Abstract
AbstractMost classical multivariate procedures (e.g., multivariate analysis of variance, multivariate measures of effect size, classification procedures, maximum likelihood factor analysis) require that the data follow a multivariate normal density function. Behavioral science researchers risk committing many more Type I errors, quantifying inaccurately the magnitude of effect sizes, missing treatment effects, establishing inaccurate confidence intervals, and so on by failing to consider whether their data conform to multivariate normality. This paper discusses a number of options for assessing and dealing with nonnormal multivariate data including: (a) testing for univariate normality among thepmeasures, (b) transforming the data to achieve normality, (c) univariate normal probability plots, (d) multivariate measures of skewness and kurtosis, (e) computing squared distance statistics to locate outlying values, and (f) adopting robust estimators with robust test statistics to circumvent the biasing effects of nonnormality.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
