Brooks, Stephen P. (1994) Diagnostics For Principal Components - Influence Functions As Diagnostic-Tools. Statistician, 43 (4). pp. 483-494. ISSN 0039-0526. (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided)
Care should be taken when interpreting the results of a principal components analysis. As an aid to interpretation and as a guide to reliability, a range of diagnostic tools have been proposed. This paper introduces and reviews recent work on influence functions, as well as introducing new methodology, and highlights their use as diagnostic tools for principal components analysis. A Monte Carlo approach is used to assess significance for the influence values obtained.
|Subjects:||H Social Sciences > HA Statistics|
|Divisions:||Faculties > Science Technology and Medical Studies > School of Mathematics Statistics and Actuarial Science > Statistics|
|Depositing User:||P. Ogbuji|
|Date Deposited:||04 Jul 2009 07:20|
|Last Modified:||18 Jun 2014 09:52|
|Resource URI:||https://kar.kent.ac.uk/id/eprint/20404 (The current URI for this page, for reference purposes)|