Arbeitspapier
Boosting ridge regression
Ridge regression is a well established method to shrink regression parameters towards zero, thereby securing existence of estimates. The present paper investigates several approaches to combining ridge regression with boosting techniques. In the direct approach the ridge estimator is used to fit iteratively the current residuals yielding an alternative to the usual ridge estimator. In partial boosting only part of the regression parameters are reestimated within one step of the iterative procedure. The technique allows to distinguish between variables that are always included in the analysis and variables that are chosen only if relevant. The resulting procedure selects variables in a similar way as the Lasso, yielding a reduced set of influential variables. The suggested procedures are investigated within the classical framework of continuous response variables as well as in the case of generalized linear models. In a simulation study boosting procedures for different stopping criteria are investigated and the performance in terms of prediction and the identification of relevant variables is compared to several competitors as the Lasso and the more recently proposed elastic net. For the evaluation of the identification of relevant variables pseudo ROC curves are introduced.
- Sprache
-
Englisch
- Erschienen in
-
Series: Discussion Paper ; No. 418
- Thema
-
Ridge regression
boosting
Lasso
Pseudo ROC curves
- Ereignis
-
Geistige Schöpfung
- (wer)
-
Tutz, Gerhard
Binder, Harald
- Ereignis
-
Veröffentlichung
- (wer)
-
Ludwig-Maximilians-Universität München, Sonderforschungsbereich 386 - Statistische Analyse diskreter Strukturen
- (wo)
-
München
- (wann)
-
2005
- DOI
-
doi:10.5282/ubm/epub.1787
- Handle
- URN
-
urn:nbn:de:bvb:19-epub-1787-5
- Letzte Aktualisierung
-
10.03.2025, 11:42 MEZ
Datenpartner
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Objekttyp
- Arbeitspapier
Beteiligte
- Tutz, Gerhard
- Binder, Harald
- Ludwig-Maximilians-Universität München, Sonderforschungsbereich 386 - Statistische Analyse diskreter Strukturen
Entstanden
- 2005
Ähnliche Objekte (12)
Modelling Issues in Kernel Ridge Regression
Nonlinear Forecasting with Many Predictors using Kernel Ridge Regression
Difference based ridge and Liu type estimators in semiparametric regression models
Boosting ridge for the extreme learning machine globally optimised for classification and regression problems
Boosting Classifiers for Drifting Concepts
Bagging, boosting and ensemble methods
Knot selection by boosting techniques
Efficient Generalized Ridge Regression
Boosting functional regression models
Boosting distributional copula regression
Comparing Knowledge-Based Sampling to Boosting
Boosting carry with equilibrium exchange rate estimates
Modelling Issues in Kernel Ridge Regression
Nonlinear Forecasting with Many Predictors using Kernel Ridge Regression
Difference based ridge and Liu type estimators in semiparametric regression models
Boosting ridge for the extreme learning machine globally optimised for classification and regression problems
Boosting Classifiers for Drifting Concepts
Bagging, boosting and ensemble methods
Knot selection by boosting techniques
Efficient Generalized Ridge Regression
Boosting functional regression models
Boosting distributional copula regression
Comparing Knowledge-Based Sampling to Boosting
Boosting carry with equilibrium exchange rate estimates
Modelling Issues in Kernel Ridge Regression
Nonlinear Forecasting with Many Predictors using Kernel Ridge Regression
Difference based ridge and Liu type estimators in semiparametric regression models
Boosting ridge for the extreme learning machine globally optimised for classification and regression problems
Boosting Classifiers for Drifting Concepts
Bagging, boosting and ensemble methods
Knot selection by boosting techniques
Efficient Generalized Ridge Regression
Boosting functional regression models
Boosting distributional copula regression
Comparing Knowledge-Based Sampling to Boosting