Loading...
Please wait, while we are loading the content...
Similar Documents
Knot selection for regression splines via the lasso (1998).
| Content Provider | CiteSeerX |
|---|---|
| Author | Osborne, M. R. Presnell, B. Turlach, B. A. |
| Abstract | : Tibshirani (1996) proposes the "Least Absolute Shrinkage and Selection Operator" (lasso) as a method for regression estimation which combines features of shrinkage and variable selection. In this paper we present an algorithm that allows efficient calculation of the lasso estimator. In particular our algorithm can also be used when the number of variables exceeds the number of observations. This algorithm is then applied to the problem of knot selection for regression splines. 1 Introduction The performance of regression spline smoothing is governed by the choice of knots used in calculating the estimator, and much research effort has been devoted to the difficult problem of knot selection (see, e.g., Wand, 1997; Denison et al., 1998). Knot selection is not unlike variable selection in linear regression, for which Tibshirani (1996) proposes the least absolute shrinkage and selection operator. The lasso estimator is the solution of the constrained estimation problem minimise fi2R ... |
| File Format | |
| Publisher Date | 1998-01-01 |
| Access Restriction | Open |
| Subject Keyword | Knot Selection Regression Spline Variable Selection Selection Operator Lasso Estimator Efficient Calculation Least Absolute Shrinkage Much Research Effort Linear Regression Regression Estimation Constrained Estimation Problem Minimise Fi2r Regression Spline Smoothing Absolute Shrinkage Difficult Problem |
| Content Type | Text |
| Resource Type | Article |
