Abstract
In nonparametric signal estimation, there is a need for estimating the logarithmic probability density derivatives. This problem is complex, because the logarithmic density derivative is a function with singularity—a ratio containing density in the denominator. Since the density estimate can take values close or even equal to zero, the estimate of the logarithmic derivative becomes unstable. This difficulty is surmounted by constructing a new nonparametric estimate for the logarithmic derivative, i.e., an estimate that is stable to observation and based piecewise-smooth approximation. Its properties for dependent observations generated by stationary processes satisfying the strong mixing condition are studied. The rate of convergence of the nonparametric estimate and the principal part of the expansion of the mean-square estimate error are determined.
Similar content being viewed by others
REFERENCES
Roussas, G.G., On Some Properties of Nonparametric Estimates of Probability Density Functions, Bull. Soc. Math., 1968, no. 1, pp. 29-43.
Roussas, G.G., Nonparametric Estimation in Markov Processes, Ann. Inst. Statist. Math., 1969, vol. 21, no. 1, pp. 73-87.
Rosenblatt, M., Density Estimates and Markov Sequences. Nonparametric Techniques in Statistical Inference, Cambridge: Cambridge Univ. Press, 1970.
Rosenblatt, M., Curve Estimates, Ann. Math. Statist., 1971, vol. 42, no. 6, pp. 1815-1842.
Rosenblatt, M., Markov Processes: Structure and Asymptotic Behavior, Berlin: Springer-Verlag, 1971.
Koshkin, G.M. and Tarasenko, F.P., A Consistency Condition for Weakly Dependent Samples, Mat. Statist. Prilozh., 1976, issue 4, pp. 29-41.
Koshkin, G.M. and Tarasenko, F.P., Recurrent Probability Density Estimation and Regression Lines of Dependent Samples, Mat. Statist. Prilozh., 1976, issue 4, pp. 122-138.
Koshkin, G.M., An Approach to Estimation of Transition Distribution Functions and Moments for Certain Markov Processes, Mat. Statist. Prilozh., 1976, issue 4, pp. 116-121.
Delecroix, M., Central Limit Theorems for Density Estimators of a ϕ-Mixing Process, in Recent Developments in Statistics, Amsterdam: North Holland, 1977, pp. 409-414.
Masry, E., Probability Density Estimation from Sampled Data, IEEE Trans. Inf. Theory, 1983, vol. 29, no. 5, pp. 696-709.
Masry, E., Recursive Probability Density Estimation for Weakly Dependent Stationary Processes, IEEE Trans. Inf. Theory, 1986, vol. 32, no. 2, pp. 254-267.
Koshkin, G.M. and Tarasenko, F.P., Nonparametric Algorithms for Identifying and Control of Continuous-Discrete Stochastic Objects, 8th IFAC-IFORS Symp. Identif. Syst. Parameter Estimation, Beijing: Pergamon Press, 1988, vol. 2, pp. 882-887.
Castellana, J.V. and Leadbetter, M.R., On Smoothed Probability Density Estimation for Stationary Processes, Stoch. Proces. Appl., 1986, vol. 21, no. 2, pp. 179-193.
Györfi, L., Strong Consistent Density Estimate from Ergodic Samples, J. Mult. Anal., 1981, vol. 11, no. 1, pp. 81-84.
Györfi, L., Recent Results on Nonparametric Regression Estimate and Multiple Classification, Prob. Control Inf. Theory, 1981, vol. 10, no. 1, pp. 43-52.
Pracasa Rao, B.L.S., Nonparametric Functional Estimation, Orlando: Academic, 1983.
Györfi, L., Hardle, W., Sarda, P., and Vieu, P., Nonparametric Curve Estimation from Time Series, Berlin: Springer, 1988.
Masry, E., Nonparametric Estimation of Conditional Probability Densities and Expectations of Stationary Processes: Strong Consistency and Rates, Stoch. Proces. Appl., 1989, vol. 32, no. 1, pp. 109-127.
Masry, E., Almost Sure Convergence of Recursive Density Estimators for Stationary Mixing Processes, Statist. Prob. Lett., 1987, vol. 5, no. 2, pp. 249-254.
Masry, E. and Györfi, L., Strong Consistency and Rates for Recursive Probability Density Estimators of Stationary Processes, J. Mult. Anal., 1987, vol. 22, no. 1, pp. 79-93.
Doukhan, P. and Ghindes, M., Estimation de la transition de probabilite d'une chain de Markov Doeblin-recurrente. Etude du eas processus autoregressif general d'ordre 1, Stoch. Proces. Appl., 1983, vol. 15, no. 3, pp. 271-293.
Robinson, P.M., Nonparametric Estimation from Time Series Residuals, Cah. Cent. Etud. Rech. Oper., 1986, vol. 28, no. 1-3, pp. 197-202.
Vasil'ev, V.A., Estimation of the Distribution of Disturbances in an Autoregression Process, Mat. Stat. Pril., 1986, issue 10, pp. 9-24.
Masry, E., Multivariate Probability Density Deconvolution for Stationary Random Processes, IEEE Trans. Inf. Theory, 1991, vol. 37, no. 4, pp. 1105-1115.
Tran, L.T., Kernel Density Estimation of Random Fields, J. Mult. Anal., 1990, vol. 34, no. 1, pp. 37-53.
Vasil'ev, V.A. and Koshkin, G.M., Estimation of Limiting Distribution Density and Its Derivative from Weakly Dependent Observations, Probl. Peredachi Inf., 1997, vol. 33, issue 2, pp. 66-80.
Koshkin, G. and Vasil'iev, V., Estimation of Multivariate Probability Density and Its Derivatives from Weakly Dependent Observations, in: Proc. Steklov Math. Inst. Seminar “Statistics and Control of Stochastic Processes,” The Liptser Festschrift, Steklov Math. Inst., Yu.M. Kabanov, B.L. Rozovskii, and A.N. Shiryaev, Eds, Singapore: World Scientific, 1997, pp. 229-241.
Vail'ev, V.A. and Koshkin, G.M., Estimation of Distribution Density Functions from Dependent Observations, Probl. Peredachi Inf., 1997, vol. 33, issue 4, pp. 45-60.
Vail'ev, V.A. and Koshkin, G.M., Nonparametric Identification of Autoregressions, Teor. Veroyatn. Primenen., 1998, vol. 43, issue 3, pp. 577-588.
Koshkin, G.M. and Vasil'iev, V.A., Nonparametric Estimation of Multivariate Density Derivatives from Dependent Observations, Math. Methods Statist., 1998, vol. 7, no. 4, pp. 361-400.
Nemirovskii, A.S. and Tsypkin, Ya.Z., Optimal Adaptive Control Algorithms, Avtom. Telemekh., 1984, no. 12, pp. 64-77.
Nadaraya, E.A., Nonparametric Estimates of Probability Density and Regression, Teor. Veroyatn. Primenen., 1965, vol. 10, issue 1, pp. 199-203.
Kushnir, A.F., Asymptotically Optimal Criteria for Hypothesis Testing Regression Problems, Teor. Veroyatn. Primenen., 1968, vol. 13, issue 4, pp. 682-700.
Dobrovidov, A.V., Asymptotically ε-Optimal Nonparametric Filtering of Stationary Sequences with Unknown Statistical Characteristics, Avtom. Telemekh., 1984, no. 12, pp. 40-49.
Dobrovidov, A.V. and Koshkin, G.M., Neparametricheskoe otsenivanie signalov (Nonparametric Estimation of Signals), Moscow: Nauka, Fizmatlit, 1997.
Cramer, H., Mathematical Methods of Statistics, Princeton: Princeton Univ. Press, 1937. Translated under the title Matematicheskie metody statistiki, Moscow: Mir, 1975.
Penskaya, M.Ya., Stable Estimation of a Function of a Parameter, in Statisticheskie metody otsenivaniya i proverki gipotez (Statistical Methods of Estimation and Testing of Hypotheses), Perm: Perm. Gos. Univ., 1990, pp. 44-55.
Koshkin, G.M., Moments of Deviations of the Estimates of a Substitution and Its Piecewise-Smooth Approximations, Sib. Mat. Zh., 1999, vol. 40, no. 3, pp. 601-614.
Vasil'ev, V.A. and Koshkin, G.M., Nonparametric Estimation of the Relations of Derivatives of a Multivariate Distribution Density from Dependent Observations, Sib. Mat. Zh., 2000, vol. 41, no. 2, pp. 312-330.
Rosenblatt, M., Remarks on Some Nonparametric Estimates of Density functions, Ann. Math. Statist., 1956, vol. 27, no. 3, pp. 832-837.
Parzen, E., On Estimation of a Probability Density Function and Mode, Ann. Math. Statist., 1962, vol. 33, no. 3, pp. 1065-1076.
Gasser, T. and Müller, H.-G., Kernel Estimation of Regression Functions, Lect. Notes Math., 1979, vol. 757, pp. 23-68.
Müller, H.-G. and Gasser, T., Optimal Convergence Properties of Kernel Estimates of Derivatives of a Density Function, Lect. Notes Math., 1979, vol. 757, pp. 144-154.
Koshkin, G.M., An Improved Nonnegative Kernel Density Estimate, Teor. Veroyatn. Primenen., 1988, vol. 33, issue 4, pp. 817-822.
Ibragimov, I.A. and Linnik, Yu.V., Nezavisimye i statsionarno svyazannye velichiny (Independent and Stationarily Connected Variables), Moscow: Nauka, 1965.
Bradley, R. and Bryc, W., Multilinear Forms and Measures of Dependence between Random Variables, J. Mult. Anal., 1985, vol. 16, no. 3, pp. 335-367.
Davydov, Yu.A., Convergence of Distributions generated by Stationary Random Processes, Teor. Veroyatn. Primenen., 1968, vol. 13, issue. 4, pp. 730-737.
Koshkin, G.M., Asymptotic Properties of Functions of Statistics and Their Application in Nonparametric Estimation, Avtom. Telemekh., 1990, no. 3, pp. 82-97.
Natanson, I.P., Teoriya funktsii veshchestvennoi peremennoi (Theory of Functions of a Real Variable), Moscow: Nauka, 1974.
Schuster, E.F., Estimation of a Probability Density Function and its derivatives, Ann. Math. Statist., 1969, vol. 40, no. 4, pp. 1187-1195.
Schuster, E.F., Joint Asymptotic Distribution of the Estimated Regression Function at a Finite Number of Distinct Points, Ann. Math. Statist., 1972, vol. 43, no. 1, pp. 84-88.
Billingsley, P., Convergence of Probability Measures, New York: Wiley, 1968. Translated under the title Skhodimost' veroyatnostnykh mer, Moscow: Nauka, 1977.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Dobrovidov, A.V., Koshkin, G.M. Nonparametric Estimation of the Logarithmic Density Derivative of Sequences with Strong Mixing. Automation and Remote Control 62, 1453–1476 (2001). https://doi.org/10.1023/A:1011647726387
Issue Date:
DOI: https://doi.org/10.1023/A:1011647726387