2000
DOI: 10.3758/bf03200807
|View full text |Cite
|
Sign up to set email alerts
|

SPSS and SAS programs for determining the number of components using parallel analysis and Velicer’s MAP test

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

22
2,200
2
81

Year Published

2009
2009
2018
2018

Publication Types

Select...
7
3

Relationship

0
10

Authors

Journals

citations
Cited by 3,414 publications
(2,305 citation statements)
references
References 23 publications
22
2,200
2
81
Order By: Relevance
“…We conducted a series of exploratory factor analyses (EFA), and determined the optimum number of factors that should be extracted via a parallel analysis. Parallel analysis compares the observed eigenvalues with eigenvalues of randomly drawn data, and we extracted factors for which the eigenvalues exceeded the randomly generated eigenvalues (O'Connor, 2000). We generated 50 parallel datasets for each analysis, and used 95% eigenvalue percentiles 1 .…”
Section: Resultsmentioning
confidence: 99%
“…We conducted a series of exploratory factor analyses (EFA), and determined the optimum number of factors that should be extracted via a parallel analysis. Parallel analysis compares the observed eigenvalues with eigenvalues of randomly drawn data, and we extracted factors for which the eigenvalues exceeded the randomly generated eigenvalues (O'Connor, 2000). We generated 50 parallel datasets for each analysis, and used 95% eigenvalue percentiles 1 .…”
Section: Resultsmentioning
confidence: 99%
“…Because the model failed to fit, we then used principal components analysis using direct oblimin oblique rotation to explore the factor patterns in the MAND raw scores at each survey year. Factors were retained based on eigenvalues of more than one, an examination of the scree plots and then confirmed using parallel analysis (O'Connor, 2000). Factor loadings of .3 or more were considered when interpreting factors.…”
Section: Resultsmentioning
confidence: 99%
“…The number of observed eigenvalues exceeding the 95 th percentile of simulated eigenvalues is taken as the appropriate number of factors to extract. To conduct the parallel analyses, we used procedures developed by O'Connor (2000) and ran 5000 simulations of sets of random data with 160 cases and 48 variables. Only the top three eigenvalues from our factor analysis were greater than the 95 th percentile of the eigenvalues from the random simulation, suggesting that three factors be extracted.…”
Section: Factor Structure Of Disgust Sensitivitymentioning
confidence: 99%