Adaptive estimation in the nonparametric random coefficients binary choice model by needlet thresholding

Abstract : In the random coefficients binary choice model, a binary variable equals 1 iff an index $X^\top\beta$ is positive. The vectors $X$ and $\beta$ are independent and belong to the sphere $\mathbb{S}^{d-1}$ in $\mathbb{R}^{d}$. We prove lower bounds on the minimax risk for estimation of the density $f_{\beta}$ over Besov bodies where the loss is a power of the $L^p(\mathbb{S}^{d-1})$ norm for $1\le p\le \infty$. We show that a hard thresholding estimator based on a needlet expansion with data-driven thresholds achieves these lower bounds up to logarithmic factors.
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download

https://hal.inria.fr/inria-00601274
Contributor : Erwan Le Pennec <>
Submitted on : Tuesday, November 28, 2017 - 11:56:02 AM
Last modification on : Wednesday, December 4, 2019 - 1:34:07 PM

Files

inverse.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution - NoDerivatives 4.0 International License

Identifiers

  • HAL Id : inria-00601274, version 4
  • ARXIV : 1106.3503

Citation

Eric Gautier, Erwan Le Pennec. Adaptive estimation in the nonparametric random coefficients binary choice model by needlet thresholding. 2017. ⟨inria-00601274v4⟩

Share

Metrics

Record views

256

Files downloads

549