Advanced search
Start date

Wavelet feature screening in high dimensional regression models

Grant number: 21/04513-9
Support type:Scholarships in Brazil - Post-Doctorate
Effective date (Start): June 01, 2021
Effective date (End): October 31, 2021
Field of knowledge:Physical Sciences and Mathematics - Probability and Statistics - Statistics
Principal researcher:Pedro Alberto Morettin
Grantee:Rodney Vasconcelos Fonseca
Home Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
Associated research grant:18/04654-9 - Time series, wavelets and high dimensional data, AP.TEM


The growing necessity of analyzing large data sets raises the problem of developing strategies to make statistical analyses in the age of Big Data. A very popular method in statistical analyses are regression models, technique used when explanatory variables are used to model some response variable of interest. When the number of explanatory variables is too large compared to sample size, researchers have employed different approaches to trying to identify which of these variables are relevant for the analysis under consideration, and the feature screening idea is an option to deal with such problem. An approach to make such screening is to evaluate correlations of the response variable with functions of covariates. The present project proposes to use wavelet methods to instruct the choice/estimation of such functions and establish the theoretical properties through properties of wavelet estimators. (AU)

News published in Agência FAPESP Newsletter about the scholarship:
Articles published in other media outlets (0 total):
More itemsLess items

Please report errors in scientific publications list by writing to: