Title: | Meta Analysis and Selection Bias |
Speaker: | Dr. Shi Jian-Qing, School of Mathematics and Statistics, The University of Newcastle Upon Tyne, United Kingdom |
Time/Place: | 11:30 - 12:30 FSC1217 |
Abstract: | A major difficulty in meta-analysis is publication bias. Studies with positive outcomes are more likely to be published than studies reporting negative or inconclusive results. Correcting for this bias is not possible without making untestable assumptions. We suggest a sensitivity analysis in which different patterns of selection bias can be tested against the fit to the funnel plot. Some applications are discussed. |
Title: | Hybrid censoring: Concepts and Results |
Speaker: | Prof. N. Balakrishnan, Department of Mathematics and Statistics, McMaster University, Canada |
Time/Place: | 11:30 - 12:30 FSC1217 |
Abstract: | In this talk, I shall define two types of hybrid censoring and motivate their use. Then, I shall illustrate these concepts by considering an exponential distribution and deriving the maximum likelihood estimates of the mean lifetime under the two types of hybrid censoring. Then, I will use the conditional moment generating function approach to derive the exact distributions of these MLEs and the confidence intervals obtained from them. Finally, I will take some examples to illustrate these results. |
Title: | Dependence Analysis in Some Stochastic and Statistical Models |
Speaker: | Mr. Sun Yunzhi, Department of Mathematics, Hong Kong Baptist University, Hong Kong |
Time/Place: | 14:30 - 15:30 T909 |
Abstract: | In this presentation, the dependence analysis particularly concentrated upon the exploration by copula analysis will be given. As compared with the classical approach with the aid of linear model and correlation, many association and dependence analysis for theoretical and practical statistical works could be readily handled with the aid of copula. In our work, two general perspectives are emphasized, one is the distributional study about the general statistical model with non-linear dependence patterns; the other is the Markovian stochastic processes constructed and analyzed with the aid of copula. Our main contributions are (I) the lower bound copula analysis generated from Gaussian family, this is particularly useful in financial mathematics when the Varlue-at-Risk confidence intervals are to be constructed (as compared with the general non-distributional lower bound given by Frechet); and (II) the linear stochastic population model’s (or the CIR model in financial mathematics) dependence analysis, which shows exactly the dependence pattern of a Markov process, which is also an typical example of how the copula-based algebra are more essential to the Markov processes in comparison to the necessary but not sufficient condition in terms of Kolmogorov-Chapman equations. |
We organize conferences and workshops every year. Hope we can see you in future.
Learn MoreProf. M. Cheng, Dr. Y. S. Hon, Dr. K. F. Lam, Prof. L. Ling, Dr. T. Tong and Prof. L. Zhu have been awarded research grants by Hong Kong Research Grant Council (RGC) — congratulations!
Learn MoreFollow HKBU Math