r2cov: Convert correlation matrix into covariance matrix

In rpsychi: Statistics for psychiatric research

Description

r2cov converts correlation matrix and sample/unbiased standard deviation into sample/unbiased covariance matrix.

Usage

 r2cov(sd, R) 

Arguments

sd	a numeric vector contains the sample/unbiased standard deviations
R	a matrix or data frame contains the correlation matrix

Details

This function converts correlation matrix and sample/unbiased standard deviation into sample/unbiased covariance matrix using the following equation: S = D^{1/2} R D^{1/2}, where S is a sample/unbiased covariance matrix, R is a correlation matrix, and D^{1/2} is a square matrix with sd on the main diagonal and 0's elsewhere. The length of sd should be equal to the number of rows and columns in R.

Value

Return a matrix containing the sample/unbiased covariance matrix.

Author(s)

Yasuyuki Okumura
Department of Social Psychiatry,
National Institute of Mental Health,
National Center of Neurology and Psychiatry
[e-mail]

References

Toyoda H (1998) Introduction to structural equation modeling (in Japanese) Tokyo: Asakura Publishing.

See Also

svar, ssd, svar, ssd2sd, lower2R

Examples

 
##data(iris) 
x <- iris[,1:4] 
cov(x)
r2cov(apply(x, 2, sd), cor(x)) 


##Toyoda (1998) p.34 
r2cov(sd = sqrt(c(.862, 1.089, 0.606)), 
      R = lower2R(c(.505, -0.077, -.233)))

rpsychi documentation built on May 1, 2019, 10:10 p.m.