Colloquium/Seminar

YearMonth
2017 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Oct   Nov   Dec  
2016 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Oct   Nov   Dec  
2015 Jan   Feb   Mar   Apr   May   Jun   Aug   Sep   Oct   Nov   Dec  
2014 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2013 Jan   Feb   Mar   Apr   May   Jun   Aug   Sep   Nov   Dec  
2012 Jan   Feb   Apr   May   Jun   Jul   Aug   Sep   Nov   Dec  
2011 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2010 Jan   Feb   Mar   Apr   May   Jun   Sep   Oct   Nov   Dec  
2009 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2008 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2007 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2006 Jan   Feb   Mar   Apr   May   Jun   Jul   Sep   Oct   Nov   Dec  
2005 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2004 Jan   Feb   Mar   Apr   May   Aug   Sep   Oct   Nov   Dec  

Event(s) on January 2006


  • Friday, 6th January, 2006

    Title: A Guide To Computational Microstructures
    Speaker: Professor Carsten Carstensen, Faculty of Mathematics and Natural Sciences II, Humboldt University, Berlin, Germany
    Time/Place: 14:30  -  16:00
    FSC1217


  • Tuesday, 10th January, 2006

    Title: Likelihood-based Approaches for Constrained Parameter Problems in Multiple Regression Models
    Speaker: Dr. Tian, Guoliang, Division of Biostatistics, University of Maryland at Baltimore, USA
    Time/Place: 11:30  -  12:30
    FSC1217
    Abstract: Constrained parameter problems arise in a variety of statistical applications but they have been most resistant to solution. This paper proposes methodology for estimating restricted parameters in general multiple regression models with known or unknown covariance matrix. The proposed method thus provides solution to an open problem: The penalized estimation for linear inverse problem with positivity restrictions originated from Vardi and Lee (1993). By first considering the simplest rectangle constraints and then generalizing them to linear inequality constraints and to arbitrary convex constraints, we propose a unified EM-type algorithm for estimating the constrained parameters via data augmentation. The key idea is to introduce a sequence of latent variables such that the complete-data model belongs to the exponential family, hence, resulting in a simple E-step and an explicit M-step. Furthermore, we extend the restricted multivariate normal distribution to the multivariate t-distribution with constrained parameters to obtain robust estimation. With the proposed algorithms, standard errors can be calculated by bootstrapping. The proposed method is appealing for its simplicity and ease of implementation and its applicability to a wide class of parameter restrictions. Four real data sets are analyzed to illustrate different aspects of the proposed methods. Finally, the proposed algorithm is applied to linear inverse problem with possible negativity restrictions and is evaluated numerically.


  • Tuesday, 10th January, 2006

    Title: A Guide To Computational Microstructures
    Speaker: Professor Carsten Carstensen, Faculty of Mathematics and Natural Sciences II, Humboldt University, Berlin, Germany
    Time/Place: 14:30  -  16:00
    FSC 1217


  • Friday, 13th January, 2006

    Title: Low Order Quadrilateral Finite Elements for Reissner-Mindlin Plate Model
    Speaker: Professor Zhong-ci Shi, Chinese Academy of Sciences, China
    Time/Place: 16:00  -  17:30
    WLB204
    Abstract: Reissner-Mindlin plate model is one of the most commonly used models of a moderately thick to thin plate. However, a direct and seemingly reasonable finite element discretization usually yields very poor results which is referred to LOCKING phenomenon. In the past two decades, many efforts have been devoted to the design of locking free finite elements to resolve this model, most of these work focus on triangular and rectangular elements, the latter may be extended to parallelograms, but very few on quadrilaterals. In this talk we will give an overview of the recent development of low order quadrilateral elements and present our new results.


  • Tuesday, 17th January, 2006

    Title: Bedrosian Theorem, its generalizations, and applications in time-frequency
    Speaker: Professor Tao QIAN, Faculty of Science and Technology, University of Macau
    Time/Place: 11:30  -  12:30
    FSC1217
    Abstract: Bedrosian Theorem says that if f and g have lower and higher frequencies, respectively, then H(fg)=fHg, where H is Hilbert transform. The first half of the talk will give an account of generalizationsof this result. The later half is devoted to their connections and applications to signal analysis.


  • Tuesday, 17th January, 2006

    Title: Joint HKBU-HKU Workshop on Mathematical and Computational Biology
    Speaker: Profs.I.Shmulevich/L.H.Tang, Institute for Systems Biology / Department of Physics, HKBU
    Time/Place: 14:30  -  17:00
    FSC 1217


  • Friday, 20th January, 2006

    Title: Structural Equation Model and Its Statistical Diagnostics
    Speaker: Dr. LU Bin, Department of Statistics, The Chinese University of Hong Kong
    Time/Place: 11:30  -  12:30
    FSC1217
    Abstract: The structural equation model (SEM) is a widely appreciated method in behavioral, educational, psychological, and social sciences. Recently, SEM has also received a great deal of attention in biological and medical researches. The main purpose of SEM is to assess the inter-relationships among manifest variables, and latent variables which cannot be measured directly by a single manifest variable. Statistical diagnostics is an important component of a thorough data analysis. The main objective of this talk is to introduce some basic concepts of SEM, and develop the efficient diagnostic procedures in the context of a nonlinear SEM with ignorable missing data. Statistical diagnostics was studied in terms of case-deletion and local influence approaches. The diagnostic measures were obtained on the basis of the conditional expectation of the complete data log-likelihood which is closely related to the MCEM algorithm in finding the ML estimate. Formulas for achieving the diagnostic measures are derived. Real examples are also presented to illustrate our method.


  • Tuesday, 24th January, 2006

    Title: On Numerical Evaluation of European and American Options
    Speaker: Professor Song Wang, School of Mathematics & Statistics, The University of Western Australia, Australia
    Time/Place: 11:30  -  12:30
    FSC1217
    Abstract: In this talk I will present some of our latest advances in the numerical solution of the Black-Scholes equation and a variational inequality problem involving the Black-Sholes equation governing, respectively, European and American option valuations. These include a penalty method for a complementarily problem and some discretization methods for the Black-Scholes equation. Both theoretical and numerical aspects of the methods will be addressed.


  • Thursday, 26th January, 2006

    Title: Mechanism of the Formation of Singularities for Quasilinear Hyperbolic Systems
    Speaker: Professor LI Ta-Tsien, Department of Mathematics, Fudan University, China
    Time/Place: 11:30  -  12:30
    FSC 1217
    Abstract: In this survey talk the mechanism and the character of the formation of singularities caused by eigenvalues or (and) eigenvectors respectively will be discussed for quasilinear hyperbolic systems.