Projection Pursuit Regression Pdf. Stuetzle journalJournal of the American Statistical Association year1981 volume76 pages817-823 Abstract A new method for nonparametric multiple regression is presented. Cleveland A tree-structured approach to nonparametric multiple regression.
One such method-projection pursuit regression Friedman and Stuetzle 1981 PPR-is capable of performing dimen- sionality reduction by composition namely it constructs an approxima- tion to the desired response function using a composition of lower dimen- sional smooth functions. PPR on the other hand is rooted on the expansion of fx as a sum of non-linear functions of unidimensional. The estimate is a sum of smoothed one-dimensional projections of.
Linear and projection pursuit regression Linear regression method L assumes fx in 1 to be a linear function ie.
HumboldtUniversitt zu Berlin Berlin Germany. Search for more papers by this author. In this work we will consider three methods. Unlimited viewing of the articlechapter PDF and any associated supplements and figures.
