Adaptive non-asymptotic confidence balls in density estimation
Matthieu Lerasle (2012)
ESAIM: Probability and Statistics
Similarity:
We build confidence balls for the common density of a real valued sample . We use resampling methods to estimate the projection of onto finite dimensional linear spaces and a model selection procedure to choose an optimal approximation space. The covering property is ensured for all ≥ 2 and the balls are adaptive over a collection of linear spaces.