More Advanced Methods; Factor Analysis

Question 1

________ ______ involves grouping similar variables into dimensions/factors.

Answer 1

Factor analysis

Question 2

Factor Analysis:

• Most commonly an _________ approach to data analysis.
• Also a _________ manner to data analysis.
• More controversial than other analytic methods leaving room for subjectivity and judgment.
• Crucial multiavariate analysis method to provide structure to data sets with multiple observed variables.

Answer 2

• exploratory (Exploratory Factor Analysis; EFA)

- confirmatory (Confirmatory Factor Analysis; CFA)

Question 3

EFA is a factor analysis used to do what?

Answer 3

• Explore the possible underlying factor structure of a set of observed variables without imposing a predefined structure of the outcome.
• Identify the underlying factor structure.
• Describe and identify the number of factors.

Question 4

What are the goals of EFA?

Answer 4

• Determine the number of latent constructs underlying a set of variables.
• Provide a means of explaining variation among variables using only a few newly created factors.
• Define the content of meaning of factors.

Question 5

What are the underlying assumptions of EFA?

Answer 5

• Continuous level of measurement with normal distribution.
• Sample size should be large enough (more than 200 and 5 observations per variable)
• Correlation >0.3 between the variables.

Question 6

What are the limitations of EFA?

Answer 6

• Variables could be sample specific, not generalizable.
• Non-normal distribution of data.
• Sample size larger than the required is desirable to accommodate the possible missing data.
• No causal inferences can be made from correlations alone.

Question 7

CFA is a factor analysis used to do what?

Answer 7

-Test the hypothesis that there exists a relationship between the observed variables and their underlying latent constructs.

Question 8

What is the procedure of CFA?

Answer 8

1. ) Review the relevant theory and research literature to support model specification.
2. ) Specify a model.
3. ) Collect data.
4. ) Assess model fit by hypothesis testing or fit indices look up.

Question 9

What are the limitations of CFA?

Answer 9

• Sample size required to be sufficiently large.
• Multivariate normality.
• Outliers
• Missing data

Question 10

If unacceptable model fit is found in CFA, an _____ can be performed to identify the underlying structure, describe and identify the number of factors.

Answer 10

EFA

Question 11

EFA steps?

Answer 11

1. ) Developing Factors
2. ) Extraction of Factors
3. ) Rotation of Factors
4. ) Naming Factors

Question 12

EFA-Developing Factors:

• What does developing factors mean?
• What is Factor Loadings?
• What are the criteria for significance of factor loadings (FL)?

Answer 12

• To examine a large set of behaviors within an individual and categorize them as representing different conceptual elements of the person’s psychological state.
• The coefficient as a measure of the correlation between the individual variable and the overall factor.
• FL >0.3 = minimum consideration
• FL >0.4 = more important
• FL >0.5 = practically significant

Question 13

EFA-Extraction of Factors:
-Example = To study behaviors related to chronic pain in a sample of 150 patients with low back pain. Seven variables are examined and measured on a 5-point Likert scale from 1="never observed" to 5="almost always observed".
These seven variables are:
1.) COMPLAINS about pain
2.) CHANGES position frequently while sitting
3.) GROANS, moans, or sighs
4.) RUBS painful body parts
5.) ISOLATES herself or himself
6.) MOVES rigidly and stiffly
7.) Drags feet when WALKING

-With the extraction of factors, pull out only the components with Eigenvalue of at least ___.

Answer 13

-1

Question 14

EFA-Rotation of Factors:
-Rotation of factors is a process of developing a unique statistical solution so that each variable relates highly to only ____ factor.

Answer 14

-1

Question 15

EFA-Naming Factors:
-Naming Factors is also a process of developing a unique statistical solution so that each variable relates highly to only ____ factor.

Answer 15

-1

Question 16

What are the applications of Factor Analysis?

Answer 16

• Exploratory Analysis
• Reduction of Data
• Factor Scores
• Construct Validity
• Hypothesis Testing

Question 17

What are the limitations of Factor Analysis?

Answer 17

• Be cautious about how “factors” are interpreted
  
  • They are not real measurement entities.
  • Only hypothetical statistical concepts.
  • Giving factor a name doesn’t make it real.
• Data may be organized differently by using different extraction or rotation methods.
  
  • These differences can alter a factor’s meaning.
• The generated factors may be totally uninterpretable within the framework of the research question.

Question 18

Summary for More Advanced Methods; Factor Analysis

• The application of factor analysis involves grouping similar ________ into _________.
• _________________ is used to explore the possible underlying factor structure of a set of observed variables without imposing a predefined structure of the outcome.
• _________________ is used to test the hypothesis that there exists a relationship between the observed variables and their underlying latent constructs.
• Steps of an exploratory factor analysis are in the order of _________ factors, __________ factors, _______ factors, and ________ factors.
• Limitations of factor analysis stem from its subjectivity and judgmental nature in decisions; specifically, factors are not real measurement entities only being hypothetical statistical concepts; the resulting data structure is subject to different selection of extraction or rotation methods; the generated factors may be totally uninterpretable within the framework of the research question.

Answer 18

• variables into factors
• Exploratory Factor Analysis (EFA)
• Confirmatory Factor Analysis (CFA)
• developing, extracting, rotating, naming