Density Estimation and Bump-Hunting by the Penalized Likelihood Method Exemplified by Scattering and Meteorite Data

Abstract The (maximum) penalized-likelihood method of probability density estimation and bump-hunting is improved and exemplified by applications to scattering and chondrite data. We show how the hyperparameter in the method can be satisfactorily estimated by using statistics of goodness of fit. A Fourier expansion is found to be usually more expeditious than a Hermite expansion but a compromise is useful. The best fit to the scattering data has 13 bumps, all of which are evaluated by the Bayesian interpretation of the method. Eight bumps are well supported. The result for the chondrite data suggests that it is trimodal and confirms that there are (at least) three kinds of chondrite.

[1]  Edmund Taylor Whittaker.  XVIII.—On the Functions which are represented by the Expansions of the Interpolation-Theory , 1915 .

[2]  J. Uspensky.  Introduction to mathematical probability , 1938 .

[3]  P. V. Krishna Iyer,et al.  The Theory of Probability Distributions of Points on a Lattice , 1950 .

[4]  I. Good.  The serial test for sampling numbers and other tests for randomness , 1953, Mathematical Proceedings of the Cambridge Philosophical Society.

[5]  I. Good.  On the Serial Test for Random Sequences , 1957 .

[6]  I. Good.  Significance Tests in Parallel and in Series , 1958 .

[7]  I. Good.  Maximum Entropy for Hypothesis Formulation, Especially for Multidimensional Contingency Tables , 1963 .

[8]  R. Omnes.  Mandelstam theory and Regge poles , 1963 .

[9]  R. Omnes and M. Froissart: Mandelstam Theory and Regge Poles, 1963, 121頁. / S.C. Frautschi: Regge Poles and S-Matrix Theory, 1963, 200頁. ともに W. A. Benjamin, Inc., New York, 15×23cm, $4.35. , 1964 .

[10]  Irving John Good,et al.  The Estimation of Probabilities: An Essay on Modern Bayesian Methods , 1965 .

[11]  L. Ahrens,et al.  Observations on the Fe-Si-Mg relationship in chondrites , 1965 .

[12]  I. Good.  A Bayesian Significance Test for Multinomial Distributions , 1967 .

[13]  David G. Kendall,et al.  Spline Transformations: Three New Diagnostic Aids for the Statistical Data‐Analyst , 1971 .

[14]  A. Barbaro-Galtieri,et al.  Observation of an anomally in the π+π− system at 980 MeV☆ , 1971 .

[15]  I. Good.  Nonparametric roughness penalties for probability densities , 1971 .

[16]  K. Mardia.  Statistics of Directional Data , 1972 .

[17]  J. F. Crook,et al.  The Bayes/Non-Bayes Compromise and the Multinomial Distribution , 1974 .

[18]  R. Tapia,et al.  Nonparametric Maximum Likelihood Estimation of Probability Densities by Penalty Function Methods , 1975 .

[19]  R. Kronmal,et al.  An Introduction to the Implementation and Theory of Nonparametric Density Estimation , 1976 .

[20]  A. Barbaro-Galtieri,et al.  Review of Particle Properties, 1976 , 1976 .

[21]  “Squeeze” Significance Tests , 1976 .

[22]  John W. Tukey,et al.  Exploratory Data Analysis. , 1979 .

[23]  G. Wahba.  Optimal Smoothing of Density Estimates , 1977 .

[24]  C9. An improvement in the chi-squared goodness-of-fit test , 1978 .

[25]  C15. A signs test when estimating probability densities , 1978 .

[26]  C14. Moments of the kolmogorov-smirnov one-sample statistic , 1978 .

[27]  Tom Leonard.  Density Estimation, Stochastic Processes and Prior Information , 1978 .

[28]  C25. A comment on runs of signs , 1979 .