Variable selection and forecasting via automated methods for linear models: LASSO/adaLASSO and Autometrics
| Autor: | Dominique Guegan, Camila Epprecht, Alvaro Veiga, Joel Correa da Rosa |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Statistics and Probability
021103 operations research Estimation theory Model selection 0211 other engineering and technologies Linear model Feature selection 02 engineering and technology computer.software_genre 01 natural sciences Regularization (mathematics) 010104 statistics & probability Lasso (statistics) Modeling and Simulation Linear regression Statistics Data mining 0101 mathematics computer Selection (genetic algorithm) Mathematics |
| Zdroj: | Communications in Statistics - Simulation and Computation. 50:103-122 |
| ISSN: | 1532-4141 0361-0918 |
| DOI: | 10.1080/03610918.2018.1554104 |
| Popis: | In this paper we compare two approaches of model selection methods for linear regression models: classical approach - Autometrics (automatic general-to-specific selection) — and statistical learning - LASSO (l1-norm regularization) and adaLASSO (adaptive LASSO). In a simulation experiment, considering a simple setup with orthogonal candidate variables and independent data, we compare the performance of the methods concerning predictive power (out-of-sample forecast), selection of the correct model (variable selection) and parameter estimation. The case where the number of candidate variables exceeds the number of observation is considered as well. Finally, in an application using genomic data from a highthroughput experiment we compare the predictive power of the methods to predict epidermal thickness in psoriatic patients. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|