haku: @journal_id 53 / yhteensä: 379
viite: 136 / 379
| Tekijä: | Stone, E. F. Hollenbeck, J. R. |
| Otsikko: | Clarifying some controversial issues surrounding statistical procedures for detecting moderator variables: empirical evidence and related matters |
| Lehti: | Journal of Applied Behavioral Science
1989 : FEB, VOL. 74:1, p.3-10 |
| Asiasana: | PSYCHOLOGY STATISTICS |
| Kieli: | eng |
| Tiivistelmä: | Data used by Arnold to show the need for separate data analytic methods to evaluate form of relationship and related differences caused problems as nonhomogeneous variance and heteroscedasticity, making them improper for analysis with moderated regressions. Having applied variance-stabilizing transformations, the authors analyzed the same data by using moderated regression. The results obtained demonstrated that Arnold's results do not serve as a viable basis for this method. |
SCIMA