I'm planning on running a hierarchical multiple regression in SPSS. In the first step, I would like to enter demographic characteristics, second step continuous predictor variables of interest, and third step interactions between the continuous predictor variables. However, the issue I've run into is that some of the demographic variables are more than two levels and either nominal (e.g., education level: less than BA, BA, graduate degree) or ordinal (e.g., age: 20-30, 31-40, 41-50, 51+). My dependent variable is continuous.
My question is: can I dummy code the nominal/ordinal variables and then run the multiple regression as I normally would? Or, would you recommend handling the data differently? I'm a bit rusty on SPSS, so I appreciate any help/input. Thanks!
The most flexible thing you can do is assign binary variables for each individual category and include them all in your model. For example, let $Age_1 = 1$ if age was between 20-30 and $0$ otherwise. Let $Age_2 = 1$ if age was between 31-40 and $0$ otherwise..., etc. The cost of this approach is that it significantly increases the number of parameters you wish to estimate.
At the other end, you can simply code up the existing variables as a variables that ranges from, for example 1-4 where 1 corresponds to ages 21-30, 2 corresponds to ages 31-40 and so forth. This is a crude method, but it is a proxy of age (or education).
There is no right or wrong answer and these are far from the only 2 methods. Any combination would also work. If you have a large sample and computation time is not a concern I would go with method 1.