Hello! I have data for a sample of 74 people who answered a 97-question assessment utilizing a likert scale. Looking at the data visually, we noticed a few responses that look like outliers/careless responses and we are considering removing them from the dataset. We want to do a formal outlier analysis to justify this. I read that Mahalanobis distance can be used to identify outliers but I don't know how to do it in SAS and with my variables. The 97-item assessment is broken up into subscales with items belonging to only one subscale. Would I calculate the means for each of the subscales and then use those values to calculate Mahalanobis' distance between the individual's mean on the subscales and the sample's means? What would the specific syntax be for this?
See "Mahalanobis distances" and "Outlier detection" in our list of Frequently Asked for Statistics (FASTats) at http://support.sas.com/kb/30333
Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 25. Read more here about why you should contribute and what is in it for you!
ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.
Find more tutorials on the SAS Users YouTube channel.