×

Theoretical aspects of ill-posed problems in statistics. (English) Zbl 0753.62022

Summary: Ill-posed problems arise in a wide variety of practical statistical situations, ranging from biased sampling and Wicksell’s problem in stereology to regression, errors-in-variables and empirical Bayes models. The common mathematics behind many of these problems is operator inversion. When this inverse is not continuous a regularization of the inverse is needed to construct approximate solutions. In the statistical literature, however, ill-posed problems are rather often solved in an ad hoc manner which obscures these common features.
It is our purpose to place the concept of regularization within a general and unifying framework and to illustrate its power in a number of interesting statistical examples. We will focus on regularization in Hilbert spaces, using spectral theory and reduction to multiplication operators. A partial extension to a Banach function space is briefly considered.

MSC:

62G07 Density estimation
62G05 Nonparametric estimation
65J10 Numerical solutions to equations with linear operators

Software:

spatial
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Armstrong, B., Howe, G., and Whittemore, A. S. (1989), Correcting for measurement error in a nutrition study, Statist. Medicine, to appear.
[2] Bachman G. (1964), Elements of Abstract Harmonic Analysis, Academic Press, New York. · Zbl 0131.13103
[3] Baker C. T. H. (1977), The Numerical Treatment of Integral Equations, Clarendon Press, Oxford. · Zbl 0373.65060
[4] Blum T. and Susarla V. (1977), Estimation of a mixing distribution, Ann. Probab. 5, 200-209. · Zbl 0358.60040 · doi:10.1214/aop/1176995845
[5] Carroll, R. J. (1989), Covariance analysis in generalized linear measurement error models, Statist. Medicine, to appear.
[6] Carroll R. J. and Hall P. (1988), Optimal rates of convergence for deconvolving a density, A. Amer. Statist. Assoc. 83, 1184-1186. · Zbl 0673.62033 · doi:10.2307/2290153
[7] Chang T. (1989), Spherical regression with errors in variables, Ann. Statist. 17, 293-306. · Zbl 0669.62042 · doi:10.1214/aos/1176347017
[8] Choi K. and Bulgren W. (1968), An estimation procedure for mixtures of distributions, J. Roy. Statist. Soc. B 30, 444-460. · Zbl 0187.15804
[9] Cox D. R. (1969), Some sampling problems in technology, in N. L. Johnson and H. SmithJr. (eds.) New Developments in Survey Sampling, Wiley, New York, pp. 506-527.
[10] Deeley J. J. and Kruse R. L. (1968), Construction of sequences estimating the mixing distribution, Ann. Math. Statist. 39, 286-288. · Zbl 0174.22302 · doi:10.1214/aoms/1177698536
[11] Devroye L. P. (1989), Consistent deconvolution in density estimation, Canad. J. Statist. 17, 235-239. · Zbl 0679.62029 · doi:10.2307/3314852
[12] Devroye L. P. and Wise G. L. (1979), On the recovery of discrete probability densities from imperfect measurements, J. Franklin Inst. 307, 1-20. · Zbl 0394.62073 · doi:10.1016/0016-0032(79)90072-3
[13] Eddington A. S. (1913), On a formula for correcting statistics for the effects of a known probable error of observation, Monthly Notices Roy. Astronom. Soc. 73, 359-360. · JFM 44.0278.11
[14] Van Es, A. J. and Hoogendoorn, A. W. (1988), Kernel estimation in Wicksell’s corpuscle problem, Biometrika, to appear. · Zbl 0691.62042
[15] Fan J. (1988), On the optimal rates of convergence for the nonparametric deconvolution problem, Tech. Report # 157, Dept. Statist., Univ. of California, Berkeley.
[16] Fan J. (1989), Adaptively local 1-dimensional subproblems, Institute of Statistics Mimeo Series 2010. Univ. of North Carolina, Chapel Hill.
[17] Gaffey W. R. (1959), A consistent estimator of a component of a convolution, Ann. Math. Statist. 30, 198-205. · Zbl 0092.36602 · doi:10.1214/aoms/1177706375
[18] Gill R. D., Vardi Y. and Wellner J. A. (1988), Large sample theory of empirical distributions in biased sampling models, Ann. Statist. 16, 1069-1112. · Zbl 0668.62024 · doi:10.1214/aos/1176350948
[19] Gilliam, D. S., Hall, P., and Ruymgaart, F. H. (1991), Rate of convergence of the empirical Radon transform, Report Texas Tech Univ. · Zbl 0782.62042
[20] Golub G. H. and Van Loan C. F. (1983), Matrix Computations, The Johns Hopkins Univ. Press, Baltimore. · Zbl 0559.65011
[21] Hall P. and Smith R. L. (1986), The kernel method for unfolding sphere distributions, J. Comput. Phys. 74, 409-421. · Zbl 0637.65148 · doi:10.1016/0021-9991(88)90085-X
[22] Halmos P. R. (1963), What does the spectral theorem say?, Amer. Math. Monthly 70(3), 241-247. · Zbl 0132.35606 · doi:10.2307/2313117
[23] Hasabelnaby, N., Fuller, W. A., and Ware, J. (1989), A measurement error model for the Six Cities data, Statist. Medicine, to appear.
[24] Helgason R. (1980), The Radon Transform, Birkhäuser, Boston. · Zbl 0453.43011
[25] Hendriks H. W. M., Janssen J. H. M., and Ruymgaart F. H. (1989), Strong uniform convergence of density estimators on Stiefel manifolds, Report, Dept. Math., Kath. Univ. Nijmegen. · Zbl 0766.62020
[26] Hewitt E. and Ross K. A. (1963), Abstract Harmonic Analysis, I, Springer, Berlin. · Zbl 0115.10603
[27] Ibragimov I. A. and Rozanov Y. A. (1978), Gaussian Random Processes, Springer, New York. · Zbl 0392.60037
[28] Johnstone I. and Silverman B. W. (1988), Speed of estimation in positron emission tomography and related diverse problems, Ann. Statist. 18, 251-280. · Zbl 0699.62043 · doi:10.1214/aos/1176347500
[29] Kahn F. D. (1955), The correction of observational data for instrumental bandwidth, Proc. Cambridge Phil. Soc. 51, 519-525. · Zbl 0065.33801 · doi:10.1017/S0305004100030528
[30] Krasnosel’skii M. A., Vainikko G. M., Zabreiko P. P., Rutitskii Ya.B., and Stetsenko V. Ya. (1972), Approximate Solution of Operator Equations, Wolters-Noordhoff, Groningen.
[31] Lasota A. and Mackey M. C. (1985), Probabilistic Properties of Deterministic Systems, Cambridge Univ. Press, Cambridge. · Zbl 0606.58002
[32] LinnikJu. V. and Ostrovskii I. V. (1977), Decomposition of Random Variables and Vectors, Amer. Math. Soc., Rhode Island.
[33] Linz P. (1985), Analytical and Numerical Methods for Volterra Equations, Soc. Ind. Appl. Math., Philadelphia. · Zbl 0566.65094
[34] Liu, M. C. and Taylor, R. L. (1989a), A consistent nonparametric density estimator for the deconvolution problem, Canad. J. Statist., to appear. · Zbl 0694.62017
[35] Liu, M. C. and Taylor, R. L. (1989b), Simulations and computations of nonparametric density estimates for the deconvolution problem, J. Statist. Comput. Simulation, to appear.
[36] Loomis L. H. (1953), An Introduction to Abstract Harmonic Analysis, Van Nostrand, New York. · Zbl 0052.11701
[37] Ludwig D. (1966), The Radon transform on Euclidean space, Comm. Pure Appl. Math. 19, 49-81. · Zbl 0134.11305 · doi:10.1002/cpa.3160190105
[38] Luenberger D. G. (1969), Optimization by Vector Space Methods, Wiley, New York. · Zbl 0176.12701
[39] Mardia K. V. (1975), Statistics of Directional Data, Academic Press, New York. · Zbl 0314.62026
[40] Maritz J. S. (1970), Empirical Bayes Methods, Methuen, London. · Zbl 0245.62001
[41] Mendelsohn J. and Rice J. (1982), Deconvolution of microfluorometric histograms with B-splines, J. Amer. Statist. Assoc. 77, 748-753. · doi:10.2307/2287301
[42] Molina R. and Ripley B. D. (1989), Using spatial models and priors in astronomical image analysis, J. Appl. Statist. 16, 193-206. · doi:10.1080/02664768900000017
[43] Nychka D. W. and Cox D. D. (1989), Convergence rates for regularized solutions of integral equations from discrete noisy data, Ann. Statist. 17, 556-572. · Zbl 0672.62054 · doi:10.1214/aos/1176347125
[44] Nychka D. W., Wahba G., Goldfarb S., and Pugh T. (1984), Cross-validated spline methods for the estimation of three dimensional tumor size distributions from observations on two-dimensional cross sections, J. Amer. Statist. Assoc. 79, 832-846. · Zbl 0572.62085 · doi:10.2307/2288713
[45] O’Sullivan F. (1986), A statistical perspective on ill-posed inverse problems, Statist. Sci. 4, 502-527. · Zbl 0955.65500 · doi:10.1214/ss/1177013525
[46] Parzen E. (1961), An approach to time series analysis, Ann. Math. Statist. 32, 951-989. · Zbl 0107.13801 · doi:10.1214/aoms/1177704840
[47] Pogorzelski W. (1966), Integral Equations and their Applications, I, Pergamon, Oxford. · Zbl 0137.30502
[48] Preston P. F. (1971), Estimating the mixing distribution by piecewise polynomial arcs, Austral. J. Statist. 13, 64-76. · Zbl 0245.62044 · doi:10.1111/j.1467-842X.1971.tb01244.x
[49] Rao C. R. (1965), Linear Statistical Inference and its Applications, Wiley, New York. · Zbl 0137.36203
[50] Riesz F. and Nagy B.Sz. (1955), Functional Analysis, Ungar, New York. · Zbl 0070.10902
[51] Ripley B. D. (1981), Spatial Statistics, Wiley, New York. · Zbl 0583.62087
[52] Ruymgaart F. H. (1989), Strong uniform convergence of density estimators on spheres, J. Statist. Plann. Inference 23, 45-52. · Zbl 0685.62039 · doi:10.1016/0378-3758(89)90038-4
[53] Silverman B. W., Jones M. C., Wilson J. D., and Nychka D. W. (1990), A smoothed EM approach to indirect estimation problems, with particular reference to stereology and emission tomography (with discussion), J. Roy. Statist. Soc. Ser. B 52, 271-325. · Zbl 0703.62105
[54] Springer M. D. (1979), The Algebra of Random Variables, Wiley, New York. · Zbl 0399.60002
[55] Stefanski, L. A. (1989), Rates of convergence of some estimators in a class of deconvolution problems, Statist. Probab. Lett., to appear.
[56] Stefanski, L. A. and Carroll, R. J. (1989), Deconvolution and score tests in generalized linear measurement error models, Ann. Statist., to appear.
[57] Stefanski, L. A. and Carroll, R. J. (1990), Deconvoluting kernel density estimators, Statistics, to appear. · Zbl 0697.62035
[58] Stromberg K. R. (1981), An Introduction to Classical Real Analysis, Wadsworth, Belmont, Calif. · Zbl 0454.26001
[59] Taylor A. E. (1958), Introduction to Functional Analysis, Wiley, New York. · Zbl 0081.10202
[60] Taylor C. C. (1982), A new method for unfolding sphere size distributions, J. Microscopy 132, 57-66.
[61] Tikhonov A. N. and Arsenin V. Y. (1977), Solutions of Ill-Posed Problems, Wiley, New York. · Zbl 0354.65028
[62] Titterington D. M. (1985), Common structure of smoothing techniques in statistics. Internat. Statist. Rev. 53, 141-170. · Zbl 0569.62026 · doi:10.2307/1402932
[63] Tosteson, T., Stefanski, L. A., and Schafer, D. W. (1989), A measurement error model for binary and ordinal regression, Statist. Medicine, to appear.
[64] Tosteson T. and Tsiatis A. (1988), The asymptotic relative efficiency of score tests in the generalized linear model. Biometrika 75, 507-514. · Zbl 0653.62076 · doi:10.1093/biomet/75.3.507
[65] Tricomi F. G. (1957), Integral Equations, Interscience, New York. · Zbl 0078.09404
[66] Trumpler R. J. and Weaver H. F. (1963), Statistical Astronomy, Univ. California Press, Berkeley. · Zbl 0053.48401
[67] Vapnik V. (1982), Estimation of Dependences Based on Empirical Data, Springer, New York. · Zbl 0499.62005
[68] Vardi Y. (1989), Multiplicative censoring, renewal processes, deconvolution and decreasing density: nonparametric estimation, Biometrika 76, 751-761. · Zbl 0678.62051 · doi:10.1093/biomet/76.4.751
[69] Wahba G. (1971), On the regression design problem of Sacks and Ylvisaker, Ann. Math. Statist. 42, 1035-1053. · Zbl 0221.62027 · doi:10.1214/aoms/1177693331
[70] Whittemore A. S. and Keller J. B. (1988), Approximations for errors in variables regression, J. Amer. Statist. Assoc. 83, 1057-1066. · Zbl 0672.62078 · doi:10.2307/2290136
[71] Wise G. L., Traganitis A. P., and Thomas J. B. (1977), The estimation of a probability density funetion from measurements corrupted by Poisson noise, IEEE Trans. Inform. Theory 23, 764-766. · Zbl 0368.62099 · doi:10.1109/TIT.1977.1055802
[72] Zhang C. H. (1990), Fourier methods for estimating mixing densities and distributions, Ann. Statist. 18, 806-831. · Zbl 0778.62037 · doi:10.1214/aos/1176347627
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.