ERIC Number: ED343914
Record Type: Non-Journal
Publication Date: 1992-Jan
Reference Count: N/A
Investigating Result Stability of Canonical Function Equations with the Jackknife Technique.
Tucker, Mary L.; Daniel, Larry G., Jr.
The jackknife statistic is discussed as a viable invariance procedure. Data from a study of leadership illustrates the use of the jackknife in determining the stability of canonical function coefficients following canonical correlation analysis. The jackknife procedure entails arbitrarily omitting one observation or a subset of observations at a time from the original sample and recalculating the original statistical estimator for each of the resulting truncated data sets. The procedure is repeated with each individual observation or unique subgroup omitted. Pseudovalues are computed for each of the truncated data sets, based on the computation of the original and the sample-minus-one subset function coefficients. These pseudovalues are then averaged, providing a jackknifed estimate of the canonical function coefficients. The stability of the original values is gauged by determining whether they fall within confidence intervals for the jackknifed values. The sample illustrating the jackknife statistic is taken from a study by M. L. Tucker of leadership styles with data from 106 college faculty and administrators who rated their supervisors. Because the jackknife technique minimizes sample splitting through sample omission and reuse, it is particularly useful when the sample size is small. There is a 10-item list of references and one table with analysis results. (SLD)
Publication Type: Reports - Evaluative; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A