Autor: |
Busk, Patricia L., Marascuilo, Leonard A. |
Zdroj: |
Australian Journal of Education; November 1989, Vol. 33 Issue: 3 p220-241, 22p |
Abstrakt: |
In recent years, the loglinear model has been proposed and used for analysing frequency data in multidimensional contingency tables. The primary focus of the literature has been on model building and only secondarily on hypothesis testing and estimation. This paper extends Kennedy's (1988) description by presenting post hoc procedures for statistically evaluating treatment effects, contrasts, and confidence intervals. It illustrates methods for main effect and interaction contrasts and pays special attention to odds ratios and their interval estimates. Procedures are described for treating the variables as interdependent and for the case where there are independent and dependent variables—both ordered and unordered. |
Databáze: |
Supplemental Index |
Externí odkaz: |
|