Robust principal component analysis in Stata
When some observations are outlying (in one or several dimensions) PCA is distorted an may lead to incorrect results. We therefore propose a simple solution to deal with this problem by providing a short ado file. To illustrate the importance of outliers in PCA I would like to present a simple analysis identifying the underlying factors of academic excellence calling both the classical PCA and the robust PCA and relying on the rankings of Universities.
|Date of creation:||16 Sep 2009|
|Date of revision:|
|Contact details of provider:|| Web page: http://www.stata.com/meeting/uk09|
More information through EDIRC
When requesting a correction, please mention this item's handle: RePEc:boc:usug09:02. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Christopher F Baum)
If references are entirely missing, you can add them using this form.