I'm using Mathematica for a project, in which I would like to fit a multiple linear regression model to my data (which is made up of both numerical and categorical variables).
I have been trying to use the function LinearModelFit to do this, but I have had no luck. Based on the MMA documentation available, the examples they've given only use simple numerical data such as {{0, 1}, {1, 0}, {3, 2}, {5, 4}}. In my case, I have 3 numerical variables, 4 categorical variables and my response variable, so I haven't been able to achieve this with LinearModelFit.
I then tried to use Predict[list1 -> list 2, Method->"LinearRegression"], with all my variable inputs in a list which I inserted in place of list1, and then my list of response variable values in a list which I inserted in place of list 2. This resulted in an error "Incompatible variable type (!("Numerical")) and variable value".
I'm wondering does anyone know if there is a different function I should be using or if I'm perhaps not using the 2 functions mentioned above correctly?
Thanks.
