I am running a generalized linear model: log-binomial regression (dist=bin, link=log)
Lets say I manually coded a linear piecewise spline knot, as age continuous and my binary outcome demonstrate a non-linear relationship with one shift in the curve (as visualized through PROC GAM)
The age continuous term has two separate betas, a ratio estimate before the spline knot (eg 1.5 per 1 year increase), and a separate ratio estimate after the spline knot (eg PR=0.9 per 1 year increase).
Say if I include a CLASS variable that has 2 levels, SAS is telling me that the ratios are static (the same) before and after the spline knot. Am I suppose to get the same ratios before and after a linear piecewise spline with one knot? Or am I suppose to expect separate ratios for the CLASS term after the spline knot?
Thanks
Lets say I manually coded a linear piecewise spline knot, as age continuous and my binary outcome demonstrate a non-linear relationship with one shift in the curve (as visualized through PROC GAM)
The age continuous term has two separate betas, a ratio estimate before the spline knot (eg 1.5 per 1 year increase), and a separate ratio estimate after the spline knot (eg PR=0.9 per 1 year increase).
Say if I include a CLASS variable that has 2 levels, SAS is telling me that the ratios are static (the same) before and after the spline knot. Am I suppose to get the same ratios before and after a linear piecewise spline with one knot? Or am I suppose to expect separate ratios for the CLASS term after the spline knot?
Thanks