# How to calculate regression with dummy variables?

54 views (last 30 days)
JFz on 17 Jul 2018
Edited: the cyclist on 17 Jul 2018
Hi, I am trying to use 2nd degree polynomial regression with dummy variables. Which function should I use? Thanks for any help!

the cyclist on 17 Jul 2018
Edited: the cyclist on 17 Jul 2018
If you have the Statistics and Machine Learning Toolbox, take a look at the fitlm function.
You might also find the dummyvar command useful for creating dummy variables.
Take a look at Regression with Categorical Covariates for an example.

JFz on 17 Jul 2018
Thanks! But fitlm is linear model. I need polynomial (2 degree or 3 degree). What function should I use? Should I use fitnlm or polyfit? Thanks again! Jennifer
the cyclist on 17 Jul 2018
Do you mean that you have polynomials for your independent variables, like
y = a + b*x + c*x^2
That is a linear model. "Linear" refers to the coefficients, not the powers (or whatever) of the variables.
On the other hand, something like
y = a + x^b
is nonlinear in the coefficient. Yes, you would need fitnlm for something like that.