SPSS provides an easier option for dummy coding in the General Linear Model (GLM) function when compared to the regression menu.

I am just wondering what should I do to perform hierarchical regression in GLM?

Should I just choose Sum of Squares Type 1.

My analysis involves one dependent variable, one categorical variable (factor) and one continuous predictor (covariate).

I am interested in the main effect as well as any interaction.

Many thanks in advance for any assistance.


In response to the comment below, I propose to enter the following in the GLM window:

  1. Enter the continuous DV
  2. Enter the continuous IV as covariate
  3. Enter the categorical IV as factor
  4. Enter the product term (factor * covariate)
  5. Select Sum of Squares 1 because of unequal sample size for the factor

As stated above, my goal is to ascertain the main effect of the covariate on the DV, as well as the interaction between the covariate and factor on the DV.

  • 1
    $\begingroup$ "Hierarchical regression" is dubious phrase. You should write in more precise terms what is on your mind. Regression in blocks, sequential SS decomposition (type I SS), multilevel linear modeling or something else. $\endgroup$ – ttnphns Mar 12 '12 at 15:18
  • $\begingroup$ SPSS 13 Help files state: "Type I [Sum of Squares]. This method is also known as the hierarchical decomposition of the sum-of-squares method. Each term is adjusted for only the term that precedes it in the model. Type I sums of squares are commonly used for: A balanced ANOVA model in which any main effects are specified before any first-order interaction effects, any first-order interaction effects are specified before any second-order interaction effects, and so on [....]" $\endgroup$ – rolando2 Mar 13 '12 at 1:16
  • $\begingroup$ I can't tell if you're asking about the statistical procedure or how to get the software to implement it correctly. If it's the former, you may find the questions & answers here & here helpful. $\endgroup$ – gung - Reinstate Monica Mar 14 '12 at 16:39

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.