1

There are shape-preserving, preserving especially positivity, monotonicity or convexity, spline interpolations such as described here and here. Are there similar shape-preserving spline regression methods? I suppose I can modify the methodology prescribed in the interpolation papers to regression. However, it would be great if there are already existing methods in place. References would be most welcome.

Hans
  • 855
  • 4
  • 14
  • 1
    Certainly, some related posts: https://stats.stackexchange.com/questions/206073/looking-for-function-to-fit-sigmoid-like-curve/316446#316446, https://stats.stackexchange.com/questions/276487/interpreting-spline-results-from-scam, https://researchportal.bath.ac.uk/en/studentTheses/additive-models-with-shape-constraints – kjetil b halvorsen Dec 21 '19 at 01:52
  • 1
    @kjetilbhalvorsen: Excellent, especially the Ph.D. thesis in the last reference. Thank you. – Hans Dec 21 '19 at 03:49

0 Answers0