Outline. Motivation Contest Sample. Estimator. Loss. Standard Error. Prior Pseudo-Data. Bayesian Estimator. Estimators. John Dodson.

Size: px
Start display at page:

Download "Outline. Motivation Contest Sample. Estimator. Loss. Standard Error. Prior Pseudo-Data. Bayesian Estimator. Estimators. John Dodson."

Transcription

1 s s Practitioner Course: Portfolio Optimization September 24, 2008

2 s

3 The Goal of s The goal of estimation is to assign numerical values to the parameters of a probability model. Considerations There are several risks to consider What if the model is mis-specified? What if the data is corrupt? These are addressed under the subject of robust statistics, which Meucci covers well, but which we will not be covering in this module

4 ! s To motivate the discussion, I am going to pose a challenge. Challenge There is a sample of U(0, θ) for some unknown (to you) parameter θ at fm503/docs/case1.dat Provide an interval estimate for θ The team whose interval included the true θ and is the narrowest wins Hint: You can load the sample into MATLAB with the command sample=sscanf(urlread( <URL> ), %f );

5 s In classical statistics, the term sample has two related meanings an (unordered) set of N values drawn from the sample space of some random variable X a random variable consisting of N (independent) copies of some random variable X You can think of the former as a realization of the latter. We can characterize the latter version of a sample, which we will denote hereafter by Y N = (X 1,..., X N ), as a random variable with f YN (Y ) = f X (X 1 ) f X (X N ) because we have assumed that the draws are independent.

6 The characterization of the sample Y N can often be expressed as the characterization of a collection of partial results, T N = T (X 1,..., X N ) called sufficient statistics. Important Example Say X N (µ, σ 2 ) and we have a sample Y N = (X 1,..., X N ). The density function of the sample is f YN (Y ) = (2π σ 2 ) N/2 e 1 2 σ 2 N i=1 (X i µ) 2 The form of this suggests T N = ( X i, X 2 i ) which yields ( N T2 T 2 ) (N 3)/2 1 f TN (T ) = N N/2 1 2 N/2 π Γ ( ) N 1 2 ( ( ) ) 1 N/2 exp σ 2 T2 N 2 T1 N µ + µ2 + log σ 2 ( ) s

7 Classical An estimator is a function of a sample. If the sample is considered to be random, the value of an estimator is a random variable subject to characterization If the estimator is applied to an actual sample, consisting of N draws from the sample space, the value of the estimator is called an estimate. Parameter We will be mostly interested in estimating the parameters of a characterization, which we will denote generically by θ. For a univariate normal, for example, θ = ( µ, σ 2). We will denote the parameter estimator by ˆθ (Y N ) where Y = (X 1,..., X N ) is the sample represented by N independent copies of the random variable X with a characterization parameterized by θ. s

8 Since ˆθ (Y N ) is a random variable, it is natural to explore its location and dispersion In particular, we are interested in how far it can diverge from the (unknown) true value, θ So we introduce a norm with respect to some positive definite metric Q, such that v 2 = v Q v for any v in the sample space of θ is the random variable ˆθ θ 2 Bias is the (unknown) value Eˆθ θ Inefficiency is the value E ˆθ Eˆθ 2 There is a usually a trade-off between bias and inefficiency. In fact, E = Bias 2 + Inef 2 s

9 (MLE) Since we have the distribution of the sample, perhaps in terms of sufficient statistics, it is natural to define an estimator for the parameters as the value of the parameters such that the sample observed is most likely 1. That is, ˆθ(y) = arg max f YN θ(y) θ = arg max f TN θ(t) θ where the sample is y = (x 1,..., x N ) or t = T (x 1,..., x N ). Important Example Consider the univariate normal from above. In terms of the sufficient statistics, the MLE (based on ( )) is ( ˆµˆσ 2 ) 1 ( = arg min (µ,σ 2 ) σ 2 t2 N 2 t1 N µ + µ2) + log σ 2 or s 1 This does not guarantee that the observation equals the mode.

10 (MLE) Important Example The solution to this (the MLE for a univariate normal) is ˆµ = t 1 N ˆσ 2 = t ( 2 N t1 N = x ) 2 = x x x x This result extends to the mutivariate case X R M whereby x has M rows and N columns. Bias We can see that the MLE is (slightly) biased. s E ˆµ = µ E ˆσ 2 = N 1 N σ2

11 Fisher Information In general we cannot evaluate the characterization of the distribution of an estimator. An application of the Central Limit Theorem gives us a useful approximation. lim N ( N (ˆθ (Y N ) θ) N where I is the Fisher Information Matrix I X θ = cov θ log f X θ(x ) = E 2 θ θ log f X θ(x ) Important Example For the univariate normal, this evaluates to ( 1 ) I X (µ,σ 2 ) = 0 σ σ 4 0, I 1 X θ ) s

12 Cramér-Rao Bound The Cramér-Rao Bound gives us a limit on the resolution of a classical estimator. 1 X θ cov ˆθ (Y N ) Eˆθ θ I N Eˆθ θ which is obtained if the estimator is efficient. The standard deviations of the margins of the estimator are called the standard errors se(ˆθ) = diag diag diag cov ˆθ In the case of the univariate normal example, this is ( ) ( σ ) N se ˆµˆσ 2 σ 2 N 1 N/2 N s

13 In estimation we do not endow the sample with a characterization; rather, we endow the parameters with a characterization, described by hyper-parameters. This is the prior characterization. We then update the characterization by conditioning on the observed data using Bayes Rule, which leads to the posterior characterization from which we can build estimates. f θ YN (θ) f θ (θ) f YN θ(y N ) The approach is inherently biased. The prior is ideally based on beliefs about the results before any data have been observed The approach is appropriate when the statistician is also a subject matter expert (such as you) s

14 In principle, the characterization of the parameter prior can be completely arbitrary. Conjugate But a judicious choice exists, which is to choose a prior from a family that this closed under updates. Such a prior is termed the conjugate prior. With a conjugate prior, updating can be expressed as an algebraic transformation of the hyper-parameters, involving the prior values, the sufficient statistics, and the sample size Improper It can be useful to consider a prior that has no information, for example a prior whose density is uniform over the sample space of the hyper-parameters. This is termed an improper prior. s

15 Important Example There is a conjugate prior for the univariate normal. It has a somewhat complicated form, but it is nonetheless very useful and worth learning. It is termed the normal-inverse Gamma distribution, and it is defined by the mixture ) µ σ 2 N (µ 0, σ2 λ 0 1 σ 2 G ( ν 0, 1 σ 2 0 The posterior is in the same family with updated parameters based on the sufficient statistics t 1, t 2 λ N = λ 0 + N ν N = ν 0 + N µ N = λ 0 µ 0 + t 1 λ 0 + N σ 2 N = σ2 0 + λ 0 µ t 2 (λ 0 µ 0 + t 1 ) 2 λ 0 + N and this can be generalized to the multinormal setting. ) s

16 Pseudo-data A useful application of the conjugate prior is to imagine that prior itself is a posterior with respect to some imaginary (random) dataset Ỹ = ( X 1,..., XÑ) where each X i are drawn independently from a known distribution representing our beliefs. f θ YN (θ) f YN θ(y) f θ (θ) ( ) = f YN θ(y) f YÑ θ(ỹ ) fθ im (θ) ) = f YN+Ñ (y θ Ỹ fθ im (θ) Application If we want to simulate from the posterior, we simply append the actual sample with a pseudo-sample of variates drawn from the characterization of X, then proceed with classical estimation (e.g. MLE). s

17 Once we know the posterior distribution f θ YN, we still need to provide a result. Some naïve approached include mode and modal dispersion, ˆθ = arg max f θ YN mean and covariance, ˆθ = E (θ Y N ) A more sophisticated approach is to find the minimum-measure region for a given level of confidence 1 α. In the univariate setting, this would be (θ 0, θ 1 ) for arg min θ 0 θ 1 (θ 0 ) θ 0 and θ 1 (θ 0 ) = Q θ YN ( Fθ YN (θ 0 ) + α ). Function The ideal approach is to find a parameter value that minimizes the expected value of some loss function customized to the subsequent application. s

MFM Practitioner Module: Risk & Asset Allocation. John Dodson. January 28, 2015

MFM Practitioner Module: Risk & Asset Allocation. John Dodson. January 28, 2015 MFM Practitioner Module: Risk & Asset Allocation Estimator January 28, 2015 Estimator Estimator Review: tells us how to reverse the roles in conditional probability. f Y X {x} (y) f Y (y)f X Y {y} (x)

More information

MFM Practitioner Module: Risk & Asset Allocation. John Dodson. February 3, 2010

MFM Practitioner Module: Risk & Asset Allocation. John Dodson. February 3, 2010 MFM Practitioner Module: Risk & Asset Allocation Estimator February 3, 2010 Estimator Estimator In estimation we do not endow the sample with a characterization; rather, we endow the parameters with a

More information

MFM Practitioner Module: Risk & Asset Allocation. John Dodson. February 18, 2015

MFM Practitioner Module: Risk & Asset Allocation. John Dodson. February 18, 2015 MFM Practitioner Module: Risk & Asset Allocation February 18, 2015 No introduction to portfolio optimization would be complete without acknowledging the significant contribution of the Markowitz mean-variance

More information

Bayesian Optimization

Bayesian Optimization Practitioner Course: Portfolio October 15, 2008 No introduction to portfolio optimization would be complete without acknowledging the significant contribution of the Markowitz mean-variance efficient frontier

More information

The Expectation-Maximization Algorithm

The Expectation-Maximization Algorithm 1/29 EM & Latent Variable Models Gaussian Mixture Models EM Theory The Expectation-Maximization Algorithm Mihaela van der Schaar Department of Engineering Science University of Oxford MLE for Latent Variable

More information

Fall 2017 STAT 532 Homework Peter Hoff. 1. Let P be a probability measure on a collection of sets A.

Fall 2017 STAT 532 Homework Peter Hoff. 1. Let P be a probability measure on a collection of sets A. 1. Let P be a probability measure on a collection of sets A. (a) For each n N, let H n be a set in A such that H n H n+1. Show that P (H n ) monotonically converges to P ( k=1 H k) as n. (b) For each n

More information

6.867 Machine Learning

6.867 Machine Learning 6.867 Machine Learning Problem set 1 Due Thursday, September 19, in class What and how to turn in? Turn in short written answers to the questions explicitly stated, and when requested to explain or prove.

More information

6.867 Machine Learning

6.867 Machine Learning 6.867 Machine Learning Problem set 1 Solutions Thursday, September 19 What and how to turn in? Turn in short written answers to the questions explicitly stated, and when requested to explain or prove.

More information

COS513 LECTURE 8 STATISTICAL CONCEPTS

COS513 LECTURE 8 STATISTICAL CONCEPTS COS513 LECTURE 8 STATISTICAL CONCEPTS NIKOLAI SLAVOV AND ANKUR PARIKH 1. MAKING MEANINGFUL STATEMENTS FROM JOINT PROBABILITY DISTRIBUTIONS. A graphical model (GM) represents a family of probability distributions

More information

Statistical Data Mining and Machine Learning Hilary Term 2016

Statistical Data Mining and Machine Learning Hilary Term 2016 Statistical Data Mining and Machine Learning Hilary Term 2016 Dino Sejdinovic Department of Statistics Oxford Slides and other materials available at: http://www.stats.ox.ac.uk/~sejdinov/sdmml Naïve Bayes

More information

Density Estimation. Seungjin Choi

Density Estimation. Seungjin Choi Density Estimation Seungjin Choi Department of Computer Science and Engineering Pohang University of Science and Technology 77 Cheongam-ro, Nam-gu, Pohang 37673, Korea seungjin@postech.ac.kr http://mlg.postech.ac.kr/

More information

Lecture 8: Information Theory and Statistics

Lecture 8: Information Theory and Statistics Lecture 8: Information Theory and Statistics Part II: Hypothesis Testing and I-Hsiang Wang Department of Electrical Engineering National Taiwan University ihwang@ntu.edu.tw December 23, 2015 1 / 50 I-Hsiang

More information

Lecture 7 Introduction to Statistical Decision Theory

Lecture 7 Introduction to Statistical Decision Theory Lecture 7 Introduction to Statistical Decision Theory I-Hsiang Wang Department of Electrical Engineering National Taiwan University ihwang@ntu.edu.tw December 20, 2016 1 / 55 I-Hsiang Wang IT Lecture 7

More information

ECE 275A Homework 6 Solutions

ECE 275A Homework 6 Solutions ECE 275A Homework 6 Solutions. The notation used in the solutions for the concentration (hyper) ellipsoid problems is defined in the lecture supplement on concentration ellipsoids. Note that θ T Σ θ =

More information

Dependence. Practitioner Course: Portfolio Optimization. John Dodson. September 10, Dependence. John Dodson. Outline.

Dependence. Practitioner Course: Portfolio Optimization. John Dodson. September 10, Dependence. John Dodson. Outline. Practitioner Course: Portfolio Optimization September 10, 2008 Before we define dependence, it is useful to define Random variables X and Y are independent iff For all x, y. In particular, F (X,Y ) (x,

More information

Parametric Techniques Lecture 3

Parametric Techniques Lecture 3 Parametric Techniques Lecture 3 Jason Corso SUNY at Buffalo 22 January 2009 J. Corso (SUNY at Buffalo) Parametric Techniques Lecture 3 22 January 2009 1 / 39 Introduction In Lecture 2, we learned how to

More information

Parametric Techniques

Parametric Techniques Parametric Techniques Jason J. Corso SUNY at Buffalo J. Corso (SUNY at Buffalo) Parametric Techniques 1 / 39 Introduction When covering Bayesian Decision Theory, we assumed the full probabilistic structure

More information

Maximum Likelihood, Logistic Regression, and Stochastic Gradient Training

Maximum Likelihood, Logistic Regression, and Stochastic Gradient Training Maximum Likelihood, Logistic Regression, and Stochastic Gradient Training Charles Elkan elkan@cs.ucsd.edu January 17, 2013 1 Principle of maximum likelihood Consider a family of probability distributions

More information

Performance Comparison of K-Means and Expectation Maximization with Gaussian Mixture Models for Clustering EE6540 Final Project

Performance Comparison of K-Means and Expectation Maximization with Gaussian Mixture Models for Clustering EE6540 Final Project Performance Comparison of K-Means and Expectation Maximization with Gaussian Mixture Models for Clustering EE6540 Final Project Devin Cornell & Sushruth Sastry May 2015 1 Abstract In this article, we explore

More information

Lecture 4: Probabilistic Learning. Estimation Theory. Classification with Probability Distributions

Lecture 4: Probabilistic Learning. Estimation Theory. Classification with Probability Distributions DD2431 Autumn, 2014 1 2 3 Classification with Probability Distributions Estimation Theory Classification in the last lecture we assumed we new: P(y) Prior P(x y) Lielihood x2 x features y {ω 1,..., ω K

More information

Estimation. Max Welling. California Institute of Technology Pasadena, CA

Estimation. Max Welling. California Institute of Technology Pasadena, CA Preliminaries Estimation Max Welling California Institute of Technology 36-93 Pasadena, CA 925 welling@vision.caltech.edu Let x denote a random variable and p(x) its probability density. x may be multidimensional

More information

ECE531 Lecture 10b: Maximum Likelihood Estimation

ECE531 Lecture 10b: Maximum Likelihood Estimation ECE531 Lecture 10b: Maximum Likelihood Estimation D. Richard Brown III Worcester Polytechnic Institute 05-Apr-2011 Worcester Polytechnic Institute D. Richard Brown III 05-Apr-2011 1 / 23 Introduction So

More information

Bayesian Learning. HT2015: SC4 Statistical Data Mining and Machine Learning. Maximum Likelihood Principle. The Bayesian Learning Framework

Bayesian Learning. HT2015: SC4 Statistical Data Mining and Machine Learning. Maximum Likelihood Principle. The Bayesian Learning Framework HT5: SC4 Statistical Data Mining and Machine Learning Dino Sejdinovic Department of Statistics Oxford http://www.stats.ox.ac.uk/~sejdinov/sdmml.html Maximum Likelihood Principle A generative model for

More information

Dependence. MFM Practitioner Module: Risk & Asset Allocation. John Dodson. September 11, Dependence. John Dodson. Outline.

Dependence. MFM Practitioner Module: Risk & Asset Allocation. John Dodson. September 11, Dependence. John Dodson. Outline. MFM Practitioner Module: Risk & Asset Allocation September 11, 2013 Before we define dependence, it is useful to define Random variables X and Y are independent iff For all x, y. In particular, F (X,Y

More information

Parameter estimation and forecasting. Cristiano Porciani AIfA, Uni-Bonn

Parameter estimation and forecasting. Cristiano Porciani AIfA, Uni-Bonn Parameter estimation and forecasting Cristiano Porciani AIfA, Uni-Bonn Questions? C. Porciani Estimation & forecasting 2 Temperature fluctuations Variance at multipole l (angle ~180o/l) C. Porciani Estimation

More information

ST 740: Linear Models and Multivariate Normal Inference

ST 740: Linear Models and Multivariate Normal Inference ST 740: Linear Models and Multivariate Normal Inference Alyson Wilson Department of Statistics North Carolina State University November 4, 2013 A. Wilson (NCSU STAT) Linear Models November 4, 2013 1 /

More information

Mathematical statistics

Mathematical statistics October 4 th, 2018 Lecture 12: Information Where are we? Week 1 Week 2 Week 4 Week 7 Week 10 Week 14 Probability reviews Chapter 6: Statistics and Sampling Distributions Chapter 7: Point Estimation Chapter

More information

A Few Notes on Fisher Information (WIP)

A Few Notes on Fisher Information (WIP) A Few Notes on Fisher Information (WIP) David Meyer dmm@{-4-5.net,uoregon.edu} Last update: April 30, 208 Definitions There are so many interesting things about Fisher Information and its theoretical properties

More information

Covariance function estimation in Gaussian process regression

Covariance function estimation in Gaussian process regression Covariance function estimation in Gaussian process regression François Bachoc Department of Statistics and Operations Research, University of Vienna WU Research Seminar - May 2015 François Bachoc Gaussian

More information

Econometrics I, Estimation

Econometrics I, Estimation Econometrics I, Estimation Department of Economics Stanford University September, 2008 Part I Parameter, Estimator, Estimate A parametric is a feature of the population. An estimator is a function of the

More information

Gibbs Sampling in Linear Models #2

Gibbs Sampling in Linear Models #2 Gibbs Sampling in Linear Models #2 Econ 690 Purdue University Outline 1 Linear Regression Model with a Changepoint Example with Temperature Data 2 The Seemingly Unrelated Regressions Model 3 Gibbs sampling

More information

LECTURE 5 NOTES. n t. t Γ(a)Γ(b) pt+a 1 (1 p) n t+b 1. The marginal density of t is. Γ(t + a)γ(n t + b) Γ(n + a + b)

LECTURE 5 NOTES. n t. t Γ(a)Γ(b) pt+a 1 (1 p) n t+b 1. The marginal density of t is. Γ(t + a)γ(n t + b) Γ(n + a + b) LECTURE 5 NOTES 1. Bayesian point estimators. In the conventional (frequentist) approach to statistical inference, the parameter θ Θ is considered a fixed quantity. In the Bayesian approach, it is considered

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

A Discussion of the Bayesian Approach

A Discussion of the Bayesian Approach A Discussion of the Bayesian Approach Reference: Chapter 10 of Theoretical Statistics, Cox and Hinkley, 1974 and Sujit Ghosh s lecture notes David Madigan Statistics The subject of statistics concerns

More information

ELEG 5633 Detection and Estimation Minimum Variance Unbiased Estimators (MVUE)

ELEG 5633 Detection and Estimation Minimum Variance Unbiased Estimators (MVUE) 1 ELEG 5633 Detection and Estimation Minimum Variance Unbiased Estimators (MVUE) Jingxian Wu Department of Electrical Engineering University of Arkansas Outline Minimum Variance Unbiased Estimators (MVUE)

More information

Chapter 9: Interval Estimation and Confidence Sets Lecture 16: Confidence sets and credible sets

Chapter 9: Interval Estimation and Confidence Sets Lecture 16: Confidence sets and credible sets Chapter 9: Interval Estimation and Confidence Sets Lecture 16: Confidence sets and credible sets Confidence sets We consider a sample X from a population indexed by θ Θ R k. We are interested in ϑ, a vector-valued

More information

STAT215: Solutions for Homework 2

STAT215: Solutions for Homework 2 STAT25: Solutions for Homework 2 Due: Wednesday, Feb 4. (0 pt) Suppose we take one observation, X, from the discrete distribution, x 2 0 2 Pr(X x θ) ( θ)/4 θ/2 /2 (3 θ)/2 θ/4, 0 θ Find an unbiased estimator

More information

Introduction to Probabilistic Machine Learning

Introduction to Probabilistic Machine Learning Introduction to Probabilistic Machine Learning Piyush Rai Dept. of CSE, IIT Kanpur (Mini-course 1) Nov 03, 2015 Piyush Rai (IIT Kanpur) Introduction to Probabilistic Machine Learning 1 Machine Learning

More information

Discrete Mathematics and Probability Theory Fall 2015 Lecture 21

Discrete Mathematics and Probability Theory Fall 2015 Lecture 21 CS 70 Discrete Mathematics and Probability Theory Fall 205 Lecture 2 Inference In this note we revisit the problem of inference: Given some data or observations from the world, what can we infer about

More information

Statistics: Learning models from data

Statistics: Learning models from data DS-GA 1002 Lecture notes 5 October 19, 2015 Statistics: Learning models from data Learning models from data that are assumed to be generated probabilistically from a certain unknown distribution is a crucial

More information

Lecture 4: Probabilistic Learning

Lecture 4: Probabilistic Learning DD2431 Autumn, 2015 1 Maximum Likelihood Methods Maximum A Posteriori Methods Bayesian methods 2 Classification vs Clustering Heuristic Example: K-means Expectation Maximization 3 Maximum Likelihood Methods

More information

CPSC 540: Machine Learning

CPSC 540: Machine Learning CPSC 540: Machine Learning Multivariate Gaussians Mark Schmidt University of British Columbia Winter 2019 Last Time: Multivariate Gaussian http://personal.kenyon.edu/hartlaub/mellonproject/bivariate2.html

More information

Parametric Unsupervised Learning Expectation Maximization (EM) Lecture 20.a

Parametric Unsupervised Learning Expectation Maximization (EM) Lecture 20.a Parametric Unsupervised Learning Expectation Maximization (EM) Lecture 20.a Some slides are due to Christopher Bishop Limitations of K-means Hard assignments of data points to clusters small shift of a

More information

ECE 275A Homework 7 Solutions

ECE 275A Homework 7 Solutions ECE 275A Homework 7 Solutions Solutions 1. For the same specification as in Homework Problem 6.11 we want to determine an estimator for θ using the Method of Moments (MOM). In general, the MOM estimator

More information

One-parameter models

One-parameter models One-parameter models Patrick Breheny January 22 Patrick Breheny BST 701: Bayesian Modeling in Biostatistics 1/17 Introduction Binomial data is not the only example in which Bayesian solutions can be worked

More information

Introduction to Machine Learning. Lecture 2

Introduction to Machine Learning. Lecture 2 Introduction to Machine Learning Lecturer: Eran Halperin Lecture 2 Fall Semester Scribe: Yishay Mansour Some of the material was not presented in class (and is marked with a side line) and is given for

More information

Answer Key for STAT 200B HW No. 7

Answer Key for STAT 200B HW No. 7 Answer Key for STAT 200B HW No. 7 May 5, 2007 Problem 2.2 p. 649 Assuming binomial 2-sample model ˆπ =.75, ˆπ 2 =.6. a ˆτ = ˆπ 2 ˆπ =.5. From Ex. 2.5a on page 644: ˆπ ˆπ + ˆπ 2 ˆπ 2.75.25.6.4 = + =.087;

More information

Master s Written Examination

Master s Written Examination Master s Written Examination Option: Statistics and Probability Spring 05 Full points may be obtained for correct answers to eight questions Each numbered question (which may have several parts) is worth

More information

STATS 200: Introduction to Statistical Inference. Lecture 29: Course review

STATS 200: Introduction to Statistical Inference. Lecture 29: Course review STATS 200: Introduction to Statistical Inference Lecture 29: Course review Course review We started in Lecture 1 with a fundamental assumption: Data is a realization of a random process. The goal throughout

More information

Predictive Distributions

Predictive Distributions Predictive Distributions October 6, 2010 Hoff Chapter 4 5 October 5, 2010 Prior Predictive Distribution Before we observe the data, what do we expect the distribution of observations to be? p(y i ) = p(y

More information

Part 6: Multivariate Normal and Linear Models

Part 6: Multivariate Normal and Linear Models Part 6: Multivariate Normal and Linear Models 1 Multiple measurements Up until now all of our statistical models have been univariate models models for a single measurement on each member of a sample of

More information

Variations. ECE 6540, Lecture 10 Maximum Likelihood Estimation

Variations. ECE 6540, Lecture 10 Maximum Likelihood Estimation Variations ECE 6540, Lecture 10 Last Time BLUE (Best Linear Unbiased Estimator) Formulation Advantages Disadvantages 2 The BLUE A simplification Assume the estimator is a linear system For a single parameter

More information

CSC321 Lecture 18: Learning Probabilistic Models

CSC321 Lecture 18: Learning Probabilistic Models CSC321 Lecture 18: Learning Probabilistic Models Roger Grosse Roger Grosse CSC321 Lecture 18: Learning Probabilistic Models 1 / 25 Overview So far in this course: mainly supervised learning Language modeling

More information

ECE 275B Homework # 1 Solutions Version Winter 2015

ECE 275B Homework # 1 Solutions Version Winter 2015 ECE 275B Homework # 1 Solutions Version Winter 2015 1. (a) Because x i are assumed to be independent realizations of a continuous random variable, it is almost surely (a.s.) 1 the case that x 1 < x 2

More information

Advanced Signal Processing Introduction to Estimation Theory

Advanced Signal Processing Introduction to Estimation Theory Advanced Signal Processing Introduction to Estimation Theory Danilo Mandic, room 813, ext: 46271 Department of Electrical and Electronic Engineering Imperial College London, UK d.mandic@imperial.ac.uk,

More information

An Introduction to Expectation-Maximization

An Introduction to Expectation-Maximization An Introduction to Expectation-Maximization Dahua Lin Abstract This notes reviews the basics about the Expectation-Maximization EM) algorithm, a popular approach to perform model estimation of the generative

More information

Linear Models A linear model is defined by the expression

Linear Models A linear model is defined by the expression Linear Models A linear model is defined by the expression x = F β + ɛ. where x = (x 1, x 2,..., x n ) is vector of size n usually known as the response vector. β = (β 1, β 2,..., β p ) is the transpose

More information

σ(a) = a N (x; 0, 1 2 ) dx. σ(a) = Φ(a) =

σ(a) = a N (x; 0, 1 2 ) dx. σ(a) = Φ(a) = Until now we have always worked with likelihoods and prior distributions that were conjugate to each other, allowing the computation of the posterior distribution to be done in closed form. Unfortunately,

More information

Fractional Hot Deck Imputation for Robust Inference Under Item Nonresponse in Survey Sampling

Fractional Hot Deck Imputation for Robust Inference Under Item Nonresponse in Survey Sampling Fractional Hot Deck Imputation for Robust Inference Under Item Nonresponse in Survey Sampling Jae-Kwang Kim 1 Iowa State University June 26, 2013 1 Joint work with Shu Yang Introduction 1 Introduction

More information

1 Bayesian Linear Regression (BLR)

1 Bayesian Linear Regression (BLR) Statistical Techniques in Robotics (STR, S15) Lecture#10 (Wednesday, February 11) Lecturer: Byron Boots Gaussian Properties, Bayesian Linear Regression 1 Bayesian Linear Regression (BLR) In linear regression,

More information

Bayesian Inference. Chapter 4: Regression and Hierarchical Models

Bayesian Inference. Chapter 4: Regression and Hierarchical Models Bayesian Inference Chapter 4: Regression and Hierarchical Models Conchi Ausín and Mike Wiper Department of Statistics Universidad Carlos III de Madrid Advanced Statistics and Data Mining Summer School

More information

Statistics & Data Sciences: First Year Prelim Exam May 2018

Statistics & Data Sciences: First Year Prelim Exam May 2018 Statistics & Data Sciences: First Year Prelim Exam May 2018 Instructions: 1. Do not turn this page until instructed to do so. 2. Start each new question on a new sheet of paper. 3. This is a closed book

More information

How Much Evidence Should One Collect?

How Much Evidence Should One Collect? How Much Evidence Should One Collect? Remco Heesen October 10, 2013 Abstract This paper focuses on the question how much evidence one should collect before deciding on the truth-value of a proposition.

More information

Stat 535 C - Statistical Computing & Monte Carlo Methods. Arnaud Doucet.

Stat 535 C - Statistical Computing & Monte Carlo Methods. Arnaud Doucet. Stat 535 C - Statistical Computing & Monte Carlo Methods Arnaud Doucet Email: arnaud@cs.ubc.ca 1 Suggested Projects: www.cs.ubc.ca/~arnaud/projects.html First assignement on the web: capture/recapture.

More information

Bayesian performance

Bayesian performance Bayesian performance Frequentist properties of estimators refer to the performance of an estimator (say the posterior mean) over repeated experiments under the same conditions. The posterior distribution

More information

Introduction to Machine Learning CMU-10701

Introduction to Machine Learning CMU-10701 Introduction to Machine Learning CMU-10701 2. MLE, MAP, Bayes classification Barnabás Póczos & Aarti Singh 2014 Spring Administration http://www.cs.cmu.edu/~aarti/class/10701_spring14/index.html Blackboard

More information

ECE 275B Homework # 1 Solutions Winter 2018

ECE 275B Homework # 1 Solutions Winter 2018 ECE 275B Homework # 1 Solutions Winter 2018 1. (a) Because x i are assumed to be independent realizations of a continuous random variable, it is almost surely (a.s.) 1 the case that x 1 < x 2 < < x n Thus,

More information

COS513: FOUNDATIONS OF PROBABILISTIC MODELS LECTURE 9: LINEAR REGRESSION

COS513: FOUNDATIONS OF PROBABILISTIC MODELS LECTURE 9: LINEAR REGRESSION COS513: FOUNDATIONS OF PROBABILISTIC MODELS LECTURE 9: LINEAR REGRESSION SEAN GERRISH AND CHONG WANG 1. WAYS OF ORGANIZING MODELS In probabilistic modeling, there are several ways of organizing models:

More information

Part 4: Multi-parameter and normal models

Part 4: Multi-parameter and normal models Part 4: Multi-parameter and normal models 1 The normal model Perhaps the most useful (or utilized) probability model for data analysis is the normal distribution There are several reasons for this, e.g.,

More information

Lecture : Probabilistic Machine Learning

Lecture : Probabilistic Machine Learning Lecture : Probabilistic Machine Learning Riashat Islam Reasoning and Learning Lab McGill University September 11, 2018 ML : Many Methods with Many Links Modelling Views of Machine Learning Machine Learning

More information

STAT 512 sp 2018 Summary Sheet

STAT 512 sp 2018 Summary Sheet STAT 5 sp 08 Summary Sheet Karl B. Gregory Spring 08. Transformations of a random variable Let X be a rv with support X and let g be a function mapping X to Y with inverse mapping g (A = {x X : g(x A}

More information

Parameter estimation Conditional risk

Parameter estimation Conditional risk Parameter estimation Conditional risk Formalizing the problem Specify random variables we care about e.g., Commute Time e.g., Heights of buildings in a city We might then pick a particular distribution

More information

CPSC 540: Machine Learning

CPSC 540: Machine Learning CPSC 540: Machine Learning Expectation Maximization Mark Schmidt University of British Columbia Winter 2018 Last Time: Learning with MAR Values We discussed learning with missing at random values in data:

More information

IEOR165 Discussion Week 5

IEOR165 Discussion Week 5 IEOR165 Discussion Week 5 Sheng Liu University of California, Berkeley Feb 19, 2016 Outline 1 1st Homework 2 Revisit Maximum A Posterior 3 Regularization IEOR165 Discussion Sheng Liu 2 About 1st Homework

More information

Bayesian Inference. Chapter 4: Regression and Hierarchical Models

Bayesian Inference. Chapter 4: Regression and Hierarchical Models Bayesian Inference Chapter 4: Regression and Hierarchical Models Conchi Ausín and Mike Wiper Department of Statistics Universidad Carlos III de Madrid Master in Business Administration and Quantitative

More information

Stratégies bayésiennes et fréquentistes dans un modèle de bandit

Stratégies bayésiennes et fréquentistes dans un modèle de bandit Stratégies bayésiennes et fréquentistes dans un modèle de bandit thèse effectuée à Telecom ParisTech, co-dirigée par Olivier Cappé, Aurélien Garivier et Rémi Munos Journées MAS, Grenoble, 30 août 2016

More information

An Estimation Based Allocation Rule with Super-linear Regret and Finite Lock-on Time for Time-dependent Multi-armed Bandit Processes

An Estimation Based Allocation Rule with Super-linear Regret and Finite Lock-on Time for Time-dependent Multi-armed Bandit Processes An Estimation Based Allocation Rule with Super-linear Regret and Finite Lock-on Time for Time-dependent Multi-armed Bandit Processes Prokopis C. Prokopiou, Peter E. Caines, and Aditya Mahajan McGill University

More information

STAT 830 Bayesian Estimation

STAT 830 Bayesian Estimation STAT 830 Bayesian Estimation Richard Lockhart Simon Fraser University STAT 830 Fall 2011 Richard Lockhart (Simon Fraser University) STAT 830 Bayesian Estimation STAT 830 Fall 2011 1 / 23 Purposes of These

More information

Theory of Statistics.

Theory of Statistics. Theory of Statistics. Homework V February 5, 00. MT 8.7.c When σ is known, ˆµ = X is an unbiased estimator for µ. If you can show that its variance attains the Cramer-Rao lower bound, then no other unbiased

More information

Lecture 25: Review. Statistics 104. April 23, Colin Rundel

Lecture 25: Review. Statistics 104. April 23, Colin Rundel Lecture 25: Review Statistics 104 Colin Rundel April 23, 2012 Joint CDF F (x, y) = P [X x, Y y] = P [(X, Y ) lies south-west of the point (x, y)] Y (x,y) X Statistics 104 (Colin Rundel) Lecture 25 April

More information

Bayesian Networks Basic and simple graphs

Bayesian Networks Basic and simple graphs Bayesian Networks Basic and simple graphs Ullrika Sahlin, Centre of Environmental and Climate Research Lund University, Sweden Ullrika.Sahlin@cec.lu.se http://www.cec.lu.se/ullrika-sahlin Bayesian [Belief]

More information

Latent Variable Models

Latent Variable Models Latent Variable Models Stefano Ermon, Aditya Grover Stanford University Lecture 5 Stefano Ermon, Aditya Grover (AI Lab) Deep Generative Models Lecture 5 1 / 31 Recap of last lecture 1 Autoregressive models:

More information

Information geometry for bivariate distribution control

Information geometry for bivariate distribution control Information geometry for bivariate distribution control C.T.J.Dodson + Hong Wang Mathematics + Control Systems Centre, University of Manchester Institute of Science and Technology Optimal control of stochastic

More information

2 Statistical Estimation: Basic Concepts

2 Statistical Estimation: Basic Concepts Technion Israel Institute of Technology, Department of Electrical Engineering Estimation and Identification in Dynamical Systems (048825) Lecture Notes, Fall 2009, Prof. N. Shimkin 2 Statistical Estimation:

More information

Estimation, Inference, and Hypothesis Testing

Estimation, Inference, and Hypothesis Testing Chapter 2 Estimation, Inference, and Hypothesis Testing Note: The primary reference for these notes is Ch. 7 and 8 of Casella & Berger 2. This text may be challenging if new to this topic and Ch. 7 of

More information

STATISTICS/ECONOMETRICS PREP COURSE PROF. MASSIMO GUIDOLIN

STATISTICS/ECONOMETRICS PREP COURSE PROF. MASSIMO GUIDOLIN Massimo Guidolin Massimo.Guidolin@unibocconi.it Dept. of Finance STATISTICS/ECONOMETRICS PREP COURSE PROF. MASSIMO GUIDOLIN SECOND PART, LECTURE 2: MODES OF CONVERGENCE AND POINT ESTIMATION Lecture 2:

More information

Parametric Inference Maximum Likelihood Inference Exponential Families Expectation Maximization (EM) Bayesian Inference Statistical Decison Theory

Parametric Inference Maximum Likelihood Inference Exponential Families Expectation Maximization (EM) Bayesian Inference Statistical Decison Theory Statistical Inference Parametric Inference Maximum Likelihood Inference Exponential Families Expectation Maximization (EM) Bayesian Inference Statistical Decison Theory IP, José Bioucas Dias, IST, 2007

More information

Non-Parametric Bayes

Non-Parametric Bayes Non-Parametric Bayes Mark Schmidt UBC Machine Learning Reading Group January 2016 Current Hot Topics in Machine Learning Bayesian learning includes: Gaussian processes. Approximate inference. Bayesian

More information

Exercises and Answers to Chapter 1

Exercises and Answers to Chapter 1 Exercises and Answers to Chapter The continuous type of random variable X has the following density function: a x, if < x < a, f (x), otherwise. Answer the following questions. () Find a. () Obtain mean

More information

A Very Brief Summary of Statistical Inference, and Examples

A Very Brief Summary of Statistical Inference, and Examples A Very Brief Summary of Statistical Inference, and Examples Trinity Term 2008 Prof. Gesine Reinert 1 Data x = x 1, x 2,..., x n, realisations of random variables X 1, X 2,..., X n with distribution (model)

More information

Module 22: Bayesian Methods Lecture 9 A: Default prior selection

Module 22: Bayesian Methods Lecture 9 A: Default prior selection Module 22: Bayesian Methods Lecture 9 A: Default prior selection Peter Hoff Departments of Statistics and Biostatistics University of Washington Outline Jeffreys prior Unit information priors Empirical

More information

Distributed Estimation, Information Loss and Exponential Families. Qiang Liu Department of Computer Science Dartmouth College

Distributed Estimation, Information Loss and Exponential Families. Qiang Liu Department of Computer Science Dartmouth College Distributed Estimation, Information Loss and Exponential Families Qiang Liu Department of Computer Science Dartmouth College Statistical Learning / Estimation Learning generative models from data Topic

More information

IEOR E4570: Machine Learning for OR&FE Spring 2015 c 2015 by Martin Haugh. The EM Algorithm

IEOR E4570: Machine Learning for OR&FE Spring 2015 c 2015 by Martin Haugh. The EM Algorithm IEOR E4570: Machine Learning for OR&FE Spring 205 c 205 by Martin Haugh The EM Algorithm The EM algorithm is used for obtaining maximum likelihood estimates of parameters when some of the data is missing.

More information

Introduction to Bayesian Methods

Introduction to Bayesian Methods Introduction to Bayesian Methods Jessi Cisewski Department of Statistics Yale University Sagan Summer Workshop 2016 Our goal: introduction to Bayesian methods Likelihoods Priors: conjugate priors, non-informative

More information

Introduction to Machine Learning. Maximum Likelihood and Bayesian Inference. Lecturers: Eran Halperin, Yishay Mansour, Lior Wolf

Introduction to Machine Learning. Maximum Likelihood and Bayesian Inference. Lecturers: Eran Halperin, Yishay Mansour, Lior Wolf 1 Introduction to Machine Learning Maximum Likelihood and Bayesian Inference Lecturers: Eran Halperin, Yishay Mansour, Lior Wolf 2013-14 We know that X ~ B(n,p), but we do not know p. We get a random sample

More information

Principles of Statistics

Principles of Statistics Part II Year 2018 2017 2016 2015 2014 2013 2012 2011 2010 2009 2008 2007 2006 2005 2018 81 Paper 4, Section II 28K Let g : R R be an unknown function, twice continuously differentiable with g (x) M for

More information

7. Estimation and hypothesis testing. Objective. Recommended reading

7. Estimation and hypothesis testing. Objective. Recommended reading 7. Estimation and hypothesis testing Objective In this chapter, we show how the election of estimators can be represented as a decision problem. Secondly, we consider the problem of hypothesis testing

More information

Brief Review on Estimation Theory

Brief Review on Estimation Theory Brief Review on Estimation Theory K. Abed-Meraim ENST PARIS, Signal and Image Processing Dept. abed@tsi.enst.fr This presentation is essentially based on the course BASTA by E. Moulines Brief review on

More information

Online Question Asking Algorithms For Measuring Skill

Online Question Asking Algorithms For Measuring Skill Online Question Asking Algorithms For Measuring Skill Jack Stahl December 4, 2007 Abstract We wish to discover the best way to design an online algorithm for measuring hidden qualities. In particular,

More information

Parametric Models. Dr. Shuang LIANG. School of Software Engineering TongJi University Fall, 2012

Parametric Models. Dr. Shuang LIANG. School of Software Engineering TongJi University Fall, 2012 Parametric Models Dr. Shuang LIANG School of Software Engineering TongJi University Fall, 2012 Today s Topics Maximum Likelihood Estimation Bayesian Density Estimation Today s Topics Maximum Likelihood

More information