Monte Carlo Methods and Statistical Computing: My Personal E

Size: px
Start display at page:

Download "Monte Carlo Methods and Statistical Computing: My Personal E"

Transcription

1 Monte Carlo Methods and Statistical Computing: My Personal Experience Department of Mathematics & Statistics Indian Institute of Technology Kanpur November 29, 2014

2 Outline Preface 1 Preface

3 Outline Preface 1 Preface

4 Limitations: Preface 1. I must admit that the topics I am going to cover are definitely not exhaustive. 2. Topics are purely of my own interest which have developed over the last 30 years. 3. I am not going to describe any statistical package.

5 Advantages: Preface 1. Packages have their own problems. 2. Different packages can give different answers even on a relatively simple problem. 3. We should know the limitations of the packages. 4. I will try to provide a general approach

6 Journals: Preface 1. Journal of Computational and Graphical Statistics. 2. Computational Statistics and Data Analysis. 3. Journal of and Simulation. 4. Statistical Computing 5. Communications in Statistics - Simulation and Computation

7 Books: Preface 1. Simulation by Sheldon Ross 2. Nonuniform Random Deviate Generator, L. Devroye 3. Simulation modelling and analysis, Law and Kelton Journal of and Simulation. 4. Statistical Computing: J.F. Keneddy and R. Gentle 5. Statistical Computing, D. Kundu and A. Basu

8 Outline Preface 1 Preface

9 Monte Carlo Method: Definition 1. A broad class of numerical alogrithm depends on repeated random sampling. 2. If it is not possible to obtain the exact analytical solution often Monta Carlo method can be used to provide a very good approximate solution

10 Monte Carlo Method: A brief history 1. It was invented by Stanislaw Ulam, a famous Polish Mathematician, in the late John von Neumann first wrote the computer code to perform Monte Carlo simulations 3. Metropolis gave this name

11 Outline Preface 1 Preface

12 Where it can be used? 1. Calculating the area below a curve. 2. Calculating multidimensional integration. 3. Optimization. 4. Analyzing any complicated stochastic system (model).

13 Examples Preface Suppose we want to compute b a e x2 dx. Or suppose we want to compute b1 bk... f(x 1,...,x k )dx 1...dx k. a 1 a k

14 Examples:Contd. Preface Suppose we want to find the maximum or minimum of the following function f(x 1,...,x k ), where a 1 x 1 b 1,...,a k x k b k. Or suppose we want to analyze the following non-linear model y(x 1,...,x k ) = f(x 1,...,x k,θ)+e.

15 Outline Preface 1 Preface

16 Back Ground Preface 1. Knowledge of Basic Probability. 2. Discrete and Continuous random variables. 3. Stochastic models. 4. Generation of random numbers.

17 Knowlwedge of Basic Probability 1. Idea of a random experiment. 2. Basic idea of convergence of random variables. 3. Weak and strong law of large numbers. 4. Central limit theorem.

18 Discrete Random Variables 1. Uniform. 2. Binomial. 3. Geometric. 4. Poisson.

19 Continuous Random Variables 1. Uniform. 2. Exponential. 3. Normal. 4. Gamma. 5. Log-concave probability density function

20 Generation of Random Numbers First we need to know how to generate Uniform random numbers. This is the most basic problem. In this respect we use group theory results and machine powers.

21 Generation of Non-Uniform Random Numbers The most popular method is the inverse transformation. The following result can be used. If X is a random variable with the distribution function F(x), then F(X) follows uniform distribution. Therefore X = F 1 (U)

22 Generation of Discrete Random Numbers All the discrete distributions can be generated using inverse transformation method. Suppose P(X = a i ) = p i, for i = 1,2,... Without loss of generality we can assume a 1 < a 2 <... Draw a uniform random number say u, if k 1 i=1 p i < u < k i=1 p i, then X takes the value a k.

23 Generation of Continuous Random Numbers Many continuous random variables can be generated using inverse transformation method, for example exponential, Weibull, generalized exponential distributions etc. On the other hand several well known distribution cannot be obtained using inverse transformation method. For example normal, gamma etc.

24 Generation of Continuous Random Numbers If a continuous distribution cannot be generated using inverse transformation method, one of the most useful method is the acceptance rejection method. The idea is as follows. If we want to generate from f(x), try to find g(x), from which generation is simple so that it satisfies the following f(x) cg(x).

25 Acceptance Rejection Method: Algorithm 1. Generate Y from g(x). 2. Generate a uniform random vaiable U. 3. If U f(y)/cg(y), set X = Y, otherwise return to 1.

26 Acceptance Rejection Method: Theorem Theorem: 1. The random variable generated by this method has density function f(x) 2. The number of iterations of the algorithm that are needed is a geometric random variable with mean c,

27 Acceptance Rejection Method: Example Example 1: Suppose we want to generate from f(x) = 20x(1 x) 3 ; 0 < x < 1. Take g(x) = 1, 0 < x < 1. c = 135/64.

28 Acceptance Rejection Method: Example Example 2: Suppose we want to generate from f(x) = 2 π x 1/2 e x ; 0 < x <. Take and g(x) = 2 3 e 2x/3 0 < x <. c = 33/2 (2πe) 1/2.

29 Acceptance Rejection Method: Example Example 3: Suppose we want to generate from f(x) = 2 2π e x2 /2 ; 0 < x <. Take and g(x) = e x ; 0 < x <. c = 2e/π.

30 Outline Preface 1 Preface

31 Very Simple Example Consider the following simple linear regression model Y = Xb+e We know the LSE s can be obtained as b = (X T X) 1 X T Y. We have a complete very nice theory when all the components of the errors are i.i.d. normal random variables.

32 Very Simple Example: Contd. Consider some slightly different conditions of the same model. 1. What will happen if the errors are not normal? 2. What will happen if the errors are heavy tail? 3. What will happen if there are outliers? 4. What will happen if the errors are correlated?

33 Very Simple Example: Contd. In all these cases Monte Carlo Method can be used to asses the performances of the estmimators. It is very simple also. 1. Generate e 2. Generate Y. 3. Calculate b. 4. Repeat step 1 to step 4, several times.

34 Example Preface Consider the following simple linear regression model Y = Xb+e Suppose we want to estimate b by minimizing the least absolute errors i.e. b = argmin Y Xb. Theories are quite complicated. All the results are asymptotic in nature.

35 Example Preface Consider the following non-linear regression model Y = f(x,θ)+e Here f is a known function the vector X is also known, the paramete vector θ is unknown. The problem is to estimate the parameter vector θ, based on a sample of size n.

36 Example Preface Natural estimators will be n θ = argmin Y i f(x i,θ) 2. or θ = argmin i=1 n Y i f(x i,θ). i=1 Theories are quite complicated. All the results are asymptotic in nature.

37 Example Preface Monte Carlo method can be used to asses the perofrmance of the estimators. Based on the Monte Carlo method the biases and the mean squared errors can be calculated. Based on Bootstrap method confidence intervals also can be obtained.

38 Example: Importance Sampling In Bayesian analysis often we need to compute the posterior mean as follows: θ = E(h(X)) = h(x)f(x)dx. Here f(x) is the PDF of X, and x can be a very high dimensional. In Bayesian analysis f(x) is the posterior density function.

39 Example: Importance Sampling Monte Carlo simulation technique can be used to approximate the value of θ as follows: θ = 1 N N h(x i ), i=1 here X 1,...,X N is a random sample of size N from f(x).

40 Example: Importance Sampling Often it is observed that it is not very easy to generate samples from f(x). h(x)f(x) θ = h(x)f(x)dx = g(x)d(x). g(x) θ = 1 N N i=1 h(x i )f(x i ), g(x i ) here X 1,...,X N is a random sample of size N from g(x).

41 Outline Preface 1 Preface

42 Important Issues Preface 1. Finding Maximum likelihood estimators in a general problem. 2. Finding least squares estimators of linear regresssion model when the design matrix is close to a singular matrix 3. Non-linear regression model if the number of parameters are very high

43 MLE Preface It basically invloves maximizing a function of the form: f(θ 1,...,θ p ) Standard method is to use Newton-Raphson method:

44 Newton-Raphson Method Assuming sufficiently smooth f(θ), we want to solve f(θ) θ = 0 Standard method is to use Newton-Raphson method. Using Taylor series expansion, it can be easily obtained: [ θ (k+1) = θ (k) 2 f(θ (k) ] 1 ) f(θ (k) ) θ θ T θ

45 Profile Likelihood Method 1. For fixed θ 1,...,θ k, try to maximize with respect to θ k+1,...,θ p 2. Maximize with respect to θ 1,...,θ k.

46 EM Algorithm Preface Suppose the data are coming from a mixture model, and we compute the MLEs of the unknown parameters f(x) = π j 0, k j=1 π j = 1. k π j f j (x;θ j ), j=1

47 Mixture Model: MLE Based on a random sample x 1,...,x n, we want to compute the MLEs of the unknown parameters L(π,θ) = n i=1 k π j f j (x i ;θ j ). j=1

48 Missing Value Problem We treat this as a missing value problem 1. Assume the data are of the form (x,δ) 2. Compute E(δ Data) 3. Continue the process

49 Copula Method Preface Any multivarite distribution can be written uniquely as follows: F(x 1,...,x p ;θ) = C(F 1 (x 1 ;θ 1 ),...,F p (x p : θ p );γ) First estimate the marginal parameters, and then estimate the copula parameters

50 Non-linear regression Preface Consider the following model y(t) = p [A k cos(ω k t)+b k sin(ω k t)]+e(t) k=1 Estimate the unknown parameters

51 Outline Preface 1 Preface

52 Very important areas Bayesian comutation: mainly MCMC Classification problem Small n large p problem Non-parametric regression Functional data analysis

53 Thank You

ISyE 6416: Computational Statistics Spring Lecture 13: Monte Carlo Methods

ISyE 6416: Computational Statistics Spring Lecture 13: Monte Carlo Methods ISyE 6416: Computational Statistics Spring 2017 Lecture 13: Monte Carlo Methods Prof. Yao Xie H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology Determine area

More information

Chapter 1. Introduction

Chapter 1. Introduction Chapter 1 Introduction A Monte Carlo method is a compuational method that uses random numbers to compute (estimate) some quantity of interest. Very often the quantity we want to compute is the mean of

More information

STAT 725 Notes Monte Carlo Integration

STAT 725 Notes Monte Carlo Integration STAT 725 Notes Monte Carlo Integration Two major classes of numerical problems arise in statistical inference: optimization and integration. We have already spent some time discussing different optimization

More information

Math 494: Mathematical Statistics

Math 494: Mathematical Statistics Math 494: Mathematical Statistics Instructor: Jimin Ding jmding@wustl.edu Department of Mathematics Washington University in St. Louis Class materials are available on course website (www.math.wustl.edu/

More information

BIVARIATE GEOMETRIC (MAXIMUM) GENERALIZED EXPONENTIAL DISTRIBUTION

BIVARIATE GEOMETRIC (MAXIMUM) GENERALIZED EXPONENTIAL DISTRIBUTION Journal of Data Science 13(2015), 693-712 BIVARIATE GEOMETRIC (MAXIMUM) GENERALIZED EXPONENTIAL DISTRIBUTION Debasis Kundu Department of Mathematics and Statistics, Indian Institute of Technology Kanpur,

More information

Convexization in Markov Chain Monte Carlo

Convexization in Markov Chain Monte Carlo in Markov Chain Monte Carlo 1 IBM T. J. Watson Yorktown Heights, NY 2 Department of Aerospace Engineering Technion, Israel August 23, 2011 Problem Statement MCMC processes in general are governed by non

More information

Assessing the Quality of the Natural Cubic Spline Approximation

Assessing the Quality of the Natural Cubic Spline Approximation Assessing the Quality of the Natural Cubic Spline Approximation AHMET SEZER ANADOLU UNIVERSITY Department of Statisticss Yunus Emre Kampusu Eskisehir TURKEY ahsst12@yahoo.com Abstract: In large samples,

More information

Quantitative Biology II!

Quantitative Biology II! Quantitative Biology II! Lecture 3: Markov Chain Monte Carlo! March 9, 2015! 2! Plan for Today!! Introduction to Sampling!! Introduction to MCMC!! Metropolis Algorithm!! Metropolis-Hastings Algorithm!!

More information

Three Different Algorithms for Generating Uniformly Distributed Random Points on the N-Sphere

Three Different Algorithms for Generating Uniformly Distributed Random Points on the N-Sphere Three Different Algorithms for Generating Uniformly Distributed Random Points on the N-Sphere Jan Poland Oct 4, 000 Abstract We present and compare three different approaches to generate random points

More information

Bayesian Estimation for Skew Normal Distributions Using Data Augmentation

Bayesian Estimation for Skew Normal Distributions Using Data Augmentation The Korean Communications in Statistics Vol. 12 No. 2, 2005 pp. 323-333 Bayesian Estimation for Skew Normal Distributions Using Data Augmentation Hea-Jung Kim 1) Abstract In this paper, we develop a MCMC

More information

Monte Carlo for Spatial Models

Monte Carlo for Spatial Models Monte Carlo for Spatial Models Murali Haran Department of Statistics Penn State University Penn State Computational Science Lectures April 2007 Spatial Models Lots of scientific questions involve analyzing

More information

Probabilistic Graphical Models

Probabilistic Graphical Models Probabilistic Graphical Models Lecture 17 EM CS/CNS/EE 155 Andreas Krause Announcements Project poster session on Thursday Dec 3, 4-6pm in Annenberg 2 nd floor atrium! Easels, poster boards and cookies

More information

Stochastic Simulation: Algorithms and Analysis

Stochastic Simulation: Algorithms and Analysis Soren Asmussen Peter W. Glynn Stochastic Simulation: Algorithms and Analysis et Springer Contents Preface Notation v xii I What This Book Is About 1 1 An Illustrative Example: The Single-Server Queue 1

More information

Physics 736. Experimental Methods in Nuclear-, Particle-, and Astrophysics. - Statistical Methods -

Physics 736. Experimental Methods in Nuclear-, Particle-, and Astrophysics. - Statistical Methods - Physics 736 Experimental Methods in Nuclear-, Particle-, and Astrophysics - Statistical Methods - Karsten Heeger heeger@wisc.edu Course Schedule and Reading course website http://neutrino.physics.wisc.edu/teaching/phys736/

More information

Markov chain Monte Carlo methods

Markov chain Monte Carlo methods Markov chain Monte Carlo methods (supplementary material) see also the applet http://www.lbreyer.com/classic.html February 9 6 Independent Hastings Metropolis Sampler Outline Independent Hastings Metropolis

More information

BESTFIT, DISTRIBUTION FITTING SOFTWARE BY PALISADE CORPORATION

BESTFIT, DISTRIBUTION FITTING SOFTWARE BY PALISADE CORPORATION Proceedings of the 1996 Winter Simulation Conference ed. J. M. Charnes, D. J. Morrice, D. T. Brunner, and J. J. S\vain BESTFIT, DISTRIBUTION FITTING SOFTWARE BY PALISADE CORPORATION Linda lankauskas Sam

More information

GAMES Webinar: Rendering Tutorial 2. Monte Carlo Methods. Shuang Zhao

GAMES Webinar: Rendering Tutorial 2. Monte Carlo Methods. Shuang Zhao GAMES Webinar: Rendering Tutorial 2 Monte Carlo Methods Shuang Zhao Assistant Professor Computer Science Department University of California, Irvine GAMES Webinar Shuang Zhao 1 Outline 1. Monte Carlo integration

More information

Clustering Lecture 5: Mixture Model

Clustering Lecture 5: Mixture Model Clustering Lecture 5: Mixture Model Jing Gao SUNY Buffalo 1 Outline Basics Motivation, definition, evaluation Methods Partitional Hierarchical Density-based Mixture model Spectral methods Advanced topics

More information

Laplace Transform of a Lognormal Random Variable

Laplace Transform of a Lognormal Random Variable Approximations of the Laplace Transform of a Lognormal Random Variable Joint work with Søren Asmussen & Jens Ledet Jensen The University of Queensland School of Mathematics and Physics August 1, 2011 Conference

More information

Level-set MCMC Curve Sampling and Geometric Conditional Simulation

Level-set MCMC Curve Sampling and Geometric Conditional Simulation Level-set MCMC Curve Sampling and Geometric Conditional Simulation Ayres Fan John W. Fisher III Alan S. Willsky February 16, 2007 Outline 1. Overview 2. Curve evolution 3. Markov chain Monte Carlo 4. Curve

More information

1 Methods for Posterior Simulation

1 Methods for Posterior Simulation 1 Methods for Posterior Simulation Let p(θ y) be the posterior. simulation. Koop presents four methods for (posterior) 1. Monte Carlo integration: draw from p(θ y). 2. Gibbs sampler: sequentially drawing

More information

Time Series Analysis by State Space Methods

Time Series Analysis by State Space Methods Time Series Analysis by State Space Methods Second Edition J. Durbin London School of Economics and Political Science and University College London S. J. Koopman Vrije Universiteit Amsterdam OXFORD UNIVERSITY

More information

Modelling and Quantitative Methods in Fisheries

Modelling and Quantitative Methods in Fisheries SUB Hamburg A/553843 Modelling and Quantitative Methods in Fisheries Second Edition Malcolm Haddon ( r oc) CRC Press \ y* J Taylor & Francis Croup Boca Raton London New York CRC Press is an imprint of

More information

Use of Extreme Value Statistics in Modeling Biometric Systems

Use of Extreme Value Statistics in Modeling Biometric Systems Use of Extreme Value Statistics in Modeling Biometric Systems Similarity Scores Two types of matching: Genuine sample Imposter sample Matching scores Enrolled sample 0.95 0.32 Probability Density Decision

More information

On the Parameter Estimation of the Generalized Exponential Distribution Under Progressive Type-I Interval Censoring Scheme

On the Parameter Estimation of the Generalized Exponential Distribution Under Progressive Type-I Interval Censoring Scheme arxiv:1811.06857v1 [math.st] 16 Nov 2018 On the Parameter Estimation of the Generalized Exponential Distribution Under Progressive Type-I Interval Censoring Scheme Mahdi Teimouri Email: teimouri@aut.ac.ir

More information

Today. Lecture 4: Last time. The EM algorithm. We examine clustering in a little more detail; we went over it a somewhat quickly last time

Today. Lecture 4: Last time. The EM algorithm. We examine clustering in a little more detail; we went over it a somewhat quickly last time Today Lecture 4: We examine clustering in a little more detail; we went over it a somewhat quickly last time The CAD data will return and give us an opportunity to work with curves (!) We then examine

More information

An Introduction to Markov Chain Monte Carlo

An Introduction to Markov Chain Monte Carlo An Introduction to Markov Chain Monte Carlo Markov Chain Monte Carlo (MCMC) refers to a suite of processes for simulating a posterior distribution based on a random (ie. monte carlo) process. In other

More information

Theoretical Concepts of Machine Learning

Theoretical Concepts of Machine Learning Theoretical Concepts of Machine Learning Part 2 Institute of Bioinformatics Johannes Kepler University, Linz, Austria Outline 1 Introduction 2 Generalization Error 3 Maximum Likelihood 4 Noise Models 5

More information

Chapter 3. Bootstrap. 3.1 Introduction. 3.2 The general idea

Chapter 3. Bootstrap. 3.1 Introduction. 3.2 The general idea Chapter 3 Bootstrap 3.1 Introduction The estimation of parameters in probability distributions is a basic problem in statistics that one tends to encounter already during the very first course on the subject.

More information

Nested Sampling: Introduction and Implementation

Nested Sampling: Introduction and Implementation UNIVERSITY OF TEXAS AT SAN ANTONIO Nested Sampling: Introduction and Implementation Liang Jing May 2009 1 1 ABSTRACT Nested Sampling is a new technique to calculate the evidence, Z = P(D M) = p(d θ, M)p(θ

More information

100 Myung Hwan Na log-hazard function. The discussion section of Abrahamowicz, et al.(1992) contains a good review of many of the papers on the use of

100 Myung Hwan Na log-hazard function. The discussion section of Abrahamowicz, et al.(1992) contains a good review of many of the papers on the use of J. KSIAM Vol.3, No.2, 99-106, 1999 SPLINE HAZARD RATE ESTIMATION USING CENSORED DATA Myung Hwan Na Abstract In this paper, the spline hazard rate model to the randomly censored data is introduced. The

More information

What is machine learning?

What is machine learning? Machine learning, pattern recognition and statistical data modelling Lecture 12. The last lecture Coryn Bailer-Jones 1 What is machine learning? Data description and interpretation finding simpler relationship

More information

You ve already read basics of simulation now I will be taking up method of simulation, that is Random Number Generation

You ve already read basics of simulation now I will be taking up method of simulation, that is Random Number Generation Unit 5 SIMULATION THEORY Lesson 39 Learning objective: To learn random number generation. Methods of simulation. Monte Carlo method of simulation You ve already read basics of simulation now I will be

More information

Markov Chain Monte Carlo (part 1)

Markov Chain Monte Carlo (part 1) Markov Chain Monte Carlo (part 1) Edps 590BAY Carolyn J. Anderson Department of Educational Psychology c Board of Trustees, University of Illinois Spring 2018 Depending on the book that you select for

More information

Bayesian Statistics Group 8th March Slice samplers. (A very brief introduction) The basic idea

Bayesian Statistics Group 8th March Slice samplers. (A very brief introduction) The basic idea Bayesian Statistics Group 8th March 2000 Slice samplers (A very brief introduction) The basic idea lacements To sample from a distribution, simply sample uniformly from the region under the density function

More information

Ludwig Fahrmeir Gerhard Tute. Statistical odelling Based on Generalized Linear Model. íecond Edition. . Springer

Ludwig Fahrmeir Gerhard Tute. Statistical odelling Based on Generalized Linear Model. íecond Edition. . Springer Ludwig Fahrmeir Gerhard Tute Statistical odelling Based on Generalized Linear Model íecond Edition. Springer Preface to the Second Edition Preface to the First Edition List of Examples List of Figures

More information

MCMC Methods for data modeling

MCMC Methods for data modeling MCMC Methods for data modeling Kenneth Scerri Department of Automatic Control and Systems Engineering Introduction 1. Symposium on Data Modelling 2. Outline: a. Definition and uses of MCMC b. MCMC algorithms

More information

Generative and discriminative classification techniques

Generative and discriminative classification techniques Generative and discriminative classification techniques Machine Learning and Category Representation 2014-2015 Jakob Verbeek, November 28, 2014 Course website: http://lear.inrialpes.fr/~verbeek/mlcr.14.15

More information

Computer vision: models, learning and inference. Chapter 10 Graphical Models

Computer vision: models, learning and inference. Chapter 10 Graphical Models Computer vision: models, learning and inference Chapter 10 Graphical Models Independence Two variables x 1 and x 2 are independent if their joint probability distribution factorizes as Pr(x 1, x 2 )=Pr(x

More information

10.4 Linear interpolation method Newton s method

10.4 Linear interpolation method Newton s method 10.4 Linear interpolation method The next best thing one can do is the linear interpolation method, also known as the double false position method. This method works similarly to the bisection method by

More information

Dynamic Thresholding for Image Analysis

Dynamic Thresholding for Image Analysis Dynamic Thresholding for Image Analysis Statistical Consulting Report for Edward Chan Clean Energy Research Center University of British Columbia by Libo Lu Department of Statistics University of British

More information

Missing Data Analysis for the Employee Dataset

Missing Data Analysis for the Employee Dataset Missing Data Analysis for the Employee Dataset 67% of the observations have missing values! Modeling Setup Random Variables: Y i =(Y i1,...,y ip ) 0 =(Y i,obs, Y i,miss ) 0 R i =(R i1,...,r ip ) 0 ( 1

More information

Random Number Generation and Monte Carlo Methods

Random Number Generation and Monte Carlo Methods James E. Gentle Random Number Generation and Monte Carlo Methods With 30 Illustrations Springer Contents Preface vii 1 Simulating Random Numbers from a Uniform Distribution 1 1.1 Linear Congruential Generators

More information

Image Segmentation using Gaussian Mixture Models

Image Segmentation using Gaussian Mixture Models Image Segmentation using Gaussian Mixture Models Rahman Farnoosh, Gholamhossein Yari and Behnam Zarpak Department of Applied Mathematics, University of Science and Technology, 16844, Narmak,Tehran, Iran

More information

CHAPTER 1 INTRODUCTION

CHAPTER 1 INTRODUCTION Introduction CHAPTER 1 INTRODUCTION Mplus is a statistical modeling program that provides researchers with a flexible tool to analyze their data. Mplus offers researchers a wide choice of models, estimators,

More information

GAMs semi-parametric GLMs. Simon Wood Mathematical Sciences, University of Bath, U.K.

GAMs semi-parametric GLMs. Simon Wood Mathematical Sciences, University of Bath, U.K. GAMs semi-parametric GLMs Simon Wood Mathematical Sciences, University of Bath, U.K. Generalized linear models, GLM 1. A GLM models a univariate response, y i as g{e(y i )} = X i β where y i Exponential

More information

The Cross-Entropy Method for Mathematical Programming

The Cross-Entropy Method for Mathematical Programming The Cross-Entropy Method for Mathematical Programming Dirk P. Kroese Reuven Y. Rubinstein Department of Mathematics, The University of Queensland, Australia Faculty of Industrial Engineering and Management,

More information

Pattern Recognition. Kjell Elenius. Speech, Music and Hearing KTH. March 29, 2007 Speech recognition

Pattern Recognition. Kjell Elenius. Speech, Music and Hearing KTH. March 29, 2007 Speech recognition Pattern Recognition Kjell Elenius Speech, Music and Hearing KTH March 29, 2007 Speech recognition 2007 1 Ch 4. Pattern Recognition 1(3) Bayes Decision Theory Minimum-Error-Rate Decision Rules Discriminant

More information

INTRO TO THE METROPOLIS ALGORITHM

INTRO TO THE METROPOLIS ALGORITHM INTRO TO THE METROPOLIS ALGORITHM A famous reliability experiment was performed where n = 23 ball bearings were tested and the number of revolutions were recorded. The observations in ballbearing2.dat

More information

Bayesian Methods. David Rosenberg. April 11, New York University. David Rosenberg (New York University) DS-GA 1003 April 11, / 19

Bayesian Methods. David Rosenberg. April 11, New York University. David Rosenberg (New York University) DS-GA 1003 April 11, / 19 Bayesian Methods David Rosenberg New York University April 11, 2017 David Rosenberg (New York University) DS-GA 1003 April 11, 2017 1 / 19 Classical Statistics Classical Statistics David Rosenberg (New

More information

Exponential Random Graph Models for Social Networks

Exponential Random Graph Models for Social Networks Exponential Random Graph Models for Social Networks ERGM Introduction Martina Morris Departments of Sociology, Statistics University of Washington Departments of Sociology, Statistics, and EECS, and Institute

More information

A Brief Look at Optimization

A Brief Look at Optimization A Brief Look at Optimization CSC 412/2506 Tutorial David Madras January 18, 2018 Slides adapted from last year s version Overview Introduction Classes of optimization problems Linear programming Steepest

More information

1. Practice the use of the C ++ repetition constructs of for, while, and do-while. 2. Use computer-generated random numbers.

1. Practice the use of the C ++ repetition constructs of for, while, and do-while. 2. Use computer-generated random numbers. 1 Purpose This lab illustrates the use of looping structures by introducing a class of programming problems called numerical algorithms. 1. Practice the use of the C ++ repetition constructs of for, while,

More information

Expectation Propagation

Expectation Propagation Expectation Propagation Erik Sudderth 6.975 Week 11 Presentation November 20, 2002 Introduction Goal: Efficiently approximate intractable distributions Features of Expectation Propagation (EP): Deterministic,

More information

Introduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization. Wolfram Burgard

Introduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization. Wolfram Burgard Introduction to Mobile Robotics Bayes Filter Particle Filter and Monte Carlo Localization Wolfram Burgard 1 Motivation Recall: Discrete filter Discretize the continuous state space High memory complexity

More information

Discussion on Bayesian Model Selection and Parameter Estimation in Extragalactic Astronomy by Martin Weinberg

Discussion on Bayesian Model Selection and Parameter Estimation in Extragalactic Astronomy by Martin Weinberg Discussion on Bayesian Model Selection and Parameter Estimation in Extragalactic Astronomy by Martin Weinberg Phil Gregory Physics and Astronomy Univ. of British Columbia Introduction Martin Weinberg reported

More information

Probabilistic Robotics

Probabilistic Robotics Probabilistic Robotics Discrete Filters and Particle Filters Models Some slides adopted from: Wolfram Burgard, Cyrill Stachniss, Maren Bennewitz, Kai Arras and Probabilistic Robotics Book SA-1 Probabilistic

More information

Data Mining Chapter 8: Search and Optimization Methods Fall 2011 Ming Li Department of Computer Science and Technology Nanjing University

Data Mining Chapter 8: Search and Optimization Methods Fall 2011 Ming Li Department of Computer Science and Technology Nanjing University Data Mining Chapter 8: Search and Optimization Methods Fall 2011 Ming Li Department of Computer Science and Technology Nanjing University Search & Optimization Search and Optimization method deals with

More information

PATTERN CLASSIFICATION AND SCENE ANALYSIS

PATTERN CLASSIFICATION AND SCENE ANALYSIS PATTERN CLASSIFICATION AND SCENE ANALYSIS RICHARD O. DUDA PETER E. HART Stanford Research Institute, Menlo Park, California A WILEY-INTERSCIENCE PUBLICATION JOHN WILEY & SONS New York Chichester Brisbane

More information

Lecture 8: The EM algorithm

Lecture 8: The EM algorithm 10-708: Probabilistic Graphical Models 10-708, Spring 2017 Lecture 8: The EM algorithm Lecturer: Manuela M. Veloso, Eric P. Xing Scribes: Huiting Liu, Yifan Yang 1 Introduction Previous lecture discusses

More information

Machine Learning for OR & FE

Machine Learning for OR & FE Machine Learning for OR & FE Unsupervised Learning: Clustering Martin Haugh Department of Industrial Engineering and Operations Research Columbia University Email: martin.b.haugh@gmail.com (Some material

More information

Modern Methods of Data Analysis - WS 07/08

Modern Methods of Data Analysis - WS 07/08 Modern Methods of Data Analysis Lecture XV (04.02.08) Contents: Function Minimization (see E. Lohrmann & V. Blobel) Optimization Problem Set of n independent variables Sometimes in addition some constraints

More information

In the real world, light sources emit light particles, which travel in space, reflect at objects or scatter in volumetric media (potentially multiple

In the real world, light sources emit light particles, which travel in space, reflect at objects or scatter in volumetric media (potentially multiple 1 In the real world, light sources emit light particles, which travel in space, reflect at objects or scatter in volumetric media (potentially multiple times) until they are absorbed. On their way, they

More information

VARIANCE REDUCTION TECHNIQUES IN MONTE CARLO SIMULATIONS K. Ming Leung

VARIANCE REDUCTION TECHNIQUES IN MONTE CARLO SIMULATIONS K. Ming Leung POLYTECHNIC UNIVERSITY Department of Computer and Information Science VARIANCE REDUCTION TECHNIQUES IN MONTE CARLO SIMULATIONS K. Ming Leung Abstract: Techniques for reducing the variance in Monte Carlo

More information

Approximate Bayesian Computation. Alireza Shafaei - April 2016

Approximate Bayesian Computation. Alireza Shafaei - April 2016 Approximate Bayesian Computation Alireza Shafaei - April 2016 The Problem Given a dataset, we are interested in. The Problem Given a dataset, we are interested in. The Problem Given a dataset, we are interested

More information

Exam Issued: May 29, 2017, 13:00 Hand in: May 29, 2017, 16:00

Exam Issued: May 29, 2017, 13:00 Hand in: May 29, 2017, 16:00 P. Hadjidoukas, C. Papadimitriou ETH Zentrum, CTL E 13 CH-8092 Zürich High Performance Computing for Science and Engineering II Exam Issued: May 29, 2017, 13:00 Hand in: May 29, 2017, 16:00 Spring semester

More information

REGULARIZED REGRESSION FOR RESERVING AND MORTALITY MODELS GARY G. VENTER

REGULARIZED REGRESSION FOR RESERVING AND MORTALITY MODELS GARY G. VENTER REGULARIZED REGRESSION FOR RESERVING AND MORTALITY MODELS GARY G. VENTER TODAY Advances in model estimation methodology Application to data that comes in rectangles Examples ESTIMATION Problems with MLE

More information

What is the Monte Carlo Method?

What is the Monte Carlo Method? Program What is the Monte Carlo Method? A bit of history Applications The core of Monte Carlo: Random realizations 1st example: Initial conditions for N-body simulations 2nd example: Simulating a proper

More information

(X 1:n η) 1 θ e 1. i=1. Using the traditional MLE derivation technique, the penalized MLEs for η and θ are: = n. (X i η) = 0. i=1 = 1.

(X 1:n η) 1 θ e 1. i=1. Using the traditional MLE derivation technique, the penalized MLEs for η and θ are: = n. (X i η) = 0. i=1 = 1. EXAMINING THE PERFORMANCE OF A CONTROL CHART FOR THE SHIFTED EXPONENTIAL DISTRIBUTION USING PENALIZED MAXIMUM LIKELIHOOD ESTIMATORS: A SIMULATION STUDY USING SAS Austin Brown, M.S., University of Northern

More information

COMPUTATIONAL STATISTICS UNSUPERVISED LEARNING

COMPUTATIONAL STATISTICS UNSUPERVISED LEARNING COMPUTATIONAL STATISTICS UNSUPERVISED LEARNING Luca Bortolussi Department of Mathematics and Geosciences University of Trieste Office 238, third floor, H2bis luca@dmi.units.it Trieste, Winter Semester

More information

An Efficient Model Selection for Gaussian Mixture Model in a Bayesian Framework

An Efficient Model Selection for Gaussian Mixture Model in a Bayesian Framework IEEE SIGNAL PROCESSING LETTERS, VOL. XX, NO. XX, XXX 23 An Efficient Model Selection for Gaussian Mixture Model in a Bayesian Framework Ji Won Yoon arxiv:37.99v [cs.lg] 3 Jul 23 Abstract In order to cluster

More information

CPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2016

CPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2016 CPSC 340: Machine Learning and Data Mining Principal Component Analysis Fall 2016 A2/Midterm: Admin Grades/solutions will be posted after class. Assignment 4: Posted, due November 14. Extra office hours:

More information

ACCURACY AND EFFICIENCY OF MONTE CARLO METHOD. Julius Goodman. Bechtel Power Corporation E. Imperial Hwy. Norwalk, CA 90650, U.S.A.

ACCURACY AND EFFICIENCY OF MONTE CARLO METHOD. Julius Goodman. Bechtel Power Corporation E. Imperial Hwy. Norwalk, CA 90650, U.S.A. - 430 - ACCURACY AND EFFICIENCY OF MONTE CARLO METHOD Julius Goodman Bechtel Power Corporation 12400 E. Imperial Hwy. Norwalk, CA 90650, U.S.A. ABSTRACT The accuracy of Monte Carlo method of simulating

More information

SYDE Winter 2011 Introduction to Pattern Recognition. Clustering

SYDE Winter 2011 Introduction to Pattern Recognition. Clustering SYDE 372 - Winter 2011 Introduction to Pattern Recognition Clustering Alexander Wong Department of Systems Design Engineering University of Waterloo Outline 1 2 3 4 5 All the approaches we have learned

More information

Computational Methods. Randomness and Monte Carlo Methods

Computational Methods. Randomness and Monte Carlo Methods Computational Methods Randomness and Monte Carlo Methods Manfred Huber 2010 1 Randomness and Monte Carlo Methods Introducing randomness in an algorithm can lead to improved efficiencies Random sampling

More information

ECG782: Multidimensional Digital Signal Processing

ECG782: Multidimensional Digital Signal Processing ECG782: Multidimensional Digital Signal Processing Object Recognition http://www.ee.unlv.edu/~b1morris/ecg782/ 2 Outline Knowledge Representation Statistical Pattern Recognition Neural Networks Boosting

More information

METROPOLIS MONTE CARLO SIMULATION

METROPOLIS MONTE CARLO SIMULATION POLYTECHNIC UNIVERSITY Department of Computer and Information Science METROPOLIS MONTE CARLO SIMULATION K. Ming Leung Abstract: The Metropolis method is another method of generating random deviates that

More information

STATISTICS (STAT) Statistics (STAT) 1

STATISTICS (STAT) Statistics (STAT) 1 Statistics (STAT) 1 STATISTICS (STAT) STAT 2013 Elementary Statistics (A) Prerequisites: MATH 1483 or MATH 1513, each with a grade of "C" or better; or an acceptable placement score (see placement.okstate.edu).

More information

The Plan: Basic statistics: Random and pseudorandom numbers and their generation: Chapter 16.

The Plan: Basic statistics: Random and pseudorandom numbers and their generation: Chapter 16. Scientific Computing with Case Studies SIAM Press, 29 http://www.cs.umd.edu/users/oleary/sccswebpage Lecture Notes for Unit IV Monte Carlo Computations Dianne P. O Leary c 28 What is a Monte-Carlo method?

More information

Probability Models.S4 Simulating Random Variables

Probability Models.S4 Simulating Random Variables Operations Research Models and Methods Paul A. Jensen and Jonathan F. Bard Probability Models.S4 Simulating Random Variables In the fashion of the last several sections, we will often create probability

More information

Physics 736. Experimental Methods in Nuclear-, Particle-, and Astrophysics. Lecture 14

Physics 736. Experimental Methods in Nuclear-, Particle-, and Astrophysics. Lecture 14 Physics 736 Experimental Methods in Nuclear-, Particle-, and Astrophysics Lecture 14 Karsten Heeger heeger@wisc.edu Course Schedule and Reading course website http://neutrino.physics.wisc.edu/teaching/phys736/

More information

Statistics 202: Data Mining. c Jonathan Taylor. Outliers Based in part on slides from textbook, slides of Susan Holmes.

Statistics 202: Data Mining. c Jonathan Taylor. Outliers Based in part on slides from textbook, slides of Susan Holmes. Outliers Based in part on slides from textbook, slides of Susan Holmes December 2, 2012 1 / 1 Concepts What is an outlier? The set of data points that are considerably different than the remainder of the

More information

Bootstrapping Methods

Bootstrapping Methods Bootstrapping Methods example of a Monte Carlo method these are one Monte Carlo statistical method some Bayesian statistical methods are Monte Carlo we can also simulate models using Monte Carlo methods

More information

Optimal designs for comparing curves

Optimal designs for comparing curves Optimal designs for comparing curves Holger Dette, Ruhr-Universität Bochum Maria Konstantinou, Ruhr-Universität Bochum Kirsten Schorning, Ruhr-Universität Bochum FP7 HEALTH 2013-602552 Outline 1 Motivation

More information

BART STAT8810, Fall 2017

BART STAT8810, Fall 2017 BART STAT8810, Fall 2017 M.T. Pratola November 1, 2017 Today BART: Bayesian Additive Regression Trees BART: Bayesian Additive Regression Trees Additive model generalizes the single-tree regression model:

More information

10/14/2017. Dejan Sarka. Anomaly Detection. Sponsors

10/14/2017. Dejan Sarka. Anomaly Detection. Sponsors Dejan Sarka Anomaly Detection Sponsors About me SQL Server MVP (17 years) and MCT (20 years) 25 years working with SQL Server Authoring 16 th book Authoring many courses, articles Agenda Introduction Simple

More information

AP Calculus BC Course Description

AP Calculus BC Course Description AP Calculus BC Course Description COURSE OUTLINE: The following topics define the AP Calculus BC course as it is taught over three trimesters, each consisting of twelve week grading periods. Limits and

More information

Overview Citation. ML Introduction. Overview Schedule. ML Intro Dataset. Introduction to Semi-Supervised Learning Review 10/4/2010

Overview Citation. ML Introduction. Overview Schedule. ML Intro Dataset. Introduction to Semi-Supervised Learning Review 10/4/2010 INFORMATICS SEMINAR SEPT. 27 & OCT. 4, 2010 Introduction to Semi-Supervised Learning Review 2 Overview Citation X. Zhu and A.B. Goldberg, Introduction to Semi- Supervised Learning, Morgan & Claypool Publishers,

More information

Machine Learning

Machine Learning Machine Learning 10-601 Tom M. Mitchell Machine Learning Department Carnegie Mellon University February 25, 2015 Today: Graphical models Bayes Nets: Inference Learning EM Readings: Bishop chapter 8 Mitchell

More information

Expectation Maximization (EM) and Gaussian Mixture Models

Expectation Maximization (EM) and Gaussian Mixture Models Expectation Maximization (EM) and Gaussian Mixture Models Reference: The Elements of Statistical Learning, by T. Hastie, R. Tibshirani, J. Friedman, Springer 1 2 3 4 5 6 7 8 Unsupervised Learning Motivation

More information

CS839: Probabilistic Graphical Models. Lecture 10: Learning with Partially Observed Data. Theo Rekatsinas

CS839: Probabilistic Graphical Models. Lecture 10: Learning with Partially Observed Data. Theo Rekatsinas CS839: Probabilistic Graphical Models Lecture 10: Learning with Partially Observed Data Theo Rekatsinas 1 Partially Observed GMs Speech recognition 2 Partially Observed GMs Evolution 3 Partially Observed

More information

10-701/15-781, Fall 2006, Final

10-701/15-781, Fall 2006, Final -7/-78, Fall 6, Final Dec, :pm-8:pm There are 9 questions in this exam ( pages including this cover sheet). If you need more room to work out your answer to a question, use the back of the page and clearly

More information

Simulation Modeling and Analysis

Simulation Modeling and Analysis Simulation Modeling and Analysis FOURTH EDITION Averill M. Law President Averill M. Law & Associates, Inc. Tucson, Arizona, USA www. averill-law. com Boston Burr Ridge, IL Dubuque, IA New York San Francisco

More information

FMA901F: Machine Learning Lecture 3: Linear Models for Regression. Cristian Sminchisescu

FMA901F: Machine Learning Lecture 3: Linear Models for Regression. Cristian Sminchisescu FMA901F: Machine Learning Lecture 3: Linear Models for Regression Cristian Sminchisescu Machine Learning: Frequentist vs. Bayesian In the frequentist setting, we seek a fixed parameter (vector), with value(s)

More information

Rough Paths, Hopf Algebras and Chinese handwriting

Rough Paths, Hopf Algebras and Chinese handwriting Rough Paths, Hopf Algebras and the classification of streams - Kings College, London, 7th October 2016 - p1/29 Rough Paths, Hopf Algebras and Chinese handwriting Greg Gyurko Hao Ni Terry Lyons Andrey Kormlitzn

More information

The PageRank Computation in Google, Randomized Algorithms and Consensus of Multi-Agent Systems

The PageRank Computation in Google, Randomized Algorithms and Consensus of Multi-Agent Systems The PageRank Computation in Google, Randomized Algorithms and Consensus of Multi-Agent Systems Roberto Tempo IEIIT-CNR Politecnico di Torino tempo@polito.it This talk The objective of this talk is to discuss

More information

The Bootstrap and Jackknife

The Bootstrap and Jackknife The Bootstrap and Jackknife Summer 2017 Summer Institutes 249 Bootstrap & Jackknife Motivation In scientific research Interest often focuses upon the estimation of some unknown parameter, θ. The parameter

More information

YEAR 12 Core 1 & 2 Maths Curriculum (A Level Year 1)

YEAR 12 Core 1 & 2 Maths Curriculum (A Level Year 1) YEAR 12 Core 1 & 2 Maths Curriculum (A Level Year 1) Algebra and Functions Quadratic Functions Equations & Inequalities Binomial Expansion Sketching Curves Coordinate Geometry Radian Measures Sine and

More information

Topics in Machine Learning-EE 5359 Model Assessment and Selection

Topics in Machine Learning-EE 5359 Model Assessment and Selection Topics in Machine Learning-EE 5359 Model Assessment and Selection Ioannis D. Schizas Electrical Engineering Department University of Texas at Arlington 1 Training and Generalization Training stage: Utilizing

More information

An Introduction to the Bootstrap

An Introduction to the Bootstrap An Introduction to the Bootstrap Bradley Efron Department of Statistics Stanford University and Robert J. Tibshirani Department of Preventative Medicine and Biostatistics and Department of Statistics,

More information