Canonical Analysis when Number of Variables is Large Relative to Sample Size

Sharon L. Weinberg and Richard B. Darlington

Journal of Educational and Behavioral Statistics, 1976, vol. 1, issue 4, 313-332

Abstract: Canonical Variate Analysis (CVA) has two major problems: sampling error and accumulated rounding error. This paper describes a method designed to minimize these problems. The combined effect of the two problems was assessed for CVA and the new technique in an empirical study. The new technique appears to be superior to CVA when the ratio of variables to sampling units is greater than 1/10.

Keywords: Canonical Variate Analysis; Sampling Error; Cross Validation (search for similar items in EconPapers)
Date: 1976
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.3102/10769986001004313 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:jedbes:v:1:y:1976:i:4:p:313-332

DOI: 10.3102/10769986001004313

Access Statistics for this article

More articles in Journal of Educational and Behavioral Statistics
Bibliographic data for series maintained by SAGE Publications ().