How can I prove that the cubic regression spline y_i = α + K+4∑k=2 β_kh_k(x_i) + e_i is continuous in the first and second derivative at the knots? I understand how to prove the property by expanding the equation for f(x)=β0+β1x+β2x2+β3x3+β4(x−ξ)3+ which is explained here:https://rstudio-pubs-static.s3.amazonaws.com/65563_d6411480e07b4aaaad9b484b66210497.html, but how can I extend the proof to K knots?
Asked
Active
Viewed 125 times
1
-
2I’m voting to close this question because it is not about programming. – VLL Feb 10 '22 at 07:58
-
Ask here https://math.stackexchange.com/ – palloc Mar 15 '22 at 10:17