| dc.contributor.author | Schey, Harry | en_US |
| dc.date.accessioned | 2007-10-10T21:09:07Z | en_US |
| dc.date.available | 2007-10-10T21:09:07Z | en_US |
| dc.date.issued | 1993-02 | en_US |
| dc.identifier.citation | The American Statistician 47N1 (1993) 26-30 | en_US |
| dc.identifier.issn | 0003-1305 | en_US |
| dc.identifier.uri | http://hdl.handle.net/1850/5069 | en_US |
| dc.description | Only the abstract is included in the file associated with this article. The complete article may be accessed from the publisher's website (additional fees may apply) at: http://links.jstor.org/sici?sici=0003-1305(199302)47%3A1%3C26%3ATRBTMO%3E2.0.CO%3B2-K | en_US |
| dc.description.abstract | We use geometric methods to investigate the relative magnitudes of SSR(x(2)), the sum of squares for regression on x(2) alone, and SSR(x(2)|x(1)), the increase in the regression sum of squares resulting from the addition of x(2) to a model that already contains x(1). We examine a variety of cases, emphasizing those in which SSR(x(2)|x(1)) > SSR(x(2)). We also point out that SSR(x(2)) and SSR(x(2)|x(1)) can be equal even when x(1) and x(2) are correlated. We present contrived data sets illustrating these points, and examine the relative magnitudes of SSR(x(2)) and SSR(x(2)|x(1)) for two real data sets (Refer to PDF file for exact formulas). | en_US |
| dc.language.iso | en_US | en_US |
| dc.publisher | American Statistical Association | en_US |
| dc.relation.ispartofseries | vol. 47 | en_US |
| dc.relation.ispartofseries | no.1 | en_US |
| dc.subject | Correlation | en_US |
| dc.subject | Geometry | en_US |
| dc.subject | Multiple regression | en_US |
| dc.subject | Suppression | en_US |
| dc.subject | Suppressor variable | en_US |
| dc.title | The Relationship between the magnitudes of SSR(X(2)) and SSR(X(2)|X(1)): a geometric description | en_US |
| dc.type | Abstract | en_US |
