hierarchical regression

steps

variables that are entered into a regression model together

• step 1 eg demographic factors

• step 2 eg psychological factors

why are variables entered in different steps

to control for the effects of different factors - by controlling for factors in step 1, we can see how much variance in the outcome is due to these factors

• can be used to measure how much variance in the outcome is due to confounding variables

R2 change

used to compare variance between steps, to see which steps account for the most variance

• must be reported in model fit

assumptions of hierarchical regressions

• linear relationship between the independent variables (predictors) and dependent variable (outcome)

• normal distribution of residuals

• homogeneity of variance