Results 11 to 20 of about 674 (121)

Boosting Ridge Regression [PDF]

, 2005
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.
Binder, Harald, Tutz, Gerhard
core   +1 more source

Ordinal Ridge Regression with Categorical Predictors [PDF]

, 2011
In multi-category response models categories are often ordered. In case of ordinal response models, the usual likelihood approach becomes unstable with ill-conditioned predictor space or when the number of parameters to be estimated is large relative to ...
Zahid, Faisal Maqbool
core   +1 more source

Pairwise Fused Lasso [PDF]

, 2011
In the last decade several estimators have been proposed that enforce the grouping property. A regularized estimate exhibits the grouping property if it selects groups of highly correlated predictor rather than selecting one representative.
Petry, Sebastian, Tutz, Gerhard, Flexeder, Claudia   +2 more
core   +1 more source

Feature Selection Guided by Structural Information [PDF]

, 2009
In generalized linear regression problems with an abundant number of features, lasso-type regularization which imposes an l1-constraint on the regression coefficients has become a widely established technique.
Wolfgang zu Castell, Gerhard Tutz, Tutz, Gerhard, zu Castell, W., Slawski, Martin, Tutz, G., Castell, Wolfgang zu, Slawski, M., Martin Slawski, zu Castell, Wolfgang   +9 more
core   +1 more source

A Comparative Study of Ridge, LASSO and Elastic net Estimators

, 2021
The focus of this thesis is to review the three basic penalty estimators, namely, ridge regression estimator, LASSO, and elastic net estimator in the light of the deficiencies of least-squares estimator.
Al Dabal, Meaad Abdullah A.
core   +1 more source

Direct effects testing : a two-stage procedure to test for effect size and variable importance for correlated binary predictors and a binary response. [PDF]

, 2010
In applications such as medical statistics and genetics, we encounter situations where a large number of highly correlated predictors explain a response.
Sperrin, M.; id_orcid, Sperrin, Matthew, Jaki, T., Jaki, Thomas, T. Jaki, M. Sperrin   +5 more
core   +1 more source

Boosting Correlation Based Penalization in Generalized Linear Models [PDF]

, 2007
In high dimensional regression problems penalization techniques are a useful tool for estimation and variable selection. We propose a novel penalization technique that aims at the grouping effect which encourages strongly correlated predictors to be in ...
Tutz, Gerhard, Ulbricht, Jan
core   +1 more source

A Penalty Approach to Differential Item Functioning in Rasch Models [PDF]

, 2012
A new diagnostic tool for the identification of differential item functioning (DIF) is proposed. Classical approaches to DIF allow to consider only few subpopulations like ethnic groups when investigating if the solution of items depends on the ...
Tutz, Gerhard, Schauberger, Gunther
core   +1 more source

Knot selection by boosting techniques [PDF]

, 2006
A novel concept for estimating smooth functions by selection techniques based on boosting is developed. It is suggested to put radial basis functions with different spreads at each knot and to do selection and estimation simultaneously by a componentwise
Gerhard Tutz, Leitenstorfer, Florian, Tutz, Gerhard, Florian Leitenstorfer   +3 more
core   +1 more source

The Effect of Outlier on Lasso Estimators and Regressions

, 2021
Lasso regression (Least Absolute Shrinkage and Selection Operator) dependent on reducing shrinkage. This kind regression deals with cases in which the explained variables have a multicollinearity problem between them and in models include a large number ...
et. al., Layla M. Nassir,
core   +1 more source