CalculatePAMixed: Parallel Analysis for numeric and ordered mixed data.

Description Usage Arguments Value Note Author(s) See Also Examples

View source: R/CalculatePAMixed.R

Description

Obtains a parallel analysis for numeric and ordered mixed data.

Usage

1
2
CalculatePAMixed(dataMatrix, percentiles = 0.99, nReplicates = 200,
                 use = "complete.obs", algorithm = "polycor")

Arguments

dataMatrix

matrix or data.frame of ordered variables.

percentiles

vector of percentiles to report.

nReplicates

number of simulations to produce for estimating the eigenvalues distribution under independence.

use

Missing values handling method: If "complete.obs", remove observations with any missing data; if "pairwise.complete.obs", compute each correlation using all observations with valid data for that pair of variables.

algorithm

string specifying the correlation estimation method. In the case of mixed variables, only the polycor package is currently used, so this value must always be "polycor".

Value

Returns a list object with the following:

observed

data.frame containing the observed eigenvalues.

percentiles

data.frame containing the estimated percentiles of the eigenvalues distribution under independence.

simulatedEigenValues

data.frame containing the simulated eigenvalues under independence.

Note

This is an auxiliary function for the "PA" function.

Author(s)

Carlos A. Arias [email protected] and Victor H. Cervantes [email protected]

See Also

CalculatePABinary, CalculatePAContinuous, CalculatePAOrdered, PA

Examples

1
2
3
4
5
6
# # NOT RUN
# # Run Parallel analysis of mixed ordered and continuous data
# data(mixedScience)
# mixedPA <- PA(mixedScience, percentiles = c(0.90, 0.99),
#               nReplicates = 200, type = "mixed")
# print(mixedPA)

pcaPA documentation built on May 29, 2017, 6:53 p.m.