BinNonNor (version 1.5.3)

correlation.limits: Computes lower and upper correlation bounds for each pair of variables

Description

This function computes lower and upper limits for pairwise correlation of binary-binary, binary-continuous non-normal, and continuous non-normal-continuous non-normal combinations.

Usage

correlation.limits(n.BB, n.NN, prop.vec = NULL, coef.mat = NULL)

Arguments

n.BB

Number of binar variables.

n.NN

Number of continuous non-normal variables.

prop.vec

Probability vector for binary variables.

coef.mat

Matrix of coefficients produced from fleishman.coef.

Value

The function returns a matrix of size (n.BB + n.NN)*(n.BB + n.NN), where the lower triangular part of the matrix contains the lower bounds and the upper triangular part of the matrix contains the upper bounds of the feasible correlations.

Details

While the function computes the exact lower and upper bounds for pairwise correlations among binary-binary variables as formulated in Demirtas et al. (2012), it computes approximate lower and upper bounds for pairwise correlations among binary-continuous non-normal and continuous non-normal-continuous non-normal variables through the method suggested by Demirtas and Hedeker (2011).

References

Demirtas, H. and Hedeker, D. (2011). A practical way for computing approximate lower and upper correlation bounds. The American Statistician, 65(2), 104-109.

Demirtas, H., Hedeker, D., and Mermelstein, R.J. (2012). Simulation of massive public health data by power polynomials. Statistics in Medicine, 31(27), 3337-3346.

See Also

fleishman.coef, correlation.bound.check

Examples

# NOT RUN {
n.BB=2
n.NN=4
prop.vec=c(0.4,0.7)
coef.mat=matrix(c(
 -0.31375,  0.00000,  0.10045, -0.10448,
  0.82632,  1.08574,  1.10502,  0.98085,
  0.31375,  0.00000, -0.10045,  0.10448,
  0.02271, -0.02945, -0.04001,  0.00272),4,byrow=TRUE)

limits=correlation.limits(n.BB,n.NN,prop.vec,coef.mat)
limits.bin=correlation.limits(n.BB,n.NN=0,prop.vec,coef.mat=NULL)
limits.nonnor=correlation.limits(n.BB=0,n.NN,prop.vec=NULL,coef.mat)

# }
# NOT RUN {
n.BB=1
prop.vec=0.5
limits=correlation.limits(n.BB,n.NN,prop.vec,coef.mat=NULL)
# }