buildSSCP: build the sum of squares and cross products matrix

In MIIVsem: Model Implied Instrumental Variable (MIIV) Estimation of Structural Equation Models

Description

Build sum of squares and crossproducts matrix (SSCP). From the means, covariances, and n's you can recover the raw sum-of-squares and products matrix for all the variables. Say the matrix of all the variables is X, with mean vector bar(x), and covariance matrix S, based on sample-size n. Then the SSCP matrix is X'X = (n - 1)S + n bar(x) bar(x)'. You then need to add the row/column for the constant, which is just n in the 1, 1 position and n bar(x) elsewhere.

Usage

buildSSCP(sample.cov, sample.mean, sample.nobs)

Arguments

sample.cov	Numeric matrix. A sample variance-covariance matrix. The rownames and colnames must contain the observed variable names.
sample.mean	A sample mean vector.
sample.nobs	Number of observations in the full data frame.

MIIVsem documentation built on July 13, 2021, 5:08 p.m.