Can I use boolean parameters in LogitModelFit?

Question

For example, to use 1 as True and 0 as False:

LogitModelFit[{{300, 0, 0}, {400, 0, 0}, {450, 1, 0}, {460, 1, 1}}, {x, y}, {x, y}]

where y is boolean parameter.

Answer 1

You can check the documentation about the option NominalVariables

http://reference.wolfram.com/language/ref/NominalVariables.html

NominalVariables is an option for machine learning functions such as LinearModelFit or Classify that specifies which variables should be treated as having discrete values specified by names.

So

LogitModelFit[{{300, 0, 0}, {400, 0, 0}, {450, 1, 0}, {460, 1, 1}}, {x, y}, {x, y},
  NominalVariables -> y ]

shoud do the job.

You ae not required to use 0 and 1 for your binary variables, you can use more meaningful symbol and strings, like True/False or "Male"/"Female", and so on.