統計方法與推論研討會

  [影像處理]    [財務數學]     [連續型馬可夫鍊模型在疾病發展史的應用]

    [計算視覺研討會][財務工程簡介]    [認購權證理論與計算]

主辦單位:台大數學系,中研院統計所

協辦單位:國科會數學研究推動中心

期間:自8921日至89731日止

主題:

一、影像處理:

    『計算視覺研討會』:UCLA統計系吳英年教授主講。

    主持人:傅承德(中研院統計所)、陳宏(台大數學系)

    協同主持人:盧鴻興(交大統計學研究所) 、鄭少為(中研院統計所)
     

二、財務數學: 一日共六小時的財務工程簡介」課程

「認購權證理論與計算」研討會:香港科技大學財務學系

段錦泉教授主講

    主持人:傅承德(中研院統計所)、陳宏(台大數學系)

三、連續型馬可夫鍊模型在疾病發展史的應用。

    主持人:傅承德(中研院統計所)、陳宏(台大數學系)

    協同主持人:趙維雄(中研院統計所)

 
 
主題一:影像處理(Image Analysis
盧鴻興教授 (交大統計學研究所)、吳漢銘、陳泰賓(交大統計學研究所博士生)共三個時演講 abstracttransparency

Introduction to the basic modeling of three medical imaging systems: PET (Positron Emission Tomography), fMRI (functional Magnetic Resonance Images), and Ultrasound Images.

張憶壽教授(中央大學數學系)abstract      transparency

Asymptotic consistency of the maximum likelihood estimate in positron emission tomography and applications

盧鴻興教授(交大統計科學研究所) abstract transparency

Some Statistical Analysis in PET (Positron Emission Tomography) and Ultrasound Images.

黃信誠博士Academia Sinica, 中央研院統計科學研究所)transparency

An Introduction to Statistical Image Analysis using Markov Random Fields 

計算視覺研討會

主講人:UCLA統計系吳英年助理教授

時間: 六月 24日至七月7日。

主題一:EM/data augmentation 6/27/2000 abstract

演講一:The Parameter Expanded EM algorithm   演講二:Data Augmentation, Parameter Expansion and Group Transformation 主題二:Computational vision 7/5/2000 abstract 演講三:An Overview of Computational Vision   演講四:Modeling and Synthesis of Texture Patterns in Natural Scenes  
主題二:財務數學

財務工程簡介」課程

時 間:2000311(星期六)上午8:20至下午4:40

點:台北市台灣大學新數學館101教室

主辦單位:中華機率統計學會
協辦單位:台灣大學國際金融研究所國際金融研究中心、台灣大學數學系
課程主題
 
 
First Generation Option
中央大學

財務管理學系

張傳章副教授

8:40-9:30 Introduction to Financial Engineering
10:00-10:50 Equivalent Martingale Measures and Risk Neutral Pricing
11:00-11:50 Alternative Option Pricing Models
Second Generation Option
中央大學

財務管理學系

張森林副教授

13:30-14:20 Term Structure Models for Interest Rates
14:50-15:40 Interest Rate Derivatives
15:50-16:40 Exotic Options

聯絡人:陳宏 教授, 106台北市羅斯福路四段一號「台灣大學數學系陳宏」

Tel02–23633860 ext 109 Fax02-23914439

E-mailhchen@math.ntu.edu.tw

註冊費: 教師:1,500元,學生:1,000元,一般:5,000

註:採線上註冊方式,中華機率統計學會永久會員,註冊費減收500元,

    中華機率統計學會一般會員,註冊費收據可抵免本年度學會會費

如您想進一步瞭解財務工程此領域,可參看Hull的書,以下是由Hull網站上取得之投影片(需UNZIP檔案)
hullslid1.exehullslid2.exe hullslid3.exe

認購權證理論與計算」研討會

主講人: Hong Kong University of Science and Technology 財務學系段錦泉教授
             (Senior Wei Lun Fellow
時間:三月十九日至二十三日

地點:台大數學系308室

研 討 會 議 程
 
主講人: 段錦泉教授(Senior Wei Lun Fellow)香港科技大學財務學系

三月二十一日(星期二)

  8:30-10:00 Derivative securities pricing theories (I)   transparency
10:30-12:00 Derivative securities pricing theories (II)  transparency
abstract

三月二十二日(星期三)

  8:30-10:00 Numerical methods for valuing derivative securities (I)   transparency
10:30-12:00 Numerical methods for valuing derivative securities (II)  transparency
abstract

演講人:

三月二十一日(星期二)

  14:00-15:00  何淮中教授(中央研究院統計科學研究所)abstract
         講題:Modeling financial time series
  15:30-16:30  廖四郎教授(政治大學金融學系) abstract
         講題:Theory of Dynamic Capital Structure and The Valuation
                    of Corporate Bonds Second Generation Option

三月二十二日(星期三)

  13:30-14:30  林建甫教授(台灣大學經濟學系)abstracttransparency
         講題:Modeling volatility in the financial data
  14:30-15:30  呂育道教授(台灣大學資訊工程學系) transparency
         講題:Computational techniques in derivatives pricing

四月份後續活動

演講人:


主題三:連續型馬可夫鍊模型在疾病發展史的應用

五月份舉行

演講人:

5/11/2000 趙維雄(中央研院統計科學研究所)

講題:Trend Analysis of Longitudinal Ordinal Data with Irregular Timing
Abstract: In many longitudinal studies, repeated observations of multivariate ordinal outcomes along with several  covariates are taken from a sample of subjects at irregular time points, resulting in multivariate longitudinal ordinal data. When the outcome fluctuates over time before entering an absorbing state, it is often of interest to investigate the relationship between the trend of the underlying outcome process and the covariates. One of the proposed models available for trend analysis without absorption is the univariate local equilibrium distribution model of Kosorok and Chao (1996). In this talk, we extend their model to a multivariate model for multivariate outcomes. Odds ratios are used to measure the cross-sectional association among outcomes that are observed at the same time.   Extenstion feasibility is examined from the estimation point of view. If time permits, a univariate extension to allow for a single absorbing state will also be introduced.

5/17/2000 鄧利源 (University of Memphis)

講題: Markov Chain Monte Carlo: Metropolis Algorithm, Gibbs Sampling and Some Applications
Abstract: In this talk, we will start with an example, Genetic Linkage Model, to motivate various Markov Chain Monte Carlo (MCMC) methods. In particular, we will use the example to illustrate the use of EM algorithm, Metropolis algorithm, and Metropolis-Hastings Method. We will discuss their connection with the standard Rejection method in random variate generation. Finally, we give another example to illustrate the foundation, the procedure and some applications of Gibbs sampling.

5/18/2000 張淑惠(國立台灣大學流行病學研究所)

講題:Regression Methods for Recurrent Event Data

5/25/2000 葉瑞徽(台灣科技大學工業管理系)

講題:The Applications of Acyclic Phase-Type Distributions on Semi-Markov Decision Processes
Abstract: It is well-known that the main barrier in analyzing semi-Markovian model is that the mathematical  formulation is so complicated that it is essentially intractable. To overcome this barrier, an acyclic phase-type approach is proposed to approximate the general sojourn time distributions of a semi-Markov process. Using the approximation, a semi-Markovian model can be transformed into a Markovian model such that the analytical tractability of Markov processes can be preserved. Based on the resulting Markovian model, algorithms are provided to derive the optimal state-dependent and state-age-dependent policies.  Furthermore, procedures are developed to implement these optimal policies back on the original semi-Markovian model.