The truncated Stieltjes moment problem solved by using kernel density functions. (English) Zbl 1247.65157
Summary: The problem of the approximate numerical determination of a semi-infinite supported, continuous probability density function (pdf) from a finite number of its moments is addressed. The target space is carefully defined and an approximation theorem is proved, establishing that the set of all convex superpositions of appropriate kernel density functions (KDFs) is dense in this space. A solution algorithm is provided, based on the established approximate representation of the target pdf and the exploitation of some theoretical results concerning moment sequence asymptotics. The solution algorithm also permits us to recover the tail behavior of the target pdf and incorporate this information in our solution. A parsimonious formulation of the proposed solution procedure, based on a novel sequentially adaptive scheme is developed, enabling a very efficient moment data inversion. The whole methodology is fully illustrated by numerical examples.
MSC:
| 65R10 | Numerical methods for integral transforms |
| 65R32 | Numerical methods for inverse problems for integral equations |
| 44A60 | Moment problems |
Keywords:
truncated Stieltjes moment problem; kernel density function; probability density function; ill-posed problem; moment asymptotics; tail behavior; algorithm; numerical examplesReferences:
| [1] | Stieltjes, T. J., Recherchers sur les fractions continues, Annales de la Faculte des Sciences de Toulouse, 8, 1-122 (1884) |
| [2] | Akhiezer, N. I., The Classical Moment Problem (1965), Oliver and Boyd: Oliver and Boyd London · Zbl 0135.33803 |
| [3] | Shohat, J. A.; Tamarkin, J. D., The problem of moments, American Mathematical Survey (1943) · Zbl 0063.06973 |
| [4] | Stoyanov, J. M., Counterexamples in Probability (1987), Wiley: Wiley New York · Zbl 0629.60001 |
| [5] | Berg, C., On powers of Stieltjes moment sequences, I, Journal of Theoretical Probability, 18, 871-889 (2005) · Zbl 1086.44003 |
| [6] | Berg, C., On powers of Stieltjes moment sequences, II, Journal of Computational and Applied Mathematics, 199, 23-38 (2007) · Zbl 1111.44001 |
| [7] | Gut, A., On the moment problem, Bernoulli, 8, 407-421 (2002) · Zbl 1006.60016 |
| [8] | Lin, G. D., On the moment problems, Statistics & Probability Letters, 35, 85-90 (1997) · Zbl 0904.62021 |
| [9] | Pakes, A. G., Structure of Stieltjes classes of moment-equivalent probability laws, Journal of Mathematical Analysis and Applications, 326, 1268-1290 (2007) · Zbl 1120.60007 |
| [10] | Pakes, A. G.; Hung, W.-L.; Wu, J.-W., Criteria for the unique determination of probability distributions by moments, Journal of the Australian Mathematical Society, 43, 101-111 (2001) · Zbl 0997.60001 |
| [11] | Stoyanov, J. M., Krein condition in probabilistic moment problems, Bernoulli, 6, 939-949 (2000) · Zbl 0971.60017 |
| [12] | Bertsimas, D.; Popescu, I., On the relation between option and stock prices: a convex optimization approach, Operations Research, 50, 358-374 (2002) · Zbl 1163.91382 |
| [13] | Bertsimas, D.; Popescu, I., Optimal inequalities in probability theory: a convex optimization approach, SIAM Journal on Optimization, 15, 780-804 (2005) · Zbl 1077.60020 |
| [14] | Bessis, D.; Handy, C. R., Moment problem formulation of the Schrodinger equation, Numerical Algorithms, 3, 1-16 (1992) · Zbl 0786.65098 |
| [15] | Handy, C. R.; Bessis, D.; Morley, D., Generating quantum energy bounds by the moment method: a linear-programming approach, Physical Review A, 15, 4557-4569 (1988) |
| [16] | Handy, C. R.; Ndow, G. L., Euclidean time formulation of the eigenvalue moment method: a moment problem-convexity analysis of Barnsley’s theorem, Journal of Physics A: Mathematical and General, 25, 2669-2681 (1992) · Zbl 0774.35050 |
| [17] | Lasserre, J. B., Bounds on measures satisfying moment conditions, The Annals of Applied Probability, 12, 1114-1137 (2002) · Zbl 1073.90534 |
| [18] | Lasserre, J. B.; Prieto-Rumeau, T.; Zervos, M., Pricing a class of exotic options via moments and SDP relaxations, Mathematical Finance, 16, 469-494 (2006) · Zbl 1133.91428 |
| [19] | Weidelt, P., The relationship between the spectral function and the underlying conductivity structure in 1-D magnetotellurics, Geophysical Journal International, 161, 566-590 (2005) |
| [20] | Poland, D., Time evolution of polymer distribution functions from moment equations and maximum-entropy methods, The Journal of Chemical Physics, 111, 8214-8224 (1999) |
| [21] | Zarzo, A.; Angulo, J. C.; Antolin, J.; Yanez, R. J., Maximum-entropy analysis of one-particle densities in atoms, Zeitschrift fur Physik D Atoms, Molecules and Clusters, 37, 295-299 (1996) |
| [22] | Berera, A.; Martin, P. A., Inverting the Sachs-Wolfe formula: an inverse problem arising in early-universe cosmology, Inverse Problems, 15, 1393-1404 (1999) · Zbl 0945.44003 |
| [23] | Alibrandi, U.; Ricciardi, G., Efficient evaluation of the pdf of a random variable through the kernel density maximum entropy approach, International Journal for Numerical Methods in Engineering, 75, 1511-1548 (2008) · Zbl 1162.65307 |
| [24] | Sobczyk, K., Stochastic Differential Equations with Applications to Physics and Engineering (1991), Kluwer Academic Publishers: Kluwer Academic Publishers Boston · Zbl 0762.60050 |
| [25] | Sobczyk, K.; Trebicki, J., Maximum entropy principle and nonlinear stochastic oscillators, Physica A: Statistical and Theoretical Physics, 193, 448-468 (1993) · Zbl 0799.60052 |
| [26] | Klauder, J. R.; Penson, K. A.; Sixdeniers, J.-M., Constructing coherent states through solutions of Stieltjes and Hausdorff moment problems, Physical Review A, 64, 013817 (2001) · Zbl 1192.81197 |
| [27] | Penson, K. A.; Solomon, A. I., New generalized coherent states, Journal of Mathematical Physics, 40, 2354-2363 (1999) · Zbl 0953.81035 |
| [28] | Penson, K. A.; Blasiak, P.; Duchamp, G.; Horzela, A.; Solomon, A. I., Hierarchical Dobinski-type relations via substitution and the moment problem, Journal of Physics A: Mathematical and General, 37, 3475-3487 (2004) · Zbl 1151.82347 |
| [29] | Diemer, R. B.; Olson, J. H., A moment methodology for coagulation and breakage problems: Part 2—moment models and distribution reconstruction, Chemical Engineering Science, 57, 2211-2228 (2002) |
| [30] | John, V.; Angelov, I.; Öncül, A. A.; Thévenin, D., Techniques for the reconstruction of a distribution from a finite number of its moments, Chemical Engineering Science, 62, 2890-2901 (2007) |
| [31] | McGraw, R.; Nemesure, S.; Schwarts, S. E., Properties and evolution of aerosols with size distributions having identical moments, Journal of Aerosol Science, 29, 761-772 (1998) |
| [32] | Buchen, P.; Kelly, M., The maximum entropy distribution of an asset inferred from option prices, Journal of Financial and Quantitative Analysis, 31, 143-159 (1996) |
| [33] | El-Wakil, S. A.; Abulwafa, E. M.; Abdou, M. A.; Elhanbaly, A., Maximum-entropy approach with higher moments for solving Fokker-Planck equation, Physica A, 315, 480-492 (2002) · Zbl 1001.82083 |
| [34] | Geman, H.; Yor, M., Bessel processes, Asian options and perpetuities, Mathematical Finance, 3, 349-375 (1993) · Zbl 0884.90029 |
| [35] | Wu, X., Calculation of maximum entropy densities with application to income distribution, Journal of Econometrics, 115, 347-354 (2003) · Zbl 1016.62094 |
| [36] | Bertero, M.; De Mol, C.; Pike, E. R., Linear inverse problems with discrete data. I: General formulation and singular system analysis, Inverse Problems, 1, 301-330 (1985) · Zbl 0615.65057 |
| [37] | Talenti, G., Recovering a function from a finite number of moments, Inverse Problems, 3, 501-517 (1987) · Zbl 0649.44007 |
| [38] | Athanassoulis, G. A.; Gavriliadis, P. N., The Hausdorff moment problem solved by using kernel density functions, Probabilistic Engineering Mechanics, 17, 273-291 (2002) · Zbl 1247.65157 |
| [39] | Tikhonov, A. N.; Arsenin, V. Y., Solutions of Ill-Posed Problems (1977), Wiley: Wiley New York · Zbl 0354.65028 |
| [40] | Tikhonov, A. N.; Goncharsky, A. V., Ill-Posed Problems in the Natural Sciences (1987), Mir Pub.: Mir Pub. Moscow |
| [41] | Gavriliadis, P. N., Moment information for probability distributions, without solving the moment problem, I: where is the mode?, Communications in Statistics. Theory and Methods, 37, 671-681 (2008) · Zbl 1136.62009 |
| [42] | Gavriliadis, P. N.; Athanassoulis, G. A., Moment information for probability distributions, without solving the moment problem. II: Main-mass, tails and shape approximation, Journal of Computational and Applied Mathematics, 229, 7-15 (2009) · Zbl 1369.62010 |
| [43] | Bandyopadhyay, K.; Bhattacharyya, K.; Bhattacharyya, A. K., On some problems of the maximum entropy ansatz, Pranama Journal of Physics, 54, 365-375 (2000) |
| [44] | Bandyopadhyay, K.; Bhattacharyya, K.; Bhattacharyya, A. K., Maximum-entropy principle with moment recursion relations as constraints, Physical Review A, 63, 064101-064104 (2001) |
| [45] | Bronski, J. C.; McLaughlin, D. W., Rigorous estimates of the tails of the probability distribution function for the random linear shear model, Journal of Statistical Physics, 98, 897-915 (2000) · Zbl 1063.76046 |
| [46] | Cobb, E. B.; Haris, B., The characterization of the solution sets for the generalized reduced problems and its application to numerical integration, Siam Review, 8, 86-99 (1966) · Zbl 0143.34806 |
| [47] | Krein, M. G.; Nudelman, A. A., The Markov Moment Problem and Extremal Problems (1977), AMS: AMS Providence RI · Zbl 0361.42014 |
| [48] | W.D. Smith, The Gamma function revisited, unpublished manuscript, 2006. http://scorevoting.net/WarrenSmithPages/homepage/gammprox.pdf; W.D. Smith, The Gamma function revisited, unpublished manuscript, 2006. http://scorevoting.net/WarrenSmithPages/homepage/gammprox.pdf |
| [49] | Abate, J.; Choudhury, G. L.; Lucantoni, D. M.; Whitt, W., Asymptotic analysis of tail probabilities based on the computation of moments, Annals of Applied Probability, 5, 983-1007 (1995) · Zbl 0865.65106 |
| [50] | Bender, C. M.; Orszag, S. A., Advanced Mathematical Methods for Scientists and Engineers (1978), McGraw-Hill: McGraw-Hill New York · Zbl 0417.34001 |
| [51] | Blinnikov, S.; Moessner, R., Expansions for nearly Gaussian distributions, Astronomy and Astrophysics Supplement Series, 130, 193-205 (1998) |
| [52] | Powell, M. J.D., Approximation Theory and Methods (1981), Cambridge University Press · Zbl 0453.41001 |
| [53] | Jurkat, W. B.; Lorentz, G. G., Uniform approximation polynomials with positive coefficients, Duke Mathematical Journal, 28, 463-473 (1961) · Zbl 0112.29002 |
| [54] | Er, G. K., A method for multi-parameter pdf estimation of random variables, Structural Safety, 20, 25-36 (1998) |
| [55] | Frontini, M.; Tagliani, A., Entropy-convergence in Stieltjes and Hamburger moment problem, Applied Mathematics and Computation, 88, 39-51 (1997) · Zbl 0909.44003 |
| [56] | Tagliani, A., On the application of maximum entropy to the moments problem, Journal of Mathematical Physics, 34, 326-337 (1993) · Zbl 0768.44004 |
| [57] | Katznelson, Y., An Introduction to Harmonic Analysis (1968), Wiley: Wiley New York · Zbl 0169.17902 |
| [58] | Gavriliadis, P. N.; Athanassoulis, G. A., Moment data can be analytically completed, Probabilistic Engineering Mechanics, 18, 329-338 (2003) |
| [59] | Li, X.; Le, J.; Gopalakrishnan, P.; Pileggi, L., Asymptotic probability extraction for nonnormal performance distributions, IEEE TCAD, 26, 16-37 (2007) |
| [60] | Coleman, T. F.; Li, Y., A reflective Newton method for minimizing a quadratic function subject to bounds on some of the variables, SIAM Journal on Optimization, 6, 1040-1058 (1996) · Zbl 0861.65053 |
| [61] | Gill, P. E.; Murray, W.; Wright, M. H., Practical Optimization (1981), Academic Press: Academic Press London · Zbl 0503.90062 |
| [62] | Nevai, P.; Freud, Geza, Orthogonal polynomials and Christoffel functions. A case study, Journal of Approximation Theory, 48, 3-167 (1986) · Zbl 0606.42020 |
| [63] | Liu, J. S.; Chen, R., Sequential Monte-Carlo methods for dynamic systems, Journal of American Statistical Association, 93, 1032-1044 (1998) · Zbl 1064.65500 |
| [64] | Richardson, S.; Green, P., On Bayesian analysis of mixtures with unknown number of components, Journal of the Royal Statistical Society B, 59, 731-792 (1997) · Zbl 0891.62020 |
| [65] | Alexandridis, A.; Sarimveis, H.; Bafas, G., A new algorithm for online structure and parameter adaptation of RBF networks, Neural Networks, 16, 1003-1017 (2003) |
| [66] | Chopin, N., A sequential particle filter method for static models, Biometrika, 89, 539-552 (2002) · Zbl 1036.62062 |
| [67] | Inverardi, P. N.; Petri, A.; Pontuale, G.; Tagliani, A., Stieltjes moment problem via fractional moments, Applied Mathematics and Computation, 166, 664-677 (2005) · Zbl 1089.44003 |
| [68] | Cottone, G.; Di Paola, M., On the use of fractional calculus for the probabilistic characterization of random variables, Probabilistic Engineering Mechanics, 24, 321-330 (2009) |
| [69] | Gzyl, H.; Tagliani, A., Stieltjes moment problem and fractional moments, Applied Mathematics and Computation, 216, 3307-3318 (2010) · Zbl 1193.44031 |
| [70] | Pantano, C.; Shotorban, B., A least-squares dynamic approximation method for evolution of uncertainty in initial conditions of dynamical systems, Physical Review E, 76, 066705-066713 (2007) |
| [71] | Sapsis, T. P.; Athanassoulis, G. A., New partial differential equations governing the response-excitation joint probability distributions of nonlinear systems under general stochastic excitation, Probabilistic Engineering Mechanics, 23, 289-306 (2008) |
| [72] | Shotorban, B., Dynamic least-squares kernel density modeling of Fokker-Planck equations with application to neural population, Physical Review E, 81, 046706 (2010) |
| [73] | Athanassoulis, G. A.; Belibassakis, K. A., Probabilistic description of metocean parameters by means of kernel density models 1. Theoretical background and first results, Applied Ocean Research, 24, 1-20 (2002) |
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.
