4th order polynomial fit with two variables

[leonzheng]

I have a parameter (let's call it power) with x y coordinates. Now I need to do a 4th order polynomial fit for power, with x and y, equation should includes below terms:

x, y, x^2, x*y, y^2, x^3, x^2*y, x*y^2, y^3, x^4, x^3*y, x^2*y^2, x*y^3, y^4

Is there a function in SAS doing this? I saw some examples about doing polynomial prediction in SAS online, but they usually only fit y = f(x).

Thanks,

[PaigeMiller · Accepted solution]

PROC GLM will do this

You need to write x^2 as x*x and x*y^3 as x*y*y*y and so on

[leonzheng]

thanks, i got the predicted result and residual in result, how can I add them directly into the original table as two new column?

[leonzheng]

got it, thx