Electronic Journal of Statistics

Univariate log-concave density estimation with symmetry or modal constraints

Charles R. Doss and Jon A. Wellner

Full-text: Open access

Enhanced PDF (1406 KB)

Abstract

We study nonparametric maximum likelihood estimation of a log-concave density function $f_{0}$ which is known to satisfy further constraints, where either (a) the mode $m$ of $f_{0}$ is known, or (b) $f_{0}$ is known to be symmetric about a fixed point $m$. We develop asymptotic theory for both constrained log-concave maximum likelihood estimators (MLE’s), including consistency, global rates of convergence, and local limit distribution theory. In both cases, we find the MLE’s pointwise limit distribution at $m$ (either the known mode or the known center of symmetry) and at a point $x_{0}\ne m$. Software to compute the constrained estimators is available in the R package logcondens.mode.

The symmetry-constrained MLE is particularly useful in contexts of location estimation. The mode-constrained MLE is useful for mode-regression. The mode-constrained MLE can also be used to form a likelihood ratio test for the location of the mode of $f_{0}$. These problems are studied in separate papers. In particular, in a separate paper we show that, under a curvature assumption, the likelihood ratio statistic for the location of the mode can be used for hypothesis tests or confidence intervals that do not depend on either tuning parameters or nuisance parameters.

Article information

Source
Electron. J. Statist., Volume 13, Number 2 (2019), 2391-2461.

Dates
Received: October 2018
First available in Project Euclid: 23 July 2019

Permanent link to this document
https://projecteuclid.org/euclid.ejs/1563868824

Digital Object Identifier
doi:10.1214/19-EJS1574

Mathematical Reviews number (MathSciNet)
MR3983344

Zentralblatt MATH identifier
1422.62137

Subjects
Primary: 62G07: Density estimation
Secondary: 62G05: Estimation 62G20: Asymptotic properties

Keywords
Mode consistency convergence rate empirical processes convex optimization log-concave shape constraints symmetric

Rights
Creative Commons Attribution 4.0 International License.

Citation

Doss, Charles R.; Wellner, Jon A. Univariate log-concave density estimation with symmetry or modal constraints. Electron. J. Statist. 13 (2019), no. 2, 2391--2461. doi:10.1214/19-EJS1574. https://projecteuclid.org/euclid.ejs/1563868824


Export citation

References

  • Azadbakhsh, M., Jankowski, H. and Gao, X. (2014). Computing confidence intervals for log-concave densities., Comput. Statist. Data Anal. 75 248–264.
    Zentralblatt MATH: 06983959
    Digital Object Identifier: doi:10.1016/j.csda.2014.01.020
  • Balabdaoui, F. and Doss, C. R. (2018). Inference for a two-component mixture of symmetric distributions under log-concavity., Bernoulli 24 1053–1071.
    Zentralblatt MATH: 1419.62059
    Digital Object Identifier: doi:10.3150/16-BEJ864
    Project Euclid: euclid.bj/1505980889
  • Balabdaoui, F., Rufibach, K. and Wellner, J. A. (2009). Limit distribution theory for maximum likelihood estimation of a log-concave density., Ann. Statist. 37 1299–1331.
    Zentralblatt MATH: 1160.62008
    Digital Object Identifier: doi:10.1214/08-AOS609
    Project Euclid: euclid.aos/1239369023
  • Balabdaoui, F. and Wellner, J. A. (2007). Estimation of a $k$-monotone density: limit distribution theory and the spline connection., Ann. Statist. 35 2536–2564.
    Zentralblatt MATH: 1129.62019
    Digital Object Identifier: doi:10.1214/009053607000000262
    Project Euclid: euclid.aos/1201012971
  • Billingsley, P. (1999)., Convergence of Probability Measures, second ed. Wiley Series in Probability and Statistics: Probability and Statistics. John Wiley & Sons Inc., New York. A Wiley-Interscience Publication.
  • Chacón, J. E. (2018a). Mixture model modal clustering., Advances in Data Analysis and Classification 12 1–26.
  • Chacón, J. E. (2018b). The Modal Age of Statistics., arXiv:1807.02789.
  • Chang, G. T. and Walther, G. (2007). Clustering with mixtures of log-concave distributions., Comput. Statist. Data Anal. 51 6242–6251.
    Zentralblatt MATH: 05560105
    Digital Object Identifier: doi:10.1016/j.csda.2007.01.008
  • Chen, Y.-C., Genovese, C. R. and Wasserman, L. (2015). Asymptotic theory for density ridges., Ann. Statist. 43 1896–1928.
    Zentralblatt MATH: 1327.62303
    Digital Object Identifier: doi:10.1214/15-AOS1329
    Project Euclid: euclid.aos/1438606848
  • Chen, Y.-C., Genovese, C. R., Tibshirani, R. J. and Wasserman, L. (2016). Nonparametric modal regression., Ann. Statist. 44 489–514.
    Zentralblatt MATH: 1338.62113
    Digital Object Identifier: doi:10.1214/15-AOS1373
    Project Euclid: euclid.aos/1458245725
  • Cule, M. and Samworth, R. (2010). Theoretical properties of the log-concave maximum likelihood estimator of a multidimensional density., Electron. J. Stat. 4 254–270.
    Zentralblatt MATH: 1329.62183
    Digital Object Identifier: doi:10.1214/09-EJS505
  • Cule, M., Samworth, R. and Stewart, M. (2010). Maximum likelihood estimation of a multi-dimensional log-concave density., J. R. Stat. Soc. Ser. B Stat. Methodol. 72 545–607.
    Zentralblatt MATH: 1411.62055
    Digital Object Identifier: doi:10.1111/j.1467-9868.2010.00753.x
  • Dieudonné, J. (1969)., Foundations of Modern Analysis. Academic Press, New York-London.
  • Doss, C. R. (2013a). logcondens.mode: Compute MLE of Log-Concave Density on R with Fixed Mode, and Perform Inference for the Mode. R package version 1.0.1. Available from, http://CRAN.R-project.org/package=logcondens.mode.
  • Doss, C. R. (2013b). Shape-constrained inference for concave-transformed densities and their modes PhD thesis, University of, Washington.
  • Doss, C. R. and Wellner, J. A. (2016). Global rates of convergence of the MLEs of log-concave and $s$-concave densities., Ann. Statist. 44 954–981. With supplementary material available online.
    Zentralblatt MATH: 1338.62101
    Digital Object Identifier: doi:10.1214/15-AOS1394
    Project Euclid: euclid.aos/1460381683
  • Doss, C. R. and Wellner, J. A. (2019). Inference for the mode of a log-concave density., Annals of Statistics 47 to appear. arXiv:1611.10348.
  • Dümbgen, L. and Rufibach, K. (2009). Maximum likelihood estimation of a log-concave density and its distribution function: basic properties and uniform consistency., Bernoulli 15 40–68.
    Zentralblatt MATH: 1200.62030
    Digital Object Identifier: doi:10.3150/08-BEJ141
    Project Euclid: euclid.bj/1233669882
  • Dümbgen, L. and Rufibach, K. (2011). logcondens: computations related to univariate log-concave density estimation., Journal of Statistical Software 39 1–28.
  • Dümbgen, L., Samworth, R. and Schuhmacher, D. (2011). Approximation by log-concave distributions, with applications to regression., Ann. Statist. 39 702–730.
    Zentralblatt MATH: 1216.62023
    Digital Object Identifier: doi:10.1214/10-AOS853
    Project Euclid: euclid.aos/1299680952
  • Eilers, P. H. C. and Borgdorff, M. W. (2007). Non-parametric log-concave mixtures., Comput. Statist. Data Anal. 51 5444–5451.
    Zentralblatt MATH: 05559638
    Digital Object Identifier: doi:10.1016/j.csda.2006.08.027
  • Folland, G. B. (1999)., Real Analysis, second ed. Pure and Applied Mathematics (New York). John Wiley & Sons Inc., New York. Modern techniques and their applications, A Wiley-Interscience Publication.
  • Groeneboom, P., Jongbloed, G. and Wellner, J. A. (2001a). A canonical process for estimation of convex functions: the “invelope” of integrated Brownian motion $+t^4$., Ann. Statist. 29 1620–1652.
    Zentralblatt MATH: 1043.62026
    Digital Object Identifier: doi:10.1214/aos/1015345957
    Project Euclid: euclid.aos/1015345957
  • Groeneboom, P., Jongbloed, G. and Wellner, J. A. (2001b). Estimation of a convex function: characterizations and asymptotic theory., Ann. Statist. 29 1653–1698.
    Zentralblatt MATH: 1043.62027
    Digital Object Identifier: doi:10.1214/aos/1015345958
    Project Euclid: euclid.aos/1015345958
  • Hall, P. (1984). On unimodality and rates of convergence for stable laws., J. London Math. Soc. (2) 30 371–384.
    Zentralblatt MATH: 0597.60017
    Digital Object Identifier: doi:10.1112/jlms/s2-30.2.371
  • Han, Q. and Wellner, J. A. (2016). Approximation and estimation of $s$-concave densities via Rényi divergences., Ann. Statist. 44 1332–1359.
    Zentralblatt MATH: 1338.62105
    Digital Object Identifier: doi:10.1214/15-AOS1408
    Project Euclid: euclid.aos/1460381695
  • Kim, J. and Pollard, D. (1990). Cube root asymptotics., Ann. Statist. 18 191–219.
    Zentralblatt MATH: 0703.62063
    Digital Object Identifier: doi:10.1214/aos/1176347498
    Project Euclid: euclid.aos/1176347498
  • Kim, A. K. H. and Samworth, R. J. (2016). Global rates of convergence in log-concave density estimation., Ann. Statist. 44 2756–2779.
    Zentralblatt MATH: 1360.62157
    Digital Object Identifier: doi:10.1214/16-AOS1480
    Project Euclid: euclid.aos/1479891634
  • Lachal, A. (1997). Local asymptotic classes for the successive primitives of Brownian motion., Ann. Probab. 25 1712–1734.
    Zentralblatt MATH: 0903.60071
    Digital Object Identifier: doi:10.1214/aop/1023481108
    Project Euclid: euclid.aop/1023481108
  • Laha, N. (2019). Some semiparametric models under log-concavity. PhD thesis in, progress.
  • Mason, D. M. and van Zwet, W. R. (1987). A refinement of the KMT inequality for the uniform empirical process., Ann. Probab. 15 871–884.
    Zentralblatt MATH: 0638.60040
    Digital Object Identifier: doi:10.1214/aop/1176992070
    Project Euclid: euclid.aop/1176992070
  • Pal, J. K., Woodroofe, M. and Meyer, M. (2007). Estimating a Polya frequency function$_2$. In, Complex datasets and inverse problems. IMS Lecture Notes Monogr. Ser. 54 239–249. Inst. Math. Statist., Beachwood, OH.
  • Polonik, W. (1995). Measuring mass concentrations and estimating density contour clusters—an excess mass approach., Ann. Statist. 23 855–881.
    Zentralblatt MATH: 0841.62045
    Digital Object Identifier: doi:10.1214/aos/1176324626
    Project Euclid: euclid.aos/1176324626
  • Pu, X. and Arias-Castro, E. (2017). Semiparametric estimation of symmetric mixture models with monotone and log-concave densities., arXiv:1702.08897.
  • Qiao, W. and Polonik, W. (2016). Theoretical analysis of nonparametric filament estimation., Ann. Statist. 44 1269–1297.
    Zentralblatt MATH: 1338.62139
    Digital Object Identifier: doi:10.1214/15-AOS1405
    Project Euclid: euclid.aos/1460381693
  • R Core Team, (2016). R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria.
  • Rockafellar, R. T. (1970)., Convex Analysis. Princeton Mathematical Series, No. 28. Princeton University Press, Princeton, N.J.
    Zentralblatt MATH: 0193.18401
  • Romano, J. P. (1987). On bootstrapping the joint distribution of the location and size of the mode PhD thesis, University of California, Berkeley.
  • Royden, H. L. (1988)., Real Analysis, Third ed. Macmillan Publishing Company, New York.
    Zentralblatt MATH: 0704.26006
  • Rufibach, K. (2006). Log-concave density estimation and bump hunting for IID observations. PhD thesis, Univ. Bern and, Gottingen.
  • Seregin, A. and Wellner, J. A. (2010). Nonparametric estimation of multivariate convex-transformed densities., Ann. Statist. 38 3751–3781. With supplementary material available online.
    Mathematical Reviews (MathSciNet): MR2766867
    Zentralblatt MATH: 1204.62058
    Digital Object Identifier: doi:10.1214/10-AOS840
    Project Euclid: euclid.aos/1291126972
  • Shorack, G. R. (2000)., Probability for Statisticians. Springer Texts in Statistics. Springer-Verlag, New York.
    Mathematical Reviews (MathSciNet): MR1762415
  • Shorack, G. R. and Wellner, J. A. (2009)., Empirical Processes with Applications to Statistics. Classics in Applied Mathematics 59. Society for Industrial and Applied Mathematics (SIAM), Philadelphia, PA.
    Mathematical Reviews (MathSciNet): MR3396731
  • Silverman, B. W. (1982). On the estimation of a probability density function by the maximum penalized likelihood method., Ann. Statist. 10 795–810.
    Zentralblatt MATH: 0492.62034
    Digital Object Identifier: doi:10.1214/aos/1176345872
    Project Euclid: euclid.aos/1176345872
  • Sinai, Y. G. (1992). Statistics of shocks in solutions of inviscid Burgers equation., Comm. Math. Phys. 148 601–621.
    Zentralblatt MATH: 0755.60105
    Digital Object Identifier: doi:10.1007/BF02096550
    Project Euclid: euclid.cmp/1104251046
  • Skorokhod, A. V. (1956). Limit theorems for stochastic processes., Theory Probab. Appl. 1 261.
    Zentralblatt MATH: 0074.33802
  • van der Vaart, A. W. and Wellner, J. A. (1996)., Weak Convergence and Empirical Processes. Springer Series in Statistics. Springer-Verlag, New York. With applications to statistics.
    Zentralblatt MATH: 0862.60002
  • Walther, G. (2002). Detecting the presence of mixing with multiscale maximum likelihood., J. Amer. Statist. Assoc. 97 508–513.
    Zentralblatt MATH: 1073.62533
    Digital Object Identifier: doi:10.1198/016214502760047032
  • Walther, G. (2009). Inference and modeling with log-concave distributions., Statist. Sci. 24 319–327.
    Zentralblatt MATH: 1329.62192
    Digital Object Identifier: doi:10.1214/09-STS303
    Project Euclid: euclid.ss/1270041258
  • Watanabe, H. (1970). An asymptotic property of Gaussian processes., Trans. Amer. Math. Soc. 148 233.
    Zentralblatt MATH: 0214.16502
    Digital Object Identifier: doi:10.1090/S0002-9947-1970-0256478-5
  • Whitt, W. (1970). Weak convergence of probability measures on the function space $C[0,\infty )$., Ann. Math. Stat. 41 939–944.
    Zentralblatt MATH: 0203.50501
    Digital Object Identifier: doi:10.1214/aoms/1177696970
    Project Euclid: euclid.aoms/1177696970
  • Whitt, W. (1980). Some useful functions for functional limit theorems., Math. Oper. Res. 5 67–85.
    Zentralblatt MATH: 0428.60010
    Digital Object Identifier: doi:10.1287/moor.5.1.67
  • Whitt, W. (2002)., Stochastic-Process Limits. Springer Series in Operations Research. Springer-Verlag, New York.
  • Xu, M. and Samworth, R. J. (2017). High-dimensional nonparametric density estimation via symmetry and shape constraints. Technical Report, Available at, http://www.statslab.cam.ac.uk/~rjs57/Research.html.

The Institute of Mathematical Statistics and the Bernoulli Society

Electronic Journal of Statistics

New content alerts

Email RSS ToC RSS Article
  • You have access to this content.
  • You have partial access to this content.
  • You do not have access to this content.
Turn Off MathJax

What is MathJax?

More like this

+ See more