Spline Functions in Data Analysis.
Abstract
This paper discusses the approximation of non-exact data by smooth functions. It is shown that optimal approximations for a large class of criteria are spline functions, and that a sub-class of these are resistant to the presence of gross errors in the data. A computational procedure for obtaining the optimal splines is described and illustrated on a set of demographic data. A listing of an APL program implementing the procedure is included.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 01, 1974
- Accession Number
- ADA001128
Entities
People
- D. R. Mcneil
- P. Bloomfield
- R. S. Anderssen
Organizations
- Princeton University