×

Asymptotic and qualitative performance of non-parametric density estimators: a comparative study. (English) Zbl 1274.62273

Summary: Motivated by finance applications, we assessed the performance of several univariate density estimation methods, focusing on their ability to deal with heavy-tailed target densities. Four approaches, a fixed bandwidth kernel estimator, an adaptive bandwidth kernel estimator, the Hermite series (SNP) estimator of Gallant and Nychka, and the logspline estimator of Kooperberg and Stone, are compared. We conclude that the logspline and adaptive kernel methods provide superior performance, and the convergence rate of the SNP estimator is remarkably slow compared with the other methods. The Hellinger convergence rate of the SNP estimator is derived as a function of tail heaviness. These findings are confirmed in Monte Carlo experiments. Qualitative assessment reveals the possibility that side lobes in the tails of the fixed kernel and SNP estimates are artefacts of the fitting method.

MSC:

62G07 Density estimation
62G20 Asymptotic properties of nonparametric inference
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Abramson, On bandwidth variation in kernel estimates-a square root law, Annals of Statistics 10 pp 1217– (1982) · Zbl 0507.62040
[2] Andersen, Efficient method of moments estimation of a stochastic volatility model: a Monte Carlo study, Journal of Econometrics 91 pp 61– (1999) · Zbl 0937.62105
[3] Baillie, The message in daily exchange rates: a conditional variance tale, Journal of Business and Economic Statistics 7 pp 297– (1989)
[4] Bollerslev, A conditional heteroskedastic time series model for speculative prices and rates of return, Review of Economics and Statistics 69 pp 542– (1987)
[5] Bollerslev, ARCH modeling in finance: a review of the theory and empirical evidence, Journal of Econometrics 52 pp 5– (1992) · Zbl 0825.90057
[6] Breiman, Variable kernel estimates of multivariate densities, Technometrics 19 pp 135– (1977) · Zbl 0379.62023
[7] Coppejans, Cross-validated SNP density estimates, Journal of Econometrics 110 pp 27– (2002) · Zbl 1030.62028
[8] Devroye, A Course in Density Estimation (1987)
[9] Efromovich, Nonparametric Curve Estimation (1999)
[10] Engle, Semiparametric ARCH models, Journal of Business and Economic Statistics 9 pp 345– (1991)
[11] Fadda, Density estimation with non-parametric methods, Astronomy and Astrophysics Supplement Series 127 pp 335– (1998)
[12] Fenton, Convergence rates of SNP density estimators, Econometrica 64 pp 719– (1996) · Zbl 0848.62023
[13] Fenton, Qualitative and asymptotic performance of SNP density estimators, Journal of Econometrics 74 pp 77– (1996) · Zbl 0866.62078
[14] Fenton, Erratum, Econometrica 64 pp 1493– (1996)
[15] Gallant, Nonparametric and Semiparametric Methods in Econometrics and Statistics (1991)
[16] Gallant, Semi-nonparametric maximum likelihood estimation, Econometrica 55 pp 363– (1987) · Zbl 0631.62110
[17] Gallant, Stock prices and volume, The Review of Financial Studies 5 pp 199– (1992)
[18] Gallant, Seminonparametric estimation of conditionally constrained heterogeneous processes: asset pricing applications, Econometrica 57 pp 1091– (1989) · Zbl 0679.62096
[19] Good, Nonparametric roughness penalties for probability densities, Biometrika 58 pp 255– (1971) · Zbl 0221.62012
[20] He, Estimators and their breakdown points, Econometrica 58 pp 1195– (1990)
[21] Huisman, Tail-index estimates in small samples, Journal of Business & Economic Statistics 19 pp 208– (2001)
[22] Hwang, Nonparametric multivariate density estimation: a comparative study, IEEE Transactions on Signal Processing 42 pp 2795– (1994)
[23] Kooperberg, A study of logspline density estimation, Computational Statistics & Data Analysis 12 pp 327– (1991) · Zbl 0825.62442
[24] Marron, Exact mean integrated squared error, Annals of Statistics 20 pp 712– (1992) · Zbl 0746.62040
[25] Pagan, Nonparametric Econometrics (1999) · doi:10.1017/CBO9780511612503
[26] Park, Practical performance of several data driven bandwidth selectors (with discussion), Computational Statistics 7 pp 251– (1992) · Zbl 0775.62100
[27] Press, Numerical Recipes in C: The Art of Scientific Computing (1992) · Zbl 0845.65001
[28] Scott, Study of three data-based nonparametric probability density estimators, Journal of American Statistical Association 76 pp 9– (1981) · Zbl 0465.62036
[29] Sheather, A reliable data-based bandwidth selection method for kernel density estimation, Journal of the Royal Statistical Society pp 683– (1991) · Zbl 0800.62219
[30] Silverman, Density Estimation for Statistics and Data Analysis (1986) · Zbl 0617.62042 · doi:10.1007/978-1-4899-3324-9
[31] Stone, Polynomial splines and their tensor products in extended linear modeling, Annals of Statistics 25 pp 1371– (1997) · Zbl 0924.62036
[32] Takada, T. (2001). Density estimation for robust financial econometrics. Ph.D. dissertation, Department of Economics, University of Illinois at Urbana-Champaign.
[33] Wand, Kernel Smoothing (1995) · doi:10.1007/978-1-4899-4493-1
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.