Inference for Stereological Extremes

In the production of clean steels, the occurrence of imperfections—so-called “inclusions”—is unavoidable. The strength of a clean steel block is largely dependent on the size of the largest imperfection that it contains, so inference on extreme inclusion size forms an important part of quality control. Sampling is generally done by measuring imperfections on planar slices, leading to an extreme value version of a standard stereological problem: how to make inference on large inclusions using only the sliced observations. Under the assumption that inclusions are spherical, this problem has been tackled previously using a combination of extreme value models, stereological calculations, a Bayesian hierarchical model, and standard Markov chain Monte Carlo (MCMC) techniques. Our objectives in this article are twofold: (1) to assess the robustness of such inferences with respect to the assumption of spherical inclusions, and (2) to develop an inference procedure that is valid for nonspherical inclusions. We investigate both of these aspects by extending the spherical family for inclusion shapes to a family of ellipsoids. We then address the issue of robustness by assessing the performance of the spherical model when fitted to measurements obtained from a simulation of ellipsoidal inclusions. The issue of inference is more difficult, because likelihood calculation is not feasible for the ellipsoidal model. To handle this aspect, we propose a modification to a recently developed likelihood-free MCMC algorithm. After verifying the viability and accuracy of the proposed algorithm through a simulation study, we analyze a real inclusion dataset, comparing the inference obtained under the ellipsoidal inclusion model with that previously obtained assuming spherical inclusions.

[1]  S. D. Wicksell,et al.  THE CORPUSCLE PROBLEM. A MATHEMATICAL STUDY OF A BIOMETRIC PROBLEM , 1925 .

[2]  S. D. Wicksell,et al.  THE CORPUSCLE PROBLEM. SECOND MEMOIR CASE OF ELLIPSOIDAL CORPUSCLES , 1926 .

[3]  Tail Behavior in Wicksell’s Corpuscle Problem , 1992 .

[4]  Y. Murakami Inclusion Rating by Statistics of Extreme Values and Its Application to Fatigue Strength Prediction and Quality Control of Materials , 1994, Journal of research of the National Institute of Standards and Technology.

[5]  C. Geyer,et al.  Annealing Markov chain Monte Carlo with applications to ancestral inference , 1995 .

[6]  Masaaki Sibuya,et al.  The maximum size of the planar sections of random spheres and its application to metallurgy , 1996 .

[7]  Masaaki Sibuya,et al.  Prediction of the Maximum Size in Wicksell's Corpuscle Problem , 1998 .

[8]  Stefano Beretta,et al.  STATISTICAL ANALYSIS OF DEFECTS FOR FATIGUE STRENGTH PREDICTION AND QUALITY CONTROL OF MATERIALS , 1998 .

[9]  Helen V. Atkinson,et al.  Application of the generalized pareto distribution to the estimation of the size of the maximum inclusion in clean steels , 1999 .

[10]  C. W. Anderson,et al.  Comparison of extreme value statistics methods for predicting maximum inclusion size in clean steels , 1999 .

[11]  Helen V. Atkinson,et al.  The precision of methods using the statistics of extremes for the estimation of the maximum size of inclusions in clean steels , 2000 .

[12]  G Stolovitzky,et al.  Catalytic tempering: A method for sampling rough energy landscapes by Monte Carlo. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[13]  Metal fatigue, Wicksell transform and extreme values , 2002 .

[14]  Stuart Coles,et al.  The Largest Inclusions in a Piece of Steel , 2002 .

[15]  D. Balding,et al.  Approximate Bayesian computation in population genetics. , 2002, Genetics.

[16]  Eric P. Smith,et al.  An Introduction to Statistical Modeling of Extreme Values , 2002, Technometrics.

[17]  A. Hobolth The spherical deformation model. , 2003, Biostatistics.

[18]  Paul Marjoram,et al.  Markov chain Monte Carlo without likelihoods , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[19]  S. Brooks,et al.  Classical model selection via simulated annealing , 2003, Journal of the Royal Statistical Society: Series B (Statistical Methodology).

[20]  Stereology of Extremes; Shape Factor of Spheroids , 2003 .

[21]  Adrian Baddeley,et al.  Stereology for Statisticians , 2004 .

[22]  Simon Tavaré,et al.  Approximate Bayesian Computation and MCMC , 2004 .

[23]  W. Gilks Markov Chain Monte Carlo , 2005 .

[24]  Andrew R. Francis,et al.  Using Approximate Bayesian Computation to Estimate Tuberculosis Transmission Parameters From Genotype Data , 2006, Genetics.

[25]  Thomas L. Griffiths,et al.  Markov Chain Monte Carlo with People , 2007, NIPS.