Learn R Programming

multicon (version 1.6)

horn: Horn's Parallel Analysis

Description

Conduct's Horn's (1965) parallel analysis for determining the number of principal components

Usage

horn(set, sims = 100, nomiss = 1, graph = TRUE)

Arguments

set
A data.frame containing the variables to be analyzed
sims
A numeric indicating the number simulated data sets to use
nomiss
A numeric from 0 to 1.00 indicating the percentage of data that must be valid (non-missing) for each case for it to be included in the analysis.
graph
A logical indicating whether the results should be displayed graphically or not

Value

Prints the number of components suggested and the number of cases deleted due to missingness. If graph=T a Scree Plot is graphed.

Details

Horn's (1965) method of determining the number of factors to extract uses bootstrap style resampling of the original data matrix to create a sample data matrix. The eigenvalues for this data matrix are then computed and stored. This process is repeated "sims" times and the average of the resulting eigenvalues is taken to indicate the vector of eigenvalues that would be expected by random data. Horn suggested that one should extract as many factors as have eigenvalues greater than the eigenvalues expected by random data.

References

Horn, J. (1965) A rationale and test for the number of factors in factor analysis. Psychometrika, 30, 179-185.

See Also

fa.parallel

Examples

Run this code
data(bfi.set)	# the Big Five Personality Inventory 
horn(bfi.set) #now we can see how many components are suggested

Run the code above in your browser using DataLab