2b Factor Anaysis

FACTOR ANALYSIS
Jimma University
Dr. Chalchissa Amentie
(Associate Professor in Management ,
chalchissa@yahoo.com)
CHALCHISSA@YAHOO.COM
Factor Analysis
• Factor analysis is a class of procedures used for data reduction and
summarization factors.
• It is an interdependence technique: no distinction between dependent and
independent variables.
• Factor analysis is used:

– To identify underlying dimensions, or factors, that explain the
correlations among a set of variables.
– To identify a new, smaller, set of uncorrelated variables to replace

the original set of correlated variables.
Factor analysis ….
General Concepts
In practice, a factor cannot be estimated with one item
Should only be estimated with three or more items
Items with higher correlation with factor contribute more to the
measure
X X X
e e e
Newsom, Spring 2017, Psy 495 Psychological Measurement

Factor analysis…
7
General Concepts
Items are referred to as indicators
Regression slopes between factor and indicators are referred to

as loadings
X1 X2 X3
e e e
Newsom, Spring 2017, Psy 495 Psychological Measurement

Factor Analysis Model
 Each variable is expressed as a linear combination of factors. The
factors are some common factors plus a unique factor. The factor model
is represented as:
 The common factors themselves can be expressed as linear
combinations of the observed variables.
Fi = Wi1X1 + Wi2X2 + Wi3X3 + . . . + WikXk

Where:
Fi = estimate of i th factor
Wi= weight or factor score coefficient
k = number of variables
FACTOR ANALYSIS (By SPSS)
 There are two types of FA :
• Exploratory Factor Analysis
• Confirmatory factor analysis

EXPLORATORY FACTOR ANALYSIS by SPSS
 exploratory factor analysis is undertaken without a hypothesis in mind.
 It’s an investigatory process that helps researchers understand whether associations

exist between the initial variables, and if so, where they lie and how they are
grouped.
 help to reduce data to a smaller set of summary variables and to explore the
underlining theoretical structure of the phenomena
 Principal component analysis is a popular

 Using this method, will run the analysis to obtain multiple possible solutions that
split their data among a number of factors.
 Identify, Items that load onto a single factor are more strongly related to one
another and can be grouped together.
Confirmatory factor analysis
 In this type of analysis, the researcher starts out with a hypothesis

about their data that they are looking to prove or disprove.
 Factor analysis will confirm – or not – where the latent variables are and
how much variance they account for.
FACTOR ANALYSIS …
I: Running the Factor Analysis Procedure (by PCA)
 From the menu bar select Analyze and choose Data Reduction and then click
on Factor.
 Highlight related variables and send them to variables lists. Then select some
options and run the procedure.
 Click on the DESCRIPTIVES ===check boxes Univariate Descriptives,
 Coefficients, Determinant, KMO and Bartlett's test of sphericity, and Reproduced.

Click on Continue to return to the Factor Analysis dialogue box. (see the next slide )
Rotation of Factors
 a rotation method helps to gets factors that are as different from each other as
possible, and helps you interpret the factors by putting each variable primarily on one
of the factors.
Note: However, you still need to decide whether you want an “orthogonal” solution
(factors are not highly correlated with each other), or
an “oblique” solution (factors are correlated with one another). If you want an oblique
solution, the only choice SPSS gives you is “Direct Oblimin.”
So, select Varimax.” Most of the factor analyses in published articles use a Varimax
rotation.
Click in suppresss small coefficient is to block loading factors less than .5,
This help easily getting strong loading factor/ highly correlated(>.5) while (>.3
also acceptable for further factor analysis
Factor Analysis run procedure with PCA…
1st 2nd
3rd 4th
loadi
gr
highly
Final – click ok
Factor Analysis .. Results of Principal Components
Analysis
II. Generating Results and implications

Bivariate Analysis
Results of Principal Components Analysis All r>0.3
Except Ut4 with
Acqui1
Correlation/Bivariate result ..
 The correlation of items to each other greater 0.3 is

Acceptable (Juile,2005; Field,2013).
 Conclusion ???
 Except Acq1 to Uti4 =low ( 0.203) is acceptable that shows

almost the variables are appropriate for factor analysis and
 but still needs further test

Kaiser-Meyer-Olkin (KMO) and Bartlett's Test :
 measures strength of the relationship among variables
two statistical measures are also generated by SPSS to assess the factorability
of the data (i.e. suitability of the dataset for factor analysis):
Bartlett’s test of sphericity should be significant (p<0.05) –to suitablee
association for hypothesis and factor analysis
Kaiser Meyer Olkin (KMO): measure of sampling adequacy the value greater
than 0.5 is Acceptable for sample is adequate (Kaiser 1974,Hair et al., 2007;
Pallant, 2011; Field, 2005; Field, 2013) for the factor analysis to be considered
appropriate
.
For current study, (see table below)
the KMO test values for this factor is 0.828 , which is good (Kaiser,1974)
the Bartlett’s test is significant (p=0.000)
indicated that the data were reliable and suitable for factor analysis
Results of Principal Components Analysis…
.Communalities
For further Communalities of constructs are
calculated to check reliabilities of data
Communalities indicate the amount of variance in
each variable that is accounted for.
Small values (average <0.60 at cases >250) indicate
variables that do not fit well with the factor solution,
and should possibly be dropped from the analysis
What is your interpretation/Conclusion for this study?

As per this table, Acqui1, Acqui3, Acqui4,
Diss3,Diss4, Uti1 and,Uti2 should be dropped
Note: But, we should furthers test to conclude
Total Variance Explained
 The next item shows all the factors extractable from the analysis along
with their eigenvalues, the percent of variance attributable to each factor,
and the cumulative variance of the factor and the previous factors.
Notice:
 the first factor accounts for 34.732% of the variance, the second 13.341% and
the third 10.441%.
 Totally 58.521% variance of the variable(CO) were explained by these 12 items

(in three components/groups) see next slide/table
 All the remaining factors are not significant. (see table below)
Results of Principal Components Analysis…
Rotated component Matrix
 -shows the loadings of the variables on the three factors extracted
(Groping the similar factors together).
 The higher the absolute value of the loading, the more the factor
contributes to the variable.
 loadings(λ) that are greater than 0.5, acceptable for factor anaysis
 NB1: in this study loadings that are greater than 0.5, this
makes reading the table easier. We suppressed/blocked all loadings less
than 0.5
Conclusion
 Conclusion ??
 shows the loadings of the 12 variables on the three factors
extracted(groups) are greater than .5,
 Therefore, these factors can be used as variables for further analysis.
EFA steps NOTE: Other method

Run MLE, oblimin allowing eigenvalues>1.00
1. Remove items with cross-loadings >.30 (By clicking in the box of suppresss and insert 0 .3)
2. Remove items with no loading >.30
3. Remove items which did not logically fit their factor
4. Remove items that seem literally repetitive in content
5. Remove factors that are repetitive in meaning to earlier factors
RESULT
Items kept fit conceptually and have strong unique loadings on 1 factor; CFA tests whether the
simplified model still fits the data.
Factor Analysis…
 Assignment (By Group)
 Do factor Analysis for (you will present in class)
1. Of Market Orientation
2. Productive innovative success

2b Factor Anaysis

Uploaded by

Copyright:

Available Formats

2b Factor Anaysis

Uploaded by

Document Information

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

2b Factor Anaysis

Uploaded by

Copyright:

Available Formats

FACTOR ANALYSIS

• Factor analysis is used:

– To identify a new, smaller, set of uncorrelated variables to replace

Newsom, Spring 2017, Psy 495 Psychological Measurement

Regression slopes between factor and indicators are referred to

Newsom, Spring 2017, Psy 495 Psychological Measurement

Fi = Wi1X1 + Wi2X2 + Wi3X3 + . . . + WikXk

 There are two types of FA :

• Exploratory Factor Analysis

• Confirmatory factor analysis

 exploratory factor analysis is undertaken without a hypothesis in mind.

 It’s an investigatory process that helps researchers understand whether associations

 Principal component analysis is a popular

 In this type of analysis, the researcher starts out with a hypothesis

 Click on the DESCRIPTIVES ===check boxes Univariate Descriptives,

 Coefficients, Determinant, KMO and Bartlett's test of sphericity, and Reproduced.

II. Generating Results and implications

 The correlation of items to each other greater 0.3 is

 Except Acq1 to Uti4 =low ( 0.203) is acceptable that shows

 but still needs further test

What is your interpretation/Conclusion for this study?

 Totally 58.521% variance of the variable(CO) were explained by these 12 items

 Therefore, these factors can be used as variables for further analysis.

EFA steps NOTE: Other method

 Assignment (By Group)

 Do factor Analysis for (you will present in class)

2. Productive innovative success

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.