Bagging of density estimators
In this work we give new density estimators by averaging classical density estimators such as the histogram, the frequency polygon and the kernel density estimators obtained over different bootstrap samples of the original data. Using existent results, we prove the \(L^2\)-consistency of these new estimators and compare them to several similar approaches by simulations. Based on them, we give also a way to construct non-parametric pointwise variability band for the target density.
KeywordsAggregation Bagging Density estimation Histogram Kernel density estimator Polygon frequency
We would like to thank project ECOS-2014 Aprendizaje Automático para la Modelización y el Análisis de Recursos Naturales, no. U14E02, the LIA-IFUM and the ANII-Uruguay for their financial support.
- Fisher R (1932) Statistical methods for research workers. Biological monographs and manuals. Oliver and Boyd, New YorkGoogle Scholar
- Hall P (1997) The bootstrap and Edgeworth expansion. Springer series in statistics. Springer, New YorkGoogle Scholar
- R Core Team (2018) R: a language and environment for statistical computing. R Foundation for Statistical Computing, ViennaGoogle Scholar
- Rosset S, Segal E (2002) Boosting density estimation. In: Advances in neural information processing systems (NIPS), pp 641–648Google Scholar
- Scott D (2015) Multivariate density estimation: theory, practice, and visualization. Wiley series in probability and statistics. Wiley, HobokenGoogle Scholar