Abstract
Monte Carlo methods were employed to investigate the effect of nonnormality on the bias associated with the squared canonical correlation coefficient (Rc2). The majority of Rc2 estimates were found to be extremely biased, but the magnitude of bias was impacted little by the degree of nonnormality.
DOI
10.22237/jmasm/1398917220
Included in
Applied Statistics Commons, Social and Behavioral Sciences Commons, Statistical Theory Commons
