analysis of reliability and validity issues. 47
Assessing Summated Scales
Unidimensionality
• Never create a summated scale without first assessing its unidimensionality with
exploratory or confirmatory factor analysis.
Reliability
• With unidimensionality, its reliability score, as measured by Cronbach’s alpha:
• should exceed a threshold of .70, although a .60 level can be used in exploratory research.
• the threshold should be raised as the number of items increases, especially as the number of items
approaches 10 or more.
Validity
• With reliability established, validity should be assessed in terms of:
• convergent validity = scale correlates with other similar scales.
• discriminant validity = scale is sufficiently different from other related scales.
• nomological validity = scale “predicts” as theoretically suggested.
48
Computing Factor Scores
Software computes composite measure of factor based on loadings
Advantages:
• represents all variables loading on the factor.
• best method for complete data reduction.
• by default, factors (and factor scores) are orthogonal and can avoid complications
caused by multicollinearity.
Disadvantages:
• interpretation more difficult since all variables contribute through loadings.
• difficult to replicate across studies.
49
AN ILLUSTRATIVE EXAMPLE OF EFA
50
Research Design
Research Objective:
• Assess dimensional structure among 13 Performance Perception Variables
Variables used Variable Description Variable Type
Performance Perceptions Variables

X6 Product Quality metric
X7 E-Commerce Activities/Website metric
X8 Technical Support metric
X9 Complaint Resolution metric
X10 Advertising metric
X11 Product Line metric
X12 Salesforce Image metric
X13 Competitive Pricing metric
X14 Warranty & Claims metric
X15 New Products metric
X16 Ordering & Billing metric
X17 Price Flexibility metric
X18 Delivery Speed metric
51
Scree Test and Parallel Analysis for Component
Analysis
52
Final Results: Rotated Component Matrix of “Reduced Set” of HBAT Perceptions

Variables
53
Factor Analysis Learning Checkpoint
1. What are the major uses of exploratory factor analysis?

2. What is the difference between component analysis and
common factor analysis?
3. Is rotation of factors necessary?
4. How do you decide how many factors to extract?
5. What is a significant factor loading?
6. How and why do you name a factor?
7. Should you use factor scores or average summated ratings in
follow-up analyses?
54

CH 03

Uploaded by

Copyright:

Available Formats

CH 03

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

CH 03

Uploaded by

Copyright:

Available Formats

© 2019 Cengage 版權所有，為課本著作之延伸教材，亦受著作權法之規範保護，僅作為授課教學使用，禁止列印、影印、未經授權重製和公開散佈

Upon completing this chapter, you should be able to do the following:

What Is Exploratory Factor Analysis?

WHAT IS EXPLORATORY FACTOR ANALYSIS?

Exploratory Factor Analysis Defined

An interdependence A primary element in

What is Exploratory Factor Analysis?

Exploratory Factor Analysis (EFA) . . .

• Examines the interrelationships among a large number of variables and

A HYPOTHETICAL EXAMPLE OF EXPLORATORY

Correlation Matrix for Store Image Elements

Correlation Matrix After Grouping Using Factor Analysis

Results: Shaded areas represent variables likely to be grouped together by

Interpreting the Factor Analysis Results

V7 Assortment Width Product Offerings

EXPLORATORY FACTOR ANALYSIS DECISION

Stage 1: Objectives of Exploratory Factor Analysis (EFA)

Types of Factor Analysis

Exploratory Factor Analysis (EFA)

Confirmatory Factor Analysis (CFA)

EFA Unit of Analysis and Objectives

Data Summarization versus Data Reduction

• Data reduction – extends the process of data summarization by deriving an

Variable Selection and Use with Other Techniques

Three Elements in variable selection

EFA Research Design

Factor analysis is performed most often only on metric variables

STAGE 3: ASSUMPTIONS IN FACTOR ANALYSIS

STAGE 4: DERIVING FACTORS AND

Selecting the factor extraction method

Partitioning the Variance

How do they differ?

Extraction Method Determines the Types of Variance

Which One To Use?

Principal component analysis is most appropriate when:

Stopping Rules: Criteria for the Number of Factors to Extract

Stopping Rules: Criteria for the Number of Factors to Extract

Scree Test Criterion

Stopping Rules: Criteria for the Number of Factors to Extract

Applicable equally well to principal components or common factor methods

Rules of Thumb – Choosing Factor Models and Number of Factors

STEP 5: INTERPRETING THE FACTORS

 The Three Processes of Factor Interpretation

The Three Processes of Factor Interpretation

1. Estimate the Factor matrix

Comparing the Two Rotation Methods

Orthogonal Rotation Oblique rotation

Rules of Thumb – Choosing Factor Rotation Methods

Orthogonal rotation methods . . .

Judging the Significance of Factor Loadings

Interpreting a Factor Matrix

Objective is simple structure, characterized by two principles:

Five step process

Step 1: Examine the factor matrix of loadings

Two Principles to Assist in Identifying Cross-loadings

Process For Identifying Cross-Loadings

1. Identify potential cross-loadings

Example for Identifying Cross-Loadings

Step 3: Assess the Communalities of the Variables