P-splines with derivative based penalties and tensor product smoothing of unevenly distributed data

@article{Wood2017PsplinesWD,
  title={P-splines with derivative based penalties and tensor product smoothing of unevenly distributed data},
  author={Simon N. Wood},
  journal={Statistics and Computing},
  year={2017},
  volume={27},
  pages={985-989}
}
The P-splines of Eilers andMarx (Stat Sci 11:89– 121, 1996) combine aB-spline basis with a discrete quadratic penalty on the basis coefficients, to produce a reduced rank spline like smoother. P-splines have three properties that make them very popular as reduced rank smoothers: (i) the basis and the penalty are sparse, enabling efficient computation, especially for Bayesian stochastic simulation; (ii) it is possible to flexibly ‘mix-and-match’ the order of B-spline basis and penalty, rather… CONTINUE READING
Tweets
This paper has been referenced on Twitter 4 times. VIEW TWEETS

Figures from this paper.

Similar Papers

Loading similar papers…