hw: Height-Weight Covariance Study

In ACSWR: A Companion Package for the Book "A Course in Statistics with R"

Description

The data set highlights the importance of handling covariance when such information is available. If the covariance is not incorporated, hypothesis testing may lead to entirely difference conclusion.

Usage

data(hw)

Format

A data frame with 20 observations on the following 2 variables.

Height

the height of an individual

Weight

the weight of an individual

References

Rencher, A.C. (2002). Methods of Multivariate Analysis, 2e. J. Wiley.

Examples

data(hw)
sigma0 <- matrix(c(20, 100, 100, 1000),nrow=2)
sigma <- var(hw)
v <- nrow(hw)-1
p <- ncol(hw)
u <- v*(log(det(sigma0))-log(det(sigma)) + sum(diag(sigma%*%solve(sigma0)))-p)
u1 <- (1- (1/(6*v-1))*(2*p+1 - 2/(p+1)))*u
u;u1;qchisq(1-0.05,p*(p+1)/2)

Example output

[1] 11.09374
[1] 10.66832
[1] 7.814728

ACSWR documentation built on May 2, 2019, 6:53 a.m.