Prof Tertius de Wet
Professor
University of Stellenbosch
Private Bag X1, Matieland
7602, South Africa
Tel: +(27) 21 808 3242
Fax: +(27) 21 808 3830
e-mail: tdewet@sun.ac.za
Obtained a DSc at Potchefstroom University for Christian Higher Education in 1972.
Rated by the National Research Foundation (NRF).
Employment History
1972 – 1978 Lecturer, Senior Lecturer, Potchefstroom University
1979 – 1981 Professor, Rhodes University
1982 – 1999 Chief Scientist and Group Manager, Institute for Maritime Technology
2000 – present Professor University of Stellenbosch
Visiting Appointments
Sep 1972 – Jun 1973 Visiting Research Associate, University of Chicago, USA
Nov 1978 – Jun 1979 Visiting Professor, University of Iowa, USA
Apr 1985 – Jun 1985 Visiting Research Professor, Limburg University (now University of Hasselt), Belgium
Sep 2005 – Dec 2005 Visiting Scholar, University of Leuven, Belgium
Mathematical Statistics 318
Actuarial Science 346
Robust Statistics (post-graduate - jointly with Prof F Osterreicher, University of Salzburg, Austria)
Extreme Value Theory (post-graduate)
Financial Mathematical Statistics (stochastic calculus) (post graduate)
Asymptotic distribution theory, goodness-of-fit, degenerate U-statistics, quantile regression, LULU non-linear smoothers, extreme value theory, statistical aspects of poverty and inequality, campanometry
Technical Reports (all downloads must be authorized first by the author or the Journal)
Residual
processes in robust regression (with JL Fresen and F Lombard)
Optimality in weighted L-2-Wasserstein goodness-of-fit statistics. Download
Submitted Papers
Ranganai, E, van Vuuren, JO and de Wet, T (2011). Multiple Case High Leverage Diagnosis in Regression Quantiles. Download
Kpanzou, TA, de Wet, T and Neethling, A (2011). Semi-parametric estimation of inequality measures. Download
Recent Publications in Journals (all downloads must be authorised first by the author or the Journal itself)
De Wet, T (2000). Invited discussant of the paper “Contributions of empirical and quantile processes to the asymptotic theory of goodness of fit tests” by del Barrio, E, Cuesta-Albertos, JA and Matran, C, published in TEST 9, 1-96. TEST 9, 74-79
De Wet, T (2002). Goodness-of-fit tests for location and scale families based on a weighted L2-Wasserstein distance measure. TEST 11, No 1, p 89-107. Download
De Jongh, PJ, de Wet, T & Cloete, GS (2002). Combining Vasicek and robust estimators for forecasting systematic risk. Investment Analyst’s Journal, 55, 37-44. Download
De Jongh, PJ & de Wet, T. (2003). Small sample performance of extreme regression quantiles. South African Journal of Statistics, 37(2), 79-104.
Beirlant, J, De Wet, T & Goegebeur, Y. (2004). Nonparametric estimation of extreme conditional quantiles. Journal of Statistical Computation and Simul, 74, 567-580. Download
De Jongh, PJ, de Wet, T & van Deventer, P.J.U. (2004). Saddlepoint approximations for the distribution of regression quantiles. South African Journal of Statistics, 38(1), 59-78.
De Wet, T. (2004). Statistical adjustment of tidal gauge data. South African Journal of Statistics, 38(1), 79-91.
Conradie, WJ, de Wet, T & Jankowitz, M (2005). An overview of LULU smoothers with applications to financial data. Studies in Economics and Econometrics 29, 97–121.
Beirlant, J, de Wet, T and Goegebeur, Y (2006). A goodness-of-fit statistic for Pareto-type behaviour. J Comp and Appl Math 186, 99-116. Download
Conradie, WJ, de Wet, T and Jankowitz, M (2006). Exact and asymptotic distributions of LULU smoothers. J Comp and Appl Math 186, 253-267. Download
Goegebeur, Y, Beirlant, J and de Wet, T (2008). Linking Pareto-tail kernel goodness-of-fit statistics with tail index at optimal threshold and second order estimation. REVSTAT – Statistical Journal, Volume 6, Number 1, 51–69. Download
De Wet, T (2008). Kwadratiese vorme in stogastiese veranderlikes. Die Suid Afrikaanse Tydskrif vir Natuurwetenskap en Tegnologie, 27, Number 3, 5-22. Download
Conradie, WJ, de Wet, T and Jankowitz, M (2009). Performance of nonlinear smoothers in signal recovery. Applied Stochastic Models in Business and Industry, 25, 425 – 444. Download
Goegebeur, Y, Beirlant, J and de Wet, T (2010). Generalized kernel estimators for the Weibull-tail coefficient. Communications in Statistics: Theory and Methods, volume 39, 3695 – 3716. Download
Goegebeur, Y, Beirlant, J and de Wet, T (2010). Kernel estimators for the second order parameter in extreme value statistics. Journal of Statistical Planning and Inference, 140, 2632-2652. Download
Goegebeur, Y and de Wet, T (2011). Local estimation of the second order parameter in extreme value statistics and local unbiased estimation of the tail index. (Accepted for publication in Communications in Statistics: Theory and Methods) Download
Goegebeur, Y and de Wet, T (2011). Estimation of the third order parameter in extreme value Statistics. (Accepted for publication in TEST) Download
De Wet, T, Goegebeur, Y and Guillou, A (2010). Weighted moment estimators for the second order scale parameter. (Accepted for publication in Methodology and Computing in Applied Probability) Download
Luus, R, Neethling, A and de Wet, T (2011). Effectiveness of weighting and Bootstrap in the estimation of welfare indices under complex sampling. (Accepted for publication in the South African Statistical Journal) Download
De Wet, T, Goegebeur, Y and Munch, MR (2012). Asymptotically unbiased estimation of the second order tail parameter. Statistics and Probability Letters, vol 82, 565–573. Download
Older Publications (before 2000)
De Wet, T and Venter, JH (1972). Asymptotic distribution of certain test criteria of normality. South African Statist J 6, 135-149.
De Wet, T and Venter, JH (1973). Asymptotic distribution for quadratic forms with applications to test of fit. Ann Statist 1, 380-387.
De Wet, T and Venter, JH (1973). A goodness of fit test for a scale parameter family of distributions. South African Statist J 7, 35-46.
De Wet, T (1974). Rates of convergence of linear combinations of order statistics. South African Statist J 8, 35-43.
De Wet, T and Venter, JH (1974). The asymptotic power of a class of goodness of fit test criteria. South African Statist J 8, 69-76.
De Wet, T and Venter, JH (1974). An asymptotic representation of trimmed means with applications. South African Statist J 8, 127-134.
De Wet, T and Venter, JH (1976). Asymptotic distribution of quadratic functionals of partial sums. South African Statist J 10, 97-105.
De Wet, T (1976). Berry-Esseen results for the trimmed mean. South African Statist J 10, 77-96.
De Wet, T and Van Wyk, JWJ (1979). Some large sample properties of Hogg's adaptive trimmed means. South African Statist J 13, 53-69.
De Wet, T and Van Wyk, JWJ (1979). Robustness and efficiency properties of Hogg's trimmed means. Comm Statist Theor Meth A8(2), 117-128.
De Wet, T, Venter, JH and Van Wyk, JWJ (1979). The nul distributions of some test criteria of multivariate normality. South African Statist J 13, 153- 176.
De Wet, T (1980). Cramer-von Mises tests for independence. J Mult Analysis 10, 38-50.
De Wet, T and Parr, WC (1981). On minimum Cramer-von Mises norm parameter estimation. Comm Statist Theor Meth A10(12), 1149-1166.
Chandra, M, De Wet, T and Singpurwalla, ND (1982). On the sample redundancy and a test for exponentiality. Comm Statist Theor Meth A11(4), 429-438.
De Wet, T and Koul, HL (1983). Minimum distance estimation in a linear regression model. Ann Statist 11, 921-932.
De Jongh, PJ and De Wet, T (1985). Trimmed means and bounded influence estimators for the parameters of the AR(1) process. Comm Statist Theor Meth A14(6), 1361-1375.
De Jongh, PJ and De Wet, T (1985). A Monte Carlo comparison of regression trimmed means. Comm Statist Theor Meth A14(10), 2457-2472.
De Jongh, PJ and De Wet, T (1986). Confidence intervals for regression parameters based on trimmed means. South African Statist J 20, 137-164.
De Wet, T and Van Wyk, JWJ (1986). Bootstrap confidence intervals for regression coefficients when the residuals are dependent. J Statist Comput Simul 23, 317-327.
De Jongh, PJ and De Wet, T (1987). Invited discussion of ``The trimmed mean in the linear model'' by AH Welsh. Ann Statist 15, 36-39.
De Wet, T and Randles, RH (1987). On the effect of substituting parameter estimators in limiting χ 2 U and V statistics. Ann Statist 15, 398-412.
De Wet, T (1987). Degenerate U- and V-statistics. South African Statist J 21, 99-129.
De Jongh, PJ, De Wet, T and Welsh, AH (1988). Mallows-type bounded-influence regression trimmed means. J Amer Statist Assoc 88, 805-810.
De Wet, T, Fresen, JL and Fresen Jill (1989). The test for logical order in English language testing. J Appl Statist 16, 47-54.
De Jongh, PJ and De Wet, T (1989). Quantification of a malfunction in a weapon system. South African Statist J 23, 269-284.
De Wet, T and Van Wyk, JWJ (1990). Scheduling of patrols to guard an installation. South African Statist J 24, 75-86.
De Wet, T and Van Wyk, JWJ (1991). Deconfounding using the probability integral transformation. South African Statist J 25, 61-72.
De Jongh, PJ and De Wet, T (1993). An introduction to neural networks. South African Statist J 27, 103-128.
De Jongh, PJ, De Wet, T and Fresen, JL (1995). An experimental design for evaluating sonar detection performance. South African Statist J 29, 79-103.
De Wet, AG and De Wet, T (1995). TQM in Knowledge Intensive Organisations. Total Quality Management, Chapman and Hall, 279-282.
De Wet, T and Finkelstein, MS (1999). On a model for spares sufficiency. South African Statist J 33, 153-169.
Smoothing of sequences by extremes and selectors. ICOTS 7, Salvador, Brasil, 2006 (with WJ Conradie) Download
Accuracy of poverty and inequality analyses under complex sampling. European Conference on Quality in Official Statistics 2008, Rome, Italy (with A Neethling) Download
Panelist in the invited session The challenge of building a supply of statisticians for the future (session IPM 15). 57th Session of the International Statistical Institute, Durban, South Africa, 16 – 22 August 2009.
Kernel estimators for the second order parameter in extreme value statistics (with Yuri Goegebeur and Jan Beirlant). 57th Session of the International Statistical Institute, Durban, South Africa, 16 – 22 August 2009. Download
The estimation process for welfare measures under complex sampling (with Ariane Neethling). 57th Session of the International Statistical Institute, Durban, South Africa, 16 – 22 August 2009. Download
Semi-parametric estimation of inequality meassures. Paper delivered at the 52nd Annual Conference of SASA, Potchefstroom, 8-12 November 2010 (with T Kpanzou).
Variance estimation of welfare indices using the bootstrap. Paper delivered at the 52nd Annual Conference of SASA, Potchefstroom, 8-12 November 2010 (with A Neethling and R Luus).
Confidence intervals for welfare indices under complex sampling. Paper delivered at the 52nd Annual Conference of SASA, Potchefstroom, 8-12 November 2010 (with A Neethling and R Luus).
Local unbiased estimation of the tail index and its application to fire insurance data. Paper delivered at the ISBIS-2010 Conference in Portoroz, Slovenia, 5-9 July 2010 (with Y Goegebeur).
Current Research Projects
Statistical properties of LULU smoothers (with WJ Conradie).
Improved estimation of extreme value parameters (with T Berning).
Bahadur efficiencies in Wasserstein goodness-of-fit tests.
Extreme value theory (with J Beirlant, Y Goegebeur and A Guillou).
Quantile regression and elemental sets (with JO van Vuuren and E Ranganai).
Statistical aspects of poverty and inequality (with A Neethling and R Luus).
Semi-parametric inference for measures of inequality (with TA Kpanzou).
Campanometry (with JL Teugels and PJU van Deventer).
South African Statistical Association: President 2002/2003.
Fellow of the South African Statistical Association.
Editor: South African Statistical Journal.
International Statistical Institute: Elected Member
Institute of Mathematical Statistics: Member.
American Statistical Association: Member.
Member of the NRF Evaluation Panel for Mathematical Sciences 2004-2006.
Member of the FRD Evaluation Committee for Statistics 1986-1989.
Member of the South African Statistics Council, 2008 – 2011.
Member of the Scientific Committee of EURANDOM, July 2009 - .
Member of the Editorial Board of the International Statistical Review.