Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Curriculum Vitae Henry P. Wynn Department of Statistics, London School of Economics January 14, 2015 1 Personal Date of Birth: 19 February 1945 Address, Home 9 Lloyd Square, London, WC1X 9BA, UK Tel/Fax: +44 (0) 207 833 2625 Mobile: +44 (0) 777 332 338 Address, work Department of Statistics, London School of Economics, Houghton Street, London WC2A 2AE, UK Tel: +44 (0) 207 955 6063 Fax: +44 (0) 207 955 7416 E-mail: [email protected] 2 Degrees 1976 MA Honours Mathematics University of Oxford 1970 PhD Mathematical Statistics Imperial College, University of London Title: ”The theory and construction of optimal experimental design” 3 Employment 2010 - present. Emeritus Professor Statistics, London School of Economics. 2003 - 2010. Professor of Statistics, London School of Economics. 2003-2006. Head of the Department of Statistics, London School of Economics. 2000 - 2005. Scientific co-Director EURANDOM, Eindhoven, the Netherlands (part-time) 1995 - 2003 Professor of Industrial Statistics. Director of The Warwick Risk Initiative and Statistical Consultancy Unit (RISCU), University of Warwick 1990 - 1995 Co-Director, Engineering Design and Quality Centre, City University. London 1 1983 - 1995 Dean of School of Mathematics, Actuarial Science and Statistics, City University, London 1985 - 1995 Professor of Mathematical Statistics, City University, London 1983 - 1985 Head of Statistics Section, Mathematics Department, Imperial College, London 1979 - 1985 Reader in Statistics, Mathematics Department, Imperial College, London 1975 - 1976 (on leave) Assistant Professor, University of California, Berkeley 1973 - 1979 Lecturer in Statistics, Imperial College, London 1972 - 1973 Statistician, Government Statistical Service, Inland Revenue Department. (Company taxation section, financial forecasting for the Budget, etc.) 1970 - 1972 Research Fellow, Statistics, University of Kent at Canterbury. (Responsibility for SSRC project ”Stochastic Analysis of National Manpower Systems”. Director: Professor D J Bartholomew) 4 Honours Elected President of the Royal Statistical Society (1977/78) Member of International Statistical Institute, (1979) Guy Medal in Silver, Royal Statistical Society (1982) Fellow of the Institute of Mathematical Statistics (1988) Member of the International Statistical Institute (1988) Honorary Fellow, Institute of Actuaries (1999) Box Medal, European Network for Business and Industrial Statistics (ENBIS) (2012) 5 Other activities Member of SERC Complex Stochastic Systems Panel (1990-92) Member of the London Mathematical Society Committee on 4-year degrees (1991-92) Member of the IEE Committee on Simultaneous Engineering (1992-93) Member of Royal Statistical Society Quality Committee (1994-95) Member of Committee for the Thames Gateway Technology Centre Science Park, University of East London (1992-95) Member of Biometrics Advisory Committee, GlaxoSmithKline (1999-2007) Chairman of the Royal Statistical Society Conference (1999) (Theme: risk) 2 Chairman of the Advisory Council, Centre for Coastal and Marine Sciences (NERC) (19982000) Member of EPSRC Mathematics Prioritisation Panel (1998) President, ENBIS: European Network for Business and Industrial Statistics:2000-2001 Member: EPSRC Critical Mass panel. 2004 Member: EPSRC Mathematics Prioritization Panel (2005) Member: Steering Group and Advisory Group, EU Network of Excellence: PASCAL (2004-present) Chairman, Scientific Advisory Board, Norwegian statistical research Centre SFI: Statistics for Innovation. (2007-present) Member, Scientific Advisory Board, Canadian National Programme on Complex Date Structures. (2006 -2009) Member, Advisory panel, CRISM, Univerity of Warwick (2007-present) Member, Advisory panel, Institute for Mathematical Sciences, Imperial College (20092012) 6 6.1 Research Recent Grants EU: HIPCON: Holistic Integrated Process Control. February 2003 - January 2006 Partner/contractor. £346,667. EPSRC. µ-RED: Micro-scale Robust Engineering Design Engineering. Contract no. GR/S63502/01. July 2004 - June 2007. £ 144,633. Research Councils UK. MUCM I, II: Managing Uncertainty in Complex models Contract no. EP/H007377/1. October 2006 - September 2012. Partner. £ 295,210. Leverhulme Trust. Advances in Algebraic Statistics. Emeritus Fellowship. July 2001 September 2012. £11, 000 Leverhulme Trust. Advances in Algebraic Statistics. Emeritus Fellowship. July 2001 September 2012. £11, 000. Leverhulme Trust. Advances in Algebraic Statistics. Emeritus Fellowship. July 2001 September 2012. £11, 000. EU: CELSIUS - Combined Efficient Large Scale Integrated Urban Systems. Lead Research Organisation: City of Gothenburg. Principal Investigator at LSE: Professor Henry Wynn. April 2013 - March 2017. £310,000. 3 6.2 Research leadership At City University was a major contributor to the research programme as co-applicant on a large EPSRC initiative in engineering design and was co-Director of the Engineering Design Centre, which has strong position on the interface between statistics and engineering. In addition was strongly represented with own research grants. At Warwick, was Founding Director of RISCU, the combined Risk Initiative and Statistical Consultancy Unit, at the University of Warwick, which grew rapidly and was well support by research funding, particularly EU grants. At present, Director of my own research group, DSRG: Decision Support and Risk Group, with one post-doc and two PhD students. Chair of CATS: Centre for the Analysis of Time Series, LSE (Director Professor L Smith). As (part-time) Scientific co-Director of EURANDOM for five years was involved in research directions particularly related to the building of theoretical and applied statistics and EU and industrial grants. In 2001 helped to found ENBIS: the European Network for Business and Industrial Statistics and was one the founding Presidents. It now has over 1000 members and an annual conference. 6.2.1 Research Students Circa 15 during career. 6.3 6.3.1 Research interests Experimental design Been involved with some of the major advances in experimental design theory since 1970 stemming from the work in optimal experimental design initiated by J Kiefer and co-workers. This includes algorithms, design for correlated and spatial processes, including the introduction of Maximum Entropy Sampling, computer experiments and the application of Gröbner basis methodology (see below). In all these areas was author or co-author of among the first papers in the field. 6.3.2 Discrete tube theory Long-standing collaboration with D Q Naiman (John Hopkins) has led to a series of papers, creating the field of discrete tube theory. These yield tight inclusion-exclusion bounds for a number of important problems in multiple comparisons and stochastic geometry. The work has also made a links to V-C dimension, computational geometry and more, recently to reliability (see below). 6.3.3 Engineering applications and computer experiments Intimately involved with the introduction of robust engineering design methodologies into the UK following extensive workshops in the US. This work has led to papers in engineering literature and extensive collaboration with industrial partners which extends into more general 4 aspects of product development. Particular expertise in computer experiments, that is the emulation of large-scale simulators, and complex modelling of engineering and related processes. Much of the work is joint with R A Bates. 6.3.4 Search and optimisation Joint with A Zhigliavsky and L Pronzato, initiated this area. By careful renormalization certain search and optimization algorithms can be turned into dynamical systems and convergence rates link to Kolmogorov/Shannon entropy and generalisations. Recent work involves a detailed study of the steepest ascent algorithm’s attractor properties in finite and infinite dimensions. 6.3.5 Algebraic Statistics The use of computational algebraic geometry in statistics. This activity has grown into a more ambitious programme to apply computer algebra to discrete statistical methods, both in the static case and via differential algebras to dynamic modelling. In addition to the innovative use of computational algebraic geometry in statistics, there have been spin-offs into real applications, including industrial experimentation, system reliability, compartmental modelling in biology, and functional approximation of various kinds, categorical data analysis and graphical models. Much of the work is joint with G Pistone and E Riccomagno (Politecnico Torino) (see joint monograph). Work with P E Caines (McGill) and R Deardon (Guelph) covers application to graphical models for time series. Work with E Sánz-de-Cabazon I(Rioja) uses the theory of minimal free resolution in reliability and related probability methods. Recent work with K. Kobayashi looks at the interface between algebraic and information geometry. 6.3.6 Stochastic orderings and group invariant orderings Extensive joint work with Professor Alessandra Giovagnoli (Bologna) began with applications of groups invariant ordering to experimental design but has widened. Notable is the introduction of the D-ordering to describe multivariate dispersion and recent work covers stochastic ordering for discrete sets and measures of agreement. The most recent paper generalises the duality between Lorenz ordering and second order stochastic dominance. Recent work with A Francis (Sydney) looks at confidence nets generated by groups. 6.3.7 Risk This is an expanding area of research activity, stimulated by live contacts with risk issues in both the commercial and private sectors, and across disciplines: physical, financial, environmental, medical. Special projects include environmental impact, risk in product development, human factors, decision support, supply chain risk, capital funding risk 6.3.8 Cities As PI on the Celsius programme, which is part of the EU ”Smart Cities” initiative a major interest in infra structure in cities, in particular district heating and cooling. Papers are planned on many aspects, but particularly socio-economic. 5 6.4 6.4.1 Research output Monographs and edited volumes 1. MODA 5 - Advances in Model-Oriented Data Analysis and Experimental Design: Proceedings of the 5th International Workshop in Marseilles, France, June 22-26, 1998 (Contributions to Statistics) by Anthony C. Atkinson, Luc Pronzato, and Henry P. Wynn (eds). Physica Verlag. 2. Pronzato, L., Wynn, H. P. and Zhigljavsky, A. A. Dynamical Search: Applications of Dynamical Systems in Search and Optimization (Interdisciplinary Statistics). Chapman & Hall/CRC, Boca Raton, FL, 1999. 3. Pistone, G., Riccomagno, E and Wynn, H. P. Algebraic statistics. Computational commutative algebra in statistics. Monographs on Statistics and Applied Probability, 89. Chapman & Hall/CRC, Boca Raton, FL, 2001. 4. mODa 7 - Advances in Model-Oriented Design and Analysis: Proceedings of the 7th International Workshop on Model-Oriented Design and Analysis. 2004 (Contributions to Statistics) by Alessandro Di Bucchianico, Henning Luter, and Henry P. Wynn (eds) Physica Verlag. 5. Algebraic and Geometric Methods in Statistics. (Volume in honour of G. Pistone). E. Riccomagno, M Rigontin, H. P. Wynn (eds). Springer Verlag. 2008. 6. Algebraic methods in statistics and probability II. M Viana, H. P. Wynn (eds). American Mathematical Society, Contemporary Mathematics, 287 (2010) 6.4.2 Publications 2014 1. Kobayashi, Kei, and Henry P. Wynn. “Computational algebraic methods in efficient estimation.” Geometric Theory of Information. Springer International Publishing, 2014. 119-140. 2. Atherton, Mark A., Ronald A. Bates, and Henry P. Wynn. “Dimensional analysis using toric ideals: Primitive invariants.” PloS one 9.12 (2014): e112827 3. Saenz-de-Cabezon, Eduardo and Wynn, Henry P. (2014) Hilbert functions in design for reliability IEEE Transactions on Reliability, PP (99). 1-11. ISSN 0018-9529 4. Francis, Andrew R. and Wynn, Henry P. (2014) Subgroup majorization Linear Algebra and Its Applications, 444. 53-66. ISSN 0024-3795 5. Saenz-de-Cabezon, E. and Wynn, H. P. (2014) Measuring the robustness of a network using minimal vertex covers Mathematics and Computers in Simulation, 104. 82-94. ISSN 0378-4754 6. Bates, Ron A. and Curtis, Peter R. and Maruri-Aguilar, Hugo and Wynn, Henry P. (2014) Optimal design for smooth supersaturated models Journal of Statistical Planning and Inference, 154. 3-11. ISSN 0378-3758 6 7. Bates, Ron A. and Maruri-Aguilar, Hugo and Wynn, Henry P. (2014) Smooth supersaturated models Journal of Statistical Computation and Simulation, 84 (11). 2453-2464. ISSN 0094-9655 8. Hainy, M. and Mller, W.G and Wynn, Henry P. (2014) Learning functions and approximate Bayesian computation design: ABCD Entropy, 16 (8). 4353-4374. ISSN 1099-4300 2013 9. Maruri-Aguilar, Hugo and Saenz-de-Cabezon, Eduardo and Wynn, Henry P. (2013) Alexander duality in experimental designs Annals of the Institute of Statistical Mathematics, 65 (4). 667-686. ISSN 0020-3157 10. Saenz-de-Cabezon, E. and Wynn, Henry P. (2013) Computational commutative algebra for tight network reliability bounds In: Steenbergen, R.D.J.M. and Van Gelder, P.H.J.M. and Miraglia, S. and Vrouwenvelder , A.C.W.M., (eds.) Safety, reliability and risk analysis: beyond the horizon. CRC Press, Boca Raton, USA, 1271-1277. ISBN 9781138001237 2012 11. Maruri-Aguilar, H., Sáenz-de-Cabezón, E. and Wynn, P. Betti numbers on polynomial hierarchical models for experimental designs. Ann. Math. Artif. Intell.(2012), 64, 411426. 12. Giovagnoli, A and Wynn, H. P. (U,V)-ordering and a duality theorem for risk aversion and Lorentz-type ordering. LSE Philosophy papers (2012). 13. Di Bucchianico, A. Wynn, H.P. The ENBIS-11 Quality and Reliability Engineering International Special Issue. Quality and Reliability Engineering International,(2012) 2, 498-499. 14. Hayter, A. J. and Kiatsupaibul, S. and Liu, W. and Wynn, H. P. An independence point method of confidence band construction for multiple linear regression models. Communications in statistics: theory and methods, (2012), 41, 4132-4141. 2011 15. Sáenz-de-Cabezón, E, and Wynn, H. P. Computational algebraic algorithms for the reliability of generalized k-out-of-n and related systems. Math. Comput. Simulation (2011), 82, 6878 2010 16. Sáenz-de-Cabezón, E. and Wynn, H. P. Mincut ideals of two-terminal networks. Appl. Alg. Eng. Comm. Comp. (2010) 21, 443-457. 7 17. Bernstein, Y., Maruri-Aguilar, H., Shmuel O, Riccomagno, E and Wynn, H.P. Minimal average degree aberration and the state polytope for experimental designs. Annals of the Institute of Statistical Mathematics, (2010), 62, 673-698. 2009 18. Sáenz-de-Cabezón, E., and Wynn, H. P. Betti numbers and minimal free resolutions for multi-state system reliability bounds. J. Symb. Comp. (2009), 22, 1311-1325. 19. Maruri-Aguilar, H. and Wynn, H.P. Generalised designs. In: Algebraic and Geometric Methods in Statistics. Cambridge University Press. 20. Haycroft, R., Pronzato, L., Wynn, H. P. and Zhigljavsky, A. A. Studying convergence of gradient algorithms via optimal experimental design. In : Optimal Design and Related Areas in Statistics. Springer: Optimization and related areas: 28 (2009), 13-37. 21. Pronzato, L., Wynn, H. P. and Zhigljavsky, A. A. A dynamical system analysis of the optimal s-step gradient algorithm. In : Optimal Design and Related Areas in Statistics. Springer: Optimization and related areas: 28 (2009),39-80. 22. Giovagnoli, A, Marzialetti, J. and Wynn, H. P. Bivariate dependence orderings for uncorrelated categorical variables. In : Optimal Design and Related Areas in Statistics. Springer: Optimization and related areas: 28 (2009), 81-96. 23. Caines, P E., Deardon, R. and Wynn, H. P. Bayes nets of time series. Stochastic realisations and projections. In : Optimal Design and Related Areas in Statistics. Springer: Optimization and related areas: 28 (2009), 155-166. 2008 24. Haycroft, R., Pronzato, L., Wynn, H. OP. and Zhigljavsky, A.A. Optimal experimental design and quadratic optimization. Tatra Mt. Mtha. Publ. 39, 115-123. 25. Liu, W., Wynn H. P., Hayter, A. J. Statistical inferences for linear regression models when the covariates have functional relationships: polynomial regression. J. Stat. Comp. Sim. (2008), 78, 315-324. 26. Giovagnoli, A and Wynn, H. P. Stochastic orderings for discrete random variables. Statistics and Probability letters. (2008), 78, 2827-2835. 27. Perry M. A., Bates R. A., and Atherton, M. A. A finite-element-based formulation for sensitivity studies of piezoelectric systems. Smart Materials and structures. 17, (2008), (7pp). 28. Berstein, Y., Lee, J., Maruri-Aguilar, H., Onn, S., Riccomagno, E., Weismantel, R., and Wynn, H.P. Henry Nonlinear matroid optimization and experimental design. SIAM J. Discrete Math. 22 (2008), 901–919 29. Wynn, H. P. Algebraic solutions to the connectivity problem for m-way layouts: interactioncontrast aliasing. J. Statist. Plan. Inference 138 (2008), 259–271. 8 30. Giovagnoli, A, Marzialetti, J. and Wynn, H. P. A new approach to inter-rater agreement through stochastic orderings: the discrete case. Metrika. 67 (2008), 349-370. 31. Perry, M.A., Atherton, M.A., Bates, M. A., Shen, Y. and Wynn, H. P. Bond Graph Based Sensitivity and Uncertainty Analysis Modelling for Micro-Scale Multiphysics Robust Engineering Design. J. Franklin Inst. 345 (2008), 282-292. 2007 32. Caines, P. E.; Wynn, H. P. An algebraic framework for Bayes nets of time series. Modeling, estimation and control, 45–57, Lecture Notes in Control and Inform. Sci., 364, Springer, Berlin, 2007. 33. Liu, W., Hayter, A. J., Wynn, H. P. Operability region equivalence: simultaneous confidence bands for the equivalence of two regression models over restricted regions. Biom. J. 49 (2007), 144–150. 34. Bates, R. A., Wynn, H. P., Fraga, E. Feasible region approximation: a comparison of search cone and convex hull methods. Journal of Engineering Optimisation, 39 (2007), 513-527. 35. Hayter, A. J., Liu, W. and Wynn, H. P. Easy-to-construct confidence bands for comparing two simple linear regression lines. J. Statist. Plann. Inference 137 (2007), 1213–1225. 2006 36. Pistone, G., Riccomagno, E. and Wynn, H. P. A note on computational algebra for discrete statistical models. Constructive algebra and systems theory, 341–347, Verh. Afd. Natuurkd. 1. Reeks. K. Ned. Akad. Wet., 53, R. Neth. Acad. Arts Sci., Amsterdam, 2006. 37. Perry, M. A., Wynn, H. P. and Bates, R, A. Principal component analysis in sensitivity studies of dynamic systems. Prob. Eng. Mech. (2006), 21, 454p–460. 38. Bates, R. A., Kenett, R. S. an d Steinberg, D. M. Robust design using computer experiments. 13th European Symposium on Mathematics in Industry (ESMI), 2004, Eindhoven, Netherlands. In: Progress in Industrial Mathematics at ECMI 2004 Book Series: Mathematics in industry, 564-568 (published 2006). 39. Bates, R. A., Kenett, R. S. and Steinberg, D. M. and Wynn, H. P. Achieving robust design from computer simulations. Qual. Technol. Quant. Manag. 3 (2006), 161–177. 40. Hayter, A. J., Wynn, H. P. and Liu, W. Slope modified confidence bands for a simple linear regression model. Stat. Methodol. 3 (2006), 186–192. 41. Pronzato, L., Wynn, H. P. and Zhigljavsky, A. A. Asymptotic behaviour of a family of gradient algorithms in Rd and Hilbert spaces. Math. Program. 107 (2006), Ser. A, 409–438. 42. Pistone, G. and Wynn, H. P. Cumulant varieties. J. Symbolic Comput. 41 (2006), 210–221. 9 2005 43. Naiman, D. Q., Wynn, H. P. The algebra of Bonferroni bounds: discrete tubes and extensions. Metrika. 62 (2005), 139–147. 44. Wynn, H. P., Figarella, T., Di Bucchianico, A., Jansen, M. H., Bergsma, W. P. End of life analysis. Modern statistical and mathematical methods in reliability, 73–86, Ser. Qual. Reliab. Eng. Stat., 10, World Sci. Publ., Singapore, 2005. 45. Pistone, G.; Riccomagno, E.; Wynn, H. P. Polynomial ideals, monomial bases and a divided difference formula. Rend. Istit. Mat. Univ. Trieste 37 (2005), 121–144. 46. Pronzato, L., Wynn, H. P.; Zhigljavsky, A. A. Kantorovich-type inequalities for operators via D-optimal design theory. Linear Algebra Appl. 410 (2005), 160–169. 2004 47. di Bucchianico, A., Figarella, T., Hgusken, G., Jansen. M. H. and Wynn, H.P. A Multi-scale approach to functional signature analysis for product end-of-life management. Qual. Rel. Eng. Int, 20 (2004), 457–467. 48. Gasparini, M., Gabriella, M and Wynn, H. P. Dynamic risk control for project development. Stat. Methods Appl. 13, 73-88. 49. Wynn, H. P. Maximum entropy sampling and general equivalence theory. mODa 7: Advances in model-oriented design and analysis, 211–218, Contrib. Statist., Physica, Heidelberg, (2004). 50. Gasparini, M., Margaria, G. and Wynn, H. P. Dynamic risk control for project development. Stat. Methods Appl. 13 (2004), 73–88. 51. Bates, R. A. and Wynn. H. P.. Modelling feasible design regions using lattice-based kernel methods. Quality And Reliability Engineering International. 20 (2004),135–142. 52. Giglio, B and Wynn, H. P. Monomial ideals and the Scarf complex for coherent systems in reliability theory. Ann. Statist. 32 (2004), 1289–1311. 2003 53. Caines, P. E., Deardon, R. and Wynn, H. P. Conditional orthogonality and conditional stochastic realization. Directions in mathematical systems theory and optimization, 71–84, Lecture Notes in Control and Inform. Sci., 286, Springer, Berlin, 2003. 54. Giglio, B. and Wynn, H. P. Alexander duality and moments in reliability modelling. Appl. Algebra Engrg. Comm. Comput. 14 (2003), 153–174. 55. Bates, R. A., Giglio, B. and Wynn, H. P. A global selection procedure for polynomial interpolators. Technometrics 45 (2003), 246–255. 2002 10 56. Giglio, B., Naiman, D. Q. and Wynn, H. P. Grbner bases, abstract tubes, and inclusionexclusion reliability bounds. IEEE Transactions on Reliability, 51 (2002), 358–366. 57. Pronzato, L., Wynn, H. P. and Zhigljavsky, A. A. An introduction to dynamical search. Handbook of global optimization, Vol. 2, 115–150, Nonconvex Optim. Appl., 62, Kluwer Acad. Publ., Dordrecht, 2002. 58. Puch, R. O., Astrup, P., Smith, J. Q., Wynn, H.P., Turcanu, C. and Rojas-Palma, C. A data assimilation methodology for the plume phase of a nuclear accident. In: Development and application of computer techniques to environmental studies. (2002), 129–138. WIT Press. 59. Bates, R. A. and Wynn, H. P. The optimisation of multivariate response criteria. In I C Parmee, editor, Adaptive Computing in Design and Manufacture, pages 285294. Springer, 2002. 60. Bates, R. A. and Wynn, H. P. Advanced polynomial emulation for robust engineering design. In P D Gosling, editor, Proceedings of the 4th ASMO UK/ISSMO Conference on Engineering Design Optimization, pages 029034. MCB University Press, 2002. 2001 61. Sebastiani, P. and Wynn, H. P. Experimental design to maximize information. Bayesian inference and maximum entropy methods in science and engineering (Gif-sur-Yvette, 2000), 192–203, AIP Conf. Proc., 568, Amer. Inst. Phys., Melville, NY, 2001. 62. Pistone, G., Riccomagno, E. and Wynn, H. P. Computational commutative algebra in discrete statistics. Algebraic methods in statistics and probability (Notre Dame, IN, 2000), 267–282, Contemp. Math., 287, Amer. Math. Soc., Providence, RI, 2001. 63. Wynn, H. P. and Sebastiani, P. The quantization of the attention function under a Bayes information theoretic model. Bayesian inference and maximum entropy methods in science and engineering (Gif-sur-Yvette, 2000), 159–168, AIP Conf. Proc., 568, Amer. Inst. Phys., Melville, NY, 2001. 64. Naiman, D. Q. and Wynn, H. P. Improved inclusion-exclusion inequalities for simplex and orthant arrangements. JIPAM. J. Inequal. Pure Appl. Math. 2 (2001), Article 18. 65. Pistone, G., Riccomagno, E. and Wynn, Henry P. Gröbner bases and factorisation in discrete probability and Bayes. Stat. Comput. 11 (2001), 37–46. 66. Pistone, G., Riccomagno, E. and Wynn, H. P. Understanding aliasing using Grbner bases. mODa 6—advances in model-oriented design and analysis (Puchberg/Schneeberg, 2001), 211–216, Contrib. Statist., Physica, Heidelberg, 2001. 67. Margaria, G., Riccomagno, E., Chappell, Michael M.J. and Wynn, H. P. Differential algebra methods for the study of the structural identifiability of rational function statespace models in the biosciences. Math. Biosci. 174 (2001), 1–26. 11 68. Pronzato, L., Wynn, H. P. and Zhigljavsky, A. A. Some convergence properties of the steepest descent algorithm revealed by renormalisation. Advances in convex analysis and global optimization (Pythagorion, 2000), 459–471, Nonconvex Optim. Appl., 54, Kluwer Acad. Publ., Dordrecht, 2001. 69. Pronzato, L., Wynn, H. P. and Zhigljavsky, A. A. Renormalised steepest descent in Hilbert space converges to a two-point attractor. Acta Appl. Math. 67 (2001), 1–18. 70. Pronzato, L., Wynn, H. P. and Zhigljavsky, A. A. Analysis of performance of symmetric second-order line search algorithms through continued fractions. IMA J. Math. Control Inform. 18 (2001), 281–296. 71. Giglio, B., Wynn, H. P.; Riccomagno, Eva. Gröbner basis methods in mixture experiments and generalisations. Optimum design 2000 (Cardiff), 33–44, Nonconvex Optim. Appl., 51, Kluwer Acad. Publ., Dordrecht, 2001. 72. Giglio, B and Wynn, H. P. Discrete tube bounds for complexity reduction in reliability modelling. In ESREL 2001: European Safety & Reliability International Conference, Torino, Italy, Towards a safer world, 2, 1117–1122. 73. Pistone, G., Riccomagno, E and Wynn, H. P. Gröbner bases and factorizations in discrete probability and Bayes. Statistics and Computing. 11 (2001), 37-46. 74. Pistone, G., Riccomagno, E and Wynn, H. P. Computational commutative algebra in discrete statistics. American Mathematical Society Contemporary Mathematics. 287 (2001), 267–281. 2000 75. Sebastiani, P and Wynn, H. P. The quantisation of the attention function under a Bayes information theoretic model. Bayesian inference and maximum entropy methods in science and engineering. Ed A. Mohammad-Djafari. American Institute of Physics, New York, (2000). 159-168. 76. Sabastiabni, P and Wynn, H.P. Experimental design to maximise information. Bayesian inference and maximum entropy methods in science and engineering”. Ed A. MohammadDjafari. American Institute of Physics, New York, (2000). 192-203. 77. Puch, R, 0., Astrup, P., Smith, J. Q., Turcanu, C., Rojas-Palma., and Wynn, H. P. A Data Assimilation Methodology for the Plume Phase of a Nuclear Accident”. (2000), 129–138. 78. Giglio, B., Riccomagno, E. Wynn, H. P. Grbner basis strategies in regression. J. Appl. Statist. 27 (2000), 923–938. 79. Sebastiani, P. and Wynn, H. P. Maximum entropy sampling and optimal Bayesian experimental design. J. R. Stat. Soc. Ser. B Stat. Methodol. 62 (2000), 145–157. 80. Giglio, B., Naiman, D. and Wynn, H. P. Abstract tube theory and Groebner bases for imporved inclusion-exclusion reliability bounds. In Laboratoire Statistique Mathematique et ses Applications, editor, MMR’2000 - Second International Conference on 12 Mathematical Methods in Reliability”, Universite Victor Segalen, Bordeaux, volume 1: 451-454. 81. Bates, R.A., Fontana, R., Randazzo, C., Vaccarino, E. and Wynn, H. P. Empirical modelling of diesel engine performance for robust engineering design. In S P Edwards, DM Grove, and H P Wynn, editors, Statistics for Engine Optimization, pages 163174. Professional Engineering Publishing, 2000. 1999 82. Pistone, G. and Wynn, H. P. Finitely generated cumulants. Statist. Sinica. 9 (1999), 1029–1052. 83. Holliday, T., Pistone, G., Riccomagno, E. and Wynn, H. P. The application of computational algebraic geometry to the analysis of designed experiments: a case study. Comput. Statist. 14 (1999), 213–231. 84. Pronzato, L., Wynn, H. P. and Zhigljavsky, A. A. Finite sample behaviour of an ergodically fast line-search algorithm. Comput. Optim. Appl. 14 (1999), 75–86. 85. Arthur, J, McCarthy, A., Harley, P and Wynn, H.P. Beyond haptic feedback: human factors and risk as design mediators in a Virtual Reality Knee Arthroscopy Training System (SKATS). Engineering Psychology and Cognitive Ergonomics, 3 (1999),387–396. 86. Riccomagno, E., Pistone, G. ands Wynn, H.P. Polynomial encoding of discrete probability. Proc. Int. Statist. Inst. 2, (1999), 163-166. 87. Bates, R, Gilliver, A. Hughes, T. Shahin S., Sivalogonathan, S. and Wynn, H. P. Fast optimisation of mechanical designs using CAD/CAE emulation: a case study”. Journal of Automobile Engineering: Proc. IMechE. part D, 213 (1999), 27-35. 88. Bates,R.A., Fontana, R. and Wynn, H. P. Multi-domain optimisation in engineering design. In V V Toropov, editor, Proceedings of the 1st ASMO UK/ISSMO Conference on Engineering Design Optimization, pages 5358. MCB University Press, 1999. 1998 89. Bates, R. A.; Riccomagno, E., Schwabe, R. and Wynn, H. P. The use of lattices in the design of high-dimensional experiments. New developments and applications in experimental design (Seattle, WA, 1997), 27–35, IMS Lecture Notes Monogr. Ser., 34, Inst. Math. Statist., Hayward, CA, 1998. 90. Sebastiani, P.; Wynn, H. P. Risk based optimal designs. MODA 5—advances in modeloriented data analysis and experimental design (Marseilles, 1998), 247–257, Contrib. Statist., Physica, Heidelberg, 1998. 91. Bates, R. A.; Riccomagno, E.; Schwabe, R.; Wynn, H. P. Lattices and dual lattices in optimal experimental design for Fourier models. Comput. Statist. Data Anal. 28 (1998), 283–296. 13 92. Bates, R and Wynn, H. P. Emulator technology in complex engineering environments. Engineering Design Conference, Brunel University, 1998. Professional Engineering Publications, IMechE, Bury St Edmonds, 67–76. 93. Zhigljavsky, A. A., Pronzato, L. and Wynn, H. P. Section-invariant numbers and generalised golden section optimization algorithms. Applications of Fibonacci numbers, Vol. 7 (Graz, 1996), 463–477, Kluwer Acad. Publ., Dordrecht, 1998. 94. Pronzato, L., Wynn, H. P. and Zhigljavsky, Anatoly A. A generalized golden-section algorithm for line search. IMA J. Math. Control Inform. 15 (1998), 185–214. 95. Bates, R., Fontana, R., Pronzato, L and Wynn, H. P. Multi-domain optimisation using computer experiments for concurrent engineering. Adaptive Computing in Design and Manufacture, (1998). 103, 354–364. Springer Verlag. 1997 96. Riccomagno, E., Schwabe, R. and Wynn, H. P. Lattice-based D-optimum design for Fourier regression. Ann. Statist. 25 (1997), 2313–2327. 97. Naiman, D. Q. and Wynn, H. P. Abstract tubes, improved inclusion-exclusion identities and inequalities and importance sampling. Ann. Statist. 25 (1997), 1954–1983. 98. Pronzato, L., Wynn, H. P. and Zhigljavsky, A. A. Using Renyi entropies to measure uncertainty in search problems. Mathematics of stochastic manufacturing systems (Williamsburg, VA, 1996), 253–268, Lectures in Appl. Math., 33, Amer. Math. Soc., Providence, RI, 1997. 99. Holliday, T., Pistone, G., Riccomagno,E. and Wynn, H. P. The application of algebraic geometry to the analysis of designed experiments: a case study. Computational Statistics. 14 (1997), 213-231. 100. Riccomagno, E and Wynn, H.P. Computational algebraic geometry in industrial experimental design. Proceedings of the International Conference on Industrial Statistics: Aims and Computational Aspects (eds. C P Kitsos and L Edler), Athens, (1997), 193– 198. 101. Pronzato, L.; Wynn, H. P.; Zhigljavsky, A. A. Stochastic analysis of convergence via dynamic representation for a class of line-search algorithms. Combin. Probab. Comput. 6 (1997), 205–229. 102. Naiman, D. Q. and Wynn, H. P. On intersecting a point set with Euclidean balls. Comput. Geom. 7 (1997), 237–244. 1996 103. Pistone, G. and Wynn, H. P. Generalised confounding with Grbner bases. Biometrika 83 (1996), no. 3, 653–666. 104. Naiman, D. Q.; Wynn, H. P. Independence number and the complexity of families of sets. Discrete Math. 154 (1996), 203–216. 14 105. O’Geran, J. H.; Wynn, H. P.; Zhiglyavsky, A. A. Rnyi-type randomization theory for search-length upper bounds. Nova J. Math. Game Theory Algebra 4 (1996), 147–160. 106. Giovagnoli, A. and Wynn, H. P. Cyclic majorization and smoothing operators. Linear Algebra Appl. 239 (1996), 215–225. 107. Bates, R. A., Buck, R. J., Riccomagno, E. and Wynn, H. P. Experimental design and observation for large systems. With discussion and a reply by the authors. J. Roy. Statist. Soc. Ser. B 58 (1996), 77–94, 95–111. 108. Bates, R. A. and Wynn, H. P. Tolerancing and optimisation for model-based robust engineering design. Quality and Reliability Engineering International. 12 (1996), 119127. 1995 109. Sivaloganathan, S., Evbuaomwan, N. F. O., Jebb, A and Wynn, H. P. A design system for the future. Designs Studies. (1995), 16, 447-470. 110. Crabb, D., Edgar, F. F., Fitzke, F., McNaught, Wynn, H. P. A. New approach to estimating variability in visual-field data using an image-processing technique”. British Journal of Opthalmology. 29 (1995), 213-217. 111. Pronzato, L., Wynn, H. P. and Zhigljavsky, A. A. Dynamic systems in search and optimisation. CWI Quarterly 8 (1995), 201–236. 112. Pronzato, Luc; Wynn, Henry P.; Zhigljavsky, Anatoly A. Improving on golden-section optimisation for locally symmetric functions. MODA 4—advances in model-oriented data analysis (Spetses, 1995), 285–297, Contrib. Statist., Physica, Heidelberg, 1995. 113. Wynn, H. P.; Zhigljavsky, A. A. Achieving the ergodically optimal convergence rate for a one-dimensional minimization problem. J. Complexity 11 (1995), 196–226. 114. Herzberg, A and Wynn, H. P. Some results on nearest neighbour balance in the statistical design of experiments. Trans Roy Soc Can, Series V, 6 (1995), 27-38. 115. (1995) Wynn, H. P. and Zhigljavsky, A. A. Chaos in search: the Golden Section, normal numbers and ergodically fast line search, Complex Stochastic Systems and Engineering”. Ed. D.M. Titterington. Oxford University Press. 116. Wynn, H. P. and Zhigljavsky, A. Dynamic systems in search and optimisation. CWI Quarterly 8, 201-236. 117. Giovagnoli, A. and Wynn, H. P. Multivariate dispersion orderings. Statist. Probab. Lett. 22 (1995), 325–332. 1994 118. Wynn, H. P. and Zhigljavsky, A. A. The theory of search from a statistical viewpoint. With discussion and a reply by the authors. Test. 3 (1994), 1-45. 15 119. Maljutov, M. B. and Wynn, H. P. Sequential screening of significant variables of an additive model. The Dynkin Festschrift, 253–265, Progr. Probab., 34, Birkhuser Boston, Boston, MA, 1994. 120. Bates, R., Buck, R. and Wynn, H. P. A statistical bolt-on for robust circuit design. J Design and Manufacture 4, (1994), 81-86. 121. Wynn, H. P.; Zhigljavsky, A. A.; O’Geran, J. H. Search methods and observer logics. Statistical decision theory and related topics, V (West Lafayette, IN, 1992), 533–537, Springer, New York, 1994. 1993 122. Karakostas, K. X. and Wynn, H. P. On the covariance function of stationary binary sequences with given mean. IEEE Information Theory. 39 (1993), 1684-1687. 123. Wynn, H. P. The foundations of experiment and observation. Journal of the Italian Statistical Society (invited read paper) 2 (1993), 137-158. 124. Wynn, H. P. and Zhigljavsky, A. A. Chaotic behaviour of search algorithms: introduction. Model-oriented data analysis (Petrodvorets, 1992), 199–211, Contrib. Statist., Physica, Heidelberg, 1993. 125. Atherton, M and Wynn, H. P. Multiple quality objectives in robust engineering design. International Conference on Quality and its Applications, Newcastle. (1993). 126. Wynn, H. P. ”Statistics in electrical engineering: combining teaching and research. Proc. Int. Statist. Inst., Florence 1993. 127. Buck, R. and Wynn, H. P. Optimization strategies for robust engineering design and computer-aided design. Qual Rel Eng Int. 9 (1993), 39-48. 128. Wynn, H. P.; Zhigljavsky, A. A. The chaotic behaviour of search algorithms. Acta Appl. Math. 32 (1993), 123–156. 129. Naiman, D. Q.; Wynn, H. P. A theorem on independence. Discrete Math. 120 (1993), 287–289. 130. O’Geran, J. H., Wynn, H. P. and Zhigljavsky, A.A. The game of mastermind as a testbed for search algorithms. Chance. 6 (1993), 31-37. 131. Naiman, D Q. and Wynn, H. P. Independent collections of translates of boxes and a conjecture due to Grnbaum. Discrete Comput. Geom. 9 (1993), 101–105. 1992 132. O’Geran, J. H., Wynn, H. P. Multi-stage step-wise group screening. Comm. Statist. Theory Methods. 21 (1992), 3291–3308. 133. Jones, B.; Kunert, J., Wynn, H. P. Information matrices for mixed effects models with applications to the optimality of repeated measurements designs. J. Statist. Plann. Inf. 33 (1992), 261–274. 16 134. Naiman, D. Q. and Wynn, H. P. Inclusion-exclusion-Bonferroni identities and inequalities for discrete tube-like problems via Euler characteristics. Ann. Statist. 20 (1992), 43–76. 135. Welch, W., Buck, R.J., Sacks, J., Wynn, H. P., Mitchell, T. and Morris, M. Screening, predicting and computer experiments. Technometrics. 34 (1992) 15-25. 1991 136. O’Geran, J. H., Wynn, H. P. and Zhiglyavsky, A. A. Search. Acta Appl. Math. 25 (1991), 241–276. 137. Jebb, A, Sivalogonathan, S and Wynn, H. P. Sketching input for computer-aided engineering.” Effective CAD/CAM European Conference, (1991). 138. Sivalogonathan, S and Wynn, H. P. Taguchi methods and engineering design. PanCommonwealth Workshop on Mathematical Modelling. Madras, India. (1991) 139. O’Geran, J. H., Zhigljavsky, A. and Wynn, H. P. Search. Acta Applicandae Mathematicae. 25 (1991), 241-276. 1989 140. Sacks, J., Welch, W. J., Mitchell, T. J. and Wynn, H. P. Design and analysis of computer experiments. With comments and a rejoinder by the authors. Statist. Sci. 4 (1989), 409–435. 141. Karakostas, K. X., Wynn, H. P. Systematic sampling for autocorrelated superpopulations. J. Statist. Plan. Inference. 22 (1989), 181–195. 142. Bevan, N. Jebb, A. and Wynn, H. P. Robust engineering design in practice. International Conference on Engineering Design (ICED). 1989, 415-424. 143. Jebb, A. Wynn, H. P., Rizvi, S. M. Robust Engineering Design Post-Taguchi. Phil. Trans. Roy. Soc. Series A, Mathematical and Physical Science. 327 (1989), 605-616. 1988 144. Lim, Y. B., Studden, W. J. and Wynn, H. P. A note on approximate D-optimal designs for G × 2m . Statistical decision theory and related topics, IV, Vol. 2 (West Lafayette, Ind., 1986), 351–361, Springer, New York, 1988. 145. Ogbonmwan, S. M.; Wynn, H. P. Resampling generated likelihoods. Statistical decision theory and related topics, IV, Vol. 1 (West Lafayette, Ind., 1986), 133–147, Springer, New York, 1988. 146. Shewry, M. C. and Wynn, H. P. Maximum entropy sampling with application to simulation codes. IMACS: Proc 12th World Congress on Scientific Computation, Paris.(1988), 517-519. 17 1987 147. Wynn, H. P. Observation and experimental design for autocorrelated processes. Proceedings of the 1st World Congress of the Bernoulli Society, Vol. 2 (Tashkent, 1986), 167–173, VNU Sci. Press, Utrecht, 1987. 148. (1987). Dodge, Y. and Wynn, H.P. Loops, the free treatment group and a solution to the connectivity problem for 3-way layouts. Proc First Int Workshop in the Optimal Design and Analysis of Experiments, Neuchatel. (1987), North Holland. 225-235. 149. Verdinelli, I and Wynn, H. P. Experimental design for target attainment. Proc First Int Workshop in the Optimal Design and Analysis of Experiments, Neuchatel. (1987), North Holland. 319-324. 150. Giovagnoli, A., Pukelsheim, F. Wynn, H. P. Group invariant orderings and experimental designs. J. Statist. Plann. Inference 17 (1987), 159–171. 151. Herzberg, A. M., Wynn, H. P. Nearest neighbour balance and interblock and intrablock analysis in the design of experiments. Utilitas Math. 31 (1987), 243–254. 152. 1. Ogbonomwan, S. M., Verrall, R. J. and Wynn, H. P. Resampling codes and regenerated likelihoods. Proc. Conf. Model Oriented Data Analysis, Wartburg. Springer Verlag, (1987), 114-119. 1986 153. 41. Studden, W.J, Lim Y. B., Studden, W.J and Wynn, H. P. D-optimum continuous designs for G × 2k factorial experiments. IV Purdue Symposium, (1986), 351-361. 154. 43. Shewry, M. C. and Wynn, H. P. Maximum entropy sampling”. Journal of Applied Statistics. 14 (1986), 165-170. 155. Basso, L., Winterbottom, A. and Wynn, H.P. A review of the ’Taguchi Methods’ for off-line quality control. Qual. Rel. Eng. Int. 2 (1986), 71-80. 156. Ogbonwan, SM and Wynn, H.P. Discussion: Jacknife, Bootstrap and other Resampling Strategies in Regression (C-F Wu). Ann. Statist. 14 (1986), 1340-1343. 1985 157. Giovagnoli, A., Wynn, H. P. Schur-optimal continuous block designs for treatments with a control. Proceedings of the Berkeley conference in honor of Jerzy Neyman and Jack Kiefer, Vol. II (Berkeley, Calif., 1983), 651–666, Wadsworth Statist./Probab. Ser., Wadsworth, Belmont, CA, 1985. 158. Giovagnoli, A.; Wynn, H. P. G-majorization with applications to matrix orderings. Linear Algebra Appl. 67 (1985), 111–135. 159. K. Karakostas and Wynn, H. P. Systematic sampling for autocorrelated super-populations”. J Stat Plan and Inference. 22(1985), 181-195. 18 1984 160. Bohrer, R.; Wynn, H. P. Probabilistic ordering of Scheff polyhedra. Inequalities in statistics and probability (Lincoln, Neb., 1982), 150–155, IMS Lecture Notes Monogr. Ser., 5, Inst. Math. Statist., Hayward, CA, 1984. 161. Wynn, H. P. An exact confidence band for one-dimensional polynomial regression. Biometrika 71 (1984), 375–379. 162. Kiefer, J., Wynn, H. P. Optimum and minimax exact treatment designs for one-dimensional autoregressive error processes. Ann. Statist. 12 (1984), 431–450. 163. Wynn, H. P. Jack Kiefer’s contributions to experimental design. Ann. Statist. 12 (1984), 416–423. 1983 164. Kiefer, J. and Wynn, H. P. Autocorrelation-robust design of experiments. Scientific inference, data analysis, and robustness (Madison, Wis., 1981), 279–299, Publ. Math. Res. Center Univ. Wisconsin, 48, Academic Press, Orlando, FL, 1983. 165. Wynn, H. P. Optimum subset problems in statistics and operational research. Multiobjective decision making (Manchester, 1982), 49–58, Inst. Math. Appl. Conf. Ser., Academic Press, London, 1983. 166. Wynn, H. P. and Bohrer, R. A geometric proof of the DEOPSS inequality for spherically symmetric distributions in 3 dimensions. A Festschrift for Erich L. Lehmann, pp. 449– 455, Wadsworth Statist./Probab. Ser., Wadsworth, Belmont, Calif., 1983. 1982 167. Herzberg, A. M. and Wynn, H. P. A general approach to Yates’ inter-block and intrablock analysis. Special issue dedicated to Frank Yates on the occasion of his eightieth birthday, Vol. B. Utilitas Math. 21 (1982), 189–203. 168. Wynn, H. P. ”Controlled versus random experimentation”. The Statistician. 31 (1982),237244. 169. Wynn, H. P. Optimum submeasures with application to finite population sampling. Statistical decision theory and related topics, III, Vol. 2 (West Lafayette, Ind., 1981), 485–495, Academic Press, New York, 1982. 170. Bohrer, R. and Wynn, H. P. Spherically symmetric probability orderings useful in multiple comparisons. Ann. Statist. 10 (1982), 1253–1260. 1981 171. . Giovagnoli, A.; Wynn, H. P. Optimum continuous block designs. Proc. Roy. Soc. London Ser. A 377 (1981), 405–416. 19 172. Stewart, I., Wynn, H. P. The estimability structure of linear models and submodels. J. Roy. Statist. Soc. Ser. B 43 (1981), 197–207. 173. Kiefer, J. and Wynn, H. P. Optimum balanced block and Latin square designs for correlated observations. Ann. Statist. 9 (1981), 737–757. 1980 174. Giovagnoli, A., Wynn, H. P. A majorization theorem for the C-matrices of binary designs. J. Statist. Plann. Inference 4 (1980), 145–154. 1978 175. Wu, C-F. and Wynn, H. P. The convergence of general step-length algorithms for regular optimum design criteria. Ann. Statist. 6 (1978), 1273–1285. 176. ”Freedom of statistical information”. (Presidential address.) J Roy Statist Soc A,(1977), 141, 1-13. 1977 177. Wynn, H. P. Minimax purposive survey sampling design. J. Amer. Statist. Assoc. 72 (1977),655–657 178. Wynn, H. P. Convex sets of finite population plans. Ann. Statist. 5 (1977), 414–418. 179. Wynn, H. P. ”An unbiased estimated under SRS of a small change in a proportion”. The Statistician 29, (1977) 225-228. 180. Wynn, H. P. An inequality for certain bivariate probability integrals. Biometrika 64 (1977), 411–414. 181. Wynn, H. P. The combinatorial characterization of certain connected 2×J ×K three-way layouts. Comm. Statist.—Theory Methods, (A6). (1977), 945–953. 182. Wynn, H. P. Optimum designs for finite populations sampling. Statistical decision theory and related topics. II (Proc. Sympos., Purdue Univ., Lafayette, Ind., 1976), 471–478, Academic Press, New York, 1977. 1976 183. Wynn, H. P. The limiting variance function for design sequences. Math. Operationsforsch. Statist. 7 (1976), 69–74. 184. Wynn, H. P. Connected finite population sampling plans. Biometrika 63 (1976), 208– 210. 1975 20 185. Wynn, H. P. ”An unbiased estimated under SRS of a small change in a proportion”. The Statistician. 29 (1975), 225-8. 186. Wynn, H. P. Simple conditions for optimum design algorithms. A survey of statistical design and linear models. (1975) J N Srivastava, Ed, North Holland. 187. Wynn, H. P. Integrals for one-sided confidence bounds: a general result. Biometrika 62 (1975), 393–396. 188. Wynn, H. P. Simple conditions for optimum design algorithms. A survey of statistical design and linear models (Proc. Internat. Sympos., Colorado State Univ., Ft. Collins, Colo., 1973), 571–579. North-Holland, Amsterdam, 1975. 1973 189. Kuhn, A., Poole, A., Sales, P and Wynn, H. P. An analysis of graduate job mobility. Brit. J. Ind. Relations. 11 (1973), 124-42. 190. Wynn, H. P. Limiting second moments for transient states of Markov chains. J. Appl. Probability 10 (1973), 891–894. 1972 191. Wynn, H. P. Results in the theory and construction of D-optimum experimental designs. (With discussion.) J. Roy. Statist. Soc. Ser. B 34 (1972), 133–147, 170–186. 1971 192. Wynn, H. P.; Bloomfield, P. Simultaneous confidence bands in regression analysis. (With discussion.) J. Roy. Statist. Soc. Ser. B 33 (1971), 202–217, 241–250. 1970 193. Wynn, H. P. The sequential generation of D-optimum experimental designs. Ann. Math. Statist. 41 (1970), 1655–1664. 21