Adaptive non-asymptotic confidence balls in density estimation

Matthieu Lerasle

ESAIM: Probability and Statistics (2012)

  • Volume: 16, page 61-85
  • ISSN: 1292-8100

Abstract

top
We build confidence balls for the common density s of a real valued sample X1,...,Xn. We use resampling methods to estimate the projection of s onto finite dimensional linear spaces and a model selection procedure to choose an optimal approximation space. The covering property is ensured for all n ≥ 2 and the balls are adaptive over a collection of linear spaces.

How to cite

top

Lerasle, Matthieu. "Adaptive non-asymptotic confidence balls in density estimation." ESAIM: Probability and Statistics 16 (2012): 61-85. <http://eudml.org/doc/222474>.

@article{Lerasle2012,
abstract = {We build confidence balls for the common density s of a real valued sample X1,...,Xn. We use resampling methods to estimate the projection of s onto finite dimensional linear spaces and a model selection procedure to choose an optimal approximation space. The covering property is ensured for all n ≥ 2 and the balls are adaptive over a collection of linear spaces.},
author = {Lerasle, Matthieu},
journal = {ESAIM: Probability and Statistics},
keywords = {Confidence balls; density estimation; resampling methods; confidence balls},
language = {eng},
month = {7},
pages = {61-85},
publisher = {EDP Sciences},
title = {Adaptive non-asymptotic confidence balls in density estimation},
url = {http://eudml.org/doc/222474},
volume = {16},
year = {2012},
}

TY - JOUR
AU - Lerasle, Matthieu
TI - Adaptive non-asymptotic confidence balls in density estimation
JO - ESAIM: Probability and Statistics
DA - 2012/7//
PB - EDP Sciences
VL - 16
SP - 61
EP - 85
AB - We build confidence balls for the common density s of a real valued sample X1,...,Xn. We use resampling methods to estimate the projection of s onto finite dimensional linear spaces and a model selection procedure to choose an optimal approximation space. The covering property is ensured for all n ≥ 2 and the balls are adaptive over a collection of linear spaces.
LA - eng
KW - Confidence balls; density estimation; resampling methods; confidence balls
UR - http://eudml.org/doc/222474
ER -

References

top
  1. S. Arlot, Model selection by resampling penalization. Electron. J. Statist.3 (2009) 557–624.  
  2. S. Arlot and P. Massart, Data-driven calibration of penalties for least-squares regression. J. Mach. Learn. Res.10 (2009) 245–279.  
  3. S. Arlot, G. Blanchard and E. Roquain, Resampling-based confidence regions and multiple tests for a correlated random vector, in Learning theory. Lect. Notes Comput. Sci.4539 (2007) 127–141.  
  4. Y. Baraud, Confidence balls in Gaussian regression. Ann. Statist.32 (2004) 528–551.  
  5. R. Beran, REACT scatterplot smoothers : superefficiency through basis economy. J. Amer. Statist. Assoc.95 (2000) 155–171.  
  6. R. Beran and L. Dümbgen, Modulation of estimators and confidence sets. Ann. Statist.26 (1998) 1826–1856.  
  7. L. Birgé and P. Massart, From model selection to adaptive estimation, in Festschrift for Lucien Le Cam. Springer, New York (1997) 55–87.  
  8. L. Birgé and P. Massart, Minimal penalties for Gaussian model selection. Probab. Theory Relat. Fields138 (2007) 33–73.  
  9. T. Cai and M.G. Low, Adaptive confidence balls. Ann. Statist.34 (2006) 202–228.  
  10. B. Efron, Bootstrap methods : another look at the jackknife. Ann. Statist.7 (1979) 1–26.  
  11. M. Fromont and B. Laurent, Adaptive goodness-of-fit tests in a density model. Ann. Statist.34 (2006) 680–720.  
  12. C.R. Genovese and L. Wasserman, Confidence sets for nonparametric wavelet regression. Ann. Statist.33 (2005) 698–729.  
  13. C. Genovese and L. Wasserman, Adaptive confidence bands. Ann. Statist.36 (2008) 875–905.  
  14. M. Hoffmann and O. Lepski, Random rates in anisotropic regression. Ann. Statist.30 (2002) 325–396. With discussions and a rejoinder by the authors.  
  15. C. Houdré and P. Reynaud-Bouret, Exponential inequalities, with constants, for U-statistics of order two, in Stochastic inequalities and applications. Progr. Probab.56 (2003) 55–69.  
  16. Y.I. Ingster, Asymptotically minimax hypothesis testing for nonparametric alternatives. I. Math. Methods Stat.2 (1993) 85–114.  
  17. Y.I. Ingster, Asymptotically minimax hypothesis testing for nonparametric alternatives. II. Math. Methods Stat.2 (1993) 171–189.  
  18. Y.I. Ingster, Asymptotically minimax hypothesis testing for nonparametric alternatives. III. Math. Methods Stat.2 (1993) 249–268.  
  19. A. Juditsky and S. Lambert-Lacroix, Nonparametric confidence set estimation. Math. Methods Stat.12 (2003) 410–428.  
  20. A. Juditsky and O. Lepski, Evaluation of the accuracy of nonparametric estimators. Math. Methods Stat.10 (2001) 422–445. Meeting on Mathematical Statistics, Marseille (2000).  
  21. B. Laurent, Estimation of integral functionnals of a density. Ann. Statist.24 (1996) 659–681.  
  22. B. Laurent, Adaptive estimation of a quadratic functional of a density by model selection. ESAIM : PS9 (2005) 1–18 (electronic).  
  23. O.V. Lepski, How to improve the accuracy of estimation. Math. Methods Stat.8 (1999) 441–486.  
  24. M. Lerasle, Optimal model selection in density estimation. Preprint (2009).  
  25. K.C. Li, Honest confidence regions for nonparametric regression. Ann. Statist.17 (1989) 1001–1008.  
  26. M.G. Low, On nonparametric confidence intervals. Ann. Statist.25 (1997) 2547–2554.  
  27. P. Massart, Concentration inequalities and model selection. Springer, Berlin. Lect. Notes Math.1896 (2007). Lectures from the 33rd Summer School on Probability Theory held in Saint-Flour (2003). With a foreword by Jean Picard.  
  28. J. Robins and A. van der Vaart, Adaptive nonparametric confidence sets. Ann. Statist.34 (2006) 229–253.  

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.