1. Aim of the study
1.1. determine
1.2. extent
1.3. predicted by
2. what kind of analysis
2.1. Multiple hierarchical regression
2.1.1. predictors entered in order
2.2. Stepwise
3. Assumptions
3.1. Evidence of multicollinearity
3.1.1. Correlation between predictors / range
3.1.2. Cut-off 0.8
3.2. Inspection of collinearity diagnostics for the final model
3.3. Tolerance
3.3.1. Range
3.3.2. value of 0.2
3.4. VIF
3.4.1. range
3.4.2. cut-off 10
3.5. Collinearity diagnostics
3.5.1. eigenvectors
3.5.1.1. underlie the data????
3.5.1.2. measuring nymber of things?
3.5.1.3. provide assurance that multicollinearity is not a problem?
4. Analysis
4.1. 1. What predictors did not significantly predict the output
4.2. 2. What we did?
4.2.1. Stepwise
4.2.1.1. nothing
4.2.2. Hierarchical
4.2.2.1. We re-run the analysis, removing the non-significant predictors
4.2.2.1.1. one at a time
4.3. 3. In the final model
4.3.1. The output was significalty predicted By:
4.3.1.1. predictor 1
4.3.1.1.1. report
4.3.1.2. predictor 2
4.3.1.2.1. same...
4.3.1.3. and go on...
4.4. 4. Expalain each predictor's analysis
4.4.1. What does it mean?
4.4.1.1. example
4.5. 5. Finally
4.5.1. The final model was significant or not?
4.5.1.1. Report
4.5.1.1.1. F(df)=... (3 decinals)
4.5.1.1.2. p value
4.5.1.1.3. Italics
4.5.2. and
4.5.3. how much (percent) of the variance was explained in the output score?