The purpose of this study was to explore the predictive potential of the information gathered on the Big Brother/Big Sister volunteer application blank for the prediction of successful (matched 12 or more months) and unsuccessful (matched six months or less) volunteers. Two alternate application blank weighting procedures (England's 1971 weighting scheme and multiple regression analysis) were used and the results of these procedures were compared. It was hypothesized that both procedures would correlate significantly with a tenure criterion. This hypothesis was supported, although the England (1971) procedure failed to cross-validate. Additionally, it was hypothesized that the multiple regression procedure would yield a shrunken r which is higher than the cross-validation estimate obtained using England's (1971) method. This hypothesis was not supported. A discussion of these results and recommendations for the use of this study is provided.
| Identifer | oai:union.ndltd.org:WKU/oai:digitalcommons.wku.edu:theses-3520 |
| Date | 01 May 1985 |
| Creators | Kuhn, Douglas |
| Publisher | TopSCHOLAR® |
| Source Sets | Western Kentucky University Theses |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | Masters Theses & Specialist Projects |
Page generated in 0.0019 seconds