GLM, insurance pricing & big data: paying attention to convergence issues.


 Aleesha Goodwin
 3 years ago
 Views:
Transcription
1 GLM, insurance pricing & big data: paying attention to convergence issues. Michaël NOACK  Senior consultant & Manager of ADDACTIS Pricing Copyright 2014 ADDACTIS Worldwide. All Rights Reserved
2 INTRODUCTION The GLM model tries to find and express the relationship between a random variable Y (response variable) and a set of predictor variables: X 1,,Xp. In the pricing process GLM is market standard and it is used to explain response variables Y like the number of claims (frequency), the average cost of a claim, the cost of the risk, the propensity of large claims. The distribution of the response variable Y must belong to the exponential family. Let μ be the mean of Y, the model can be written as: * Equivalence satisfied under certain conditions for the function g. To find a solution means to find a maximum of the loglikelihood (MLE): Generally the solution to this equation must be calculated by iterative methods. Iterative solutions to nonlinear equations follow this algorithm: 1. A start value is selected (initial guess for β) 2. Using a polynomial approximation of the likelihood, a second guess is obtained 3. The difference, C, between guess i and i + 1 is calculated C= β (i+1) β (i) 4. Once the difference C < k, where k = convergence criterion (say ) then the estimate β (i+1) =β Note: when β is a vector, the difference β (i+1) β (i) yields a vector of c i s where c i is the convergence criterion for the i th element of β. Convergence could be reached when all ci < k or when the ci < k. But iteration doesn t converge in all cases. What to do when there is no convergence? To have a robust algorithm, an algorithm that converges in almost every situation  seems to be something very positive, even if it requires more explanations. To evaluate what are the really important properties of the GLMalgorithm, we will show some more details about GLM (chapter 1 and 2) and explain convergence issues and how our solution ADDACTIS Pricing handles these situations (chapter 3).
3 1MAIN METHODS In general, there are two popular iterative methods for estimating the parameters of a nonlinear equations. g NewtonRaphson Method g Fisher s Scoring Method (or Iteratively Reweighted Least Squares Algorithm) Both take on the same general form and differ only in the variance structure. The NewtonRaphson method uses the Wald test (nonnull standard error) and the Fisher s scoring method uses the Score test (null standard error). These algorithms find (iteratively) a point x where f(x)=0 for any f functions that possess the appropriate conditions. The iterative solution can be written as: One of the most common methods is the Newton Raphson method and this is based on successive approximations to the solution, using Taylor s theorem to approximate the equation. Copyright 2014 ADDACTIS Worldwide. All Rights Reserved
4 Using matrices, the NewtonRaphson algorithm can then be written as follows: Where: * β is the vector (of size p) containing the parameters to estimate, * S is the gradient of the (log)likelihood computed at the point β (t), * H the Hessian matrix of the (log)likelihood computed at the point β (t). H has the form H=(X T VX) where V is a diagonal matrix (n, n). Fisher s Scoring Method is identically to NewtonRaphson, except that in place of the Hessian matrix (observed information matrix) the expectation of the Hessian matrix is used (expected information matrix). Generally NewtonRaphson converges faster, but is more sensitive to the starting point. In same situations Hessian matrix cannot be negative defined when we are not close enough to the final estimator. The Fisher scoring method is less dependent on individual Y i values and provides more stable convergence. But the calculation of the expected information matrix is not always computationally feasible.
5 2ADDITIONAL PARAMETERS It has been proved that in case of canonical link function there is no difference between both methods. So in the most decisive case in the insurance sector  the frequency model with a Poisson Error distribution and a log link function  there is no difference between both methods. Once selected the method to apply to solve the GLM calculation, there are more parameters that have to be defined for the iteration process. The solution and the execution time also depend on: g Selection of the starting point An adequate selection of starting points can avoid convergence problems and can reduce the number of iteration steps. g Convergence criterion As we have seen before a convergence criterion can be based on the individual difference for the estimates between two iteration steps or on the difference in the error sum. In both cases the user can get quite different results. If the problem converges by the individual criterion it will also converge by the criterion on the aggregated difference. But it is possible to obtain convergence by the aggregated criterion but non convergence by the individual one. In which cases can this occur? If the overall error is stable and the individual is not, there must be at least two estimates with (compensated) fluctuations. From the ADDACTIS Pricing point of view this is an unstable solution the user should not accept without further analysis. Normally the affected estimates can be identified by a large confidence interval and a low exposure. Copyright 2014 ADDACTIS Worldwide. All Rights Reserved
6 g Handling of special situations In most cases we get a convergence and the result doesn t depend on the selected method and the parameters. But in some special cases we have some more conflictive situations like: o Matrix no invertible o Unobserved Modalities main factor o Unobserved Modalities marginal interaction o Non convergence o Max is really maximum In these cases it is especially important that the user gets all information about the iteration process to make the correct decision.
7 3ADDACTIS Pricing In this section we will show all details about the method integrated in ADDACTIS Pricing, explain and demonstrate with an example, why it matters to give the full information on calculations to the user. 3.1 The method Our software works with the NewtonRaphson method. It is a fast converging method to solve the problem. Possible nonconvergence in most cases will be avoided by the selection of the starting points. Documented examples about nonconvergence are from biostatistics studies and due to the big impact of single observations for small sample size. However for insurance data this shouldn t be a problem. 3.2 Starting points ADDACTIS Pricing takes as a starting point the ordinary least squares estimator: In the improbable case of nonconvergence the user has the option to start with the Weighted Least Squares (which is theoretically closer to a maximum). If both methods don t converge, that means nothing else that neither the ordinary least squares estimator, nor the weighted least squares estimator are close to the maximum. In such a case we would not recommend to consider a different method that could converge (are we really interested in such a solution?), but to change the design matrix (include/exclude parameters or change mapping of parameters). Copyright 2014 ADDACTIS Worldwide. All Rights Reserved
8 3.3 Convergence criterion The convergence criterion is based on the difference between β (t+1) and β (t) : As soon as the maximum of these values is lower than the target accuracy defined by the user (104 by default), ADDACTIS Pricing stops, and the algorithm has converged: if it converges, it is fast; generally in 5 steps a solution has been found. Other software bases its convergence criterion on the sum of errors (Deviance). This criterion normally converge faster, but in some situations of nearly colinearity between to parameters a and b, we can find situations where the pairs (a,b) and (a/2, b*2) etc. give very similar results and the sum of errors converge, but at individual level there is an unstable situation with nonconvergence. In that case we also suggest that it is better to change the design matrix than to accept convergence based on the sum of errors.
9 3.4 Handling of special situations In special situation ADDACTIS Pricing always gives as much information as possible to help the user to find a solution. g Matrix no invertible (Colinearities detected) The matrix is not of full range. Each matrix has a unique (Row)Reduced Echelon form. This matrix form can be obtained by the GaussianElimination method (due to the uniqueness of the reduced echelon form, every method produced the same results). ADDACTIS Pricing executes the matrix reduction by this method and calculates the dependencies between the parameters. With this information the user can see exactly which factors are the sources of the problem. g Unobserved Modalities main factor If there are unobserved modalities ADDACTIS Pricing doesn t start the iteration process and shows the user which modalities have no observation. It is not compulsory to have observations for each modality; we could execute the GLM and just ignore these modalities (like other applications do). In these situations the unobserved modalities have no rate (or rate equal 1, like the reference value). That means the rate depends on the selection of the reference value and the user will know about it. This is why ADDACTIS Pricing is making the user aware of the situation and helps him make a decision joining these modalities with the adequate ones. Copyright 2014 ADDACTIS Worldwide. All Rights Reserved
10 g Unobserved Modalities marginal interaction For a main factor it s very uncommon to have unobserved modalities, but in case of marginal interactions it is quite frequent. We will illustrate with an example the difference. Let s take some fictive policy and claim data. The variables of interest are age and vehicle. The oneway analysis shows us an expected behavior:
11 In our case there are no observations for the combination age x vehicle for the group for [20:22[ x M. (Maybe due to subscription rules). This can be observed in the twoway analysis: When we now include both variables with a marginal interaction ADDACTIS Pricing doesn t converge. Depending on the selected reference value for vehicle ADDACTIS Pricing delivers the message: unobserved modalities or collinearities detected. The user has consequently to make a decision on how to regroup the age variable. Once done the new model will converge without problem. But what impact could have this distinct handling in practice? Copyright 2014 ADDACTIS Worldwide. All Rights Reserved
12 A standard software package like SAS gives no advice about unobserved modalities. You get the parameter list for the frequency calculation like: Notice that the line age*vehicle B.[20,22[ M is omitted and the reference value is changed to L. The user can calculate the best frequencyestimation for all elements in this critical segment:
13 In ADDACTIS Pricing the user was forced to regroup the age variable, for instance like A.[18,21[ and B.[21,24[. The best frequencyestimation in this situation gives: For the age = 20 and vehicle = M the SAS premium would be 1/3 of ADDACTIS Pricing ; for the age = 21 aprox. ½. This example shows the impact of forced convergence. We prefer not to force convergence in ADDACTIS Pricing and let the user in the driver s seat to solve the convergence issue if any. Copyright 2014 ADDACTIS Worldwide. All Rights Reserved
14 SUMMARY Convergence of the model is a decisive issue when using GLM models that are based on iterative methods. In most cases, with the selection of adequate starting points and enough data, GLM models do converge. But it is not always the case. ADDACTIS Pricing assumes that in the case where NewtonRaphson doesn t converge, the GLM model might be incorrectly specified. In which case, some modifications in the design matrix (parameter selection and/or parameter grouping) will help achieve convergence. But in order to make a valid and documented decision, the user has as many and complete informations as possible on calculations. Consequently convergence should not be artificially forced by the GLM methods, as exist in some software and nonconvergence is an information of utmost importance for the user. It is the primary condition to evaluate the correctness of the solution. Moreover this transparency of calculations and information is in tune with the requirements of control over calculations at the heart of Solvency Boulevard de la Madeleine F PARIS +33 (0) Worldwide actuarial software. European expertise. Local solutions.
STATISTICA Formula Guide: Logistic Regression. Table of Contents
: Table of Contents... 1 Overview of Model... 1 Dispersion... 2 Parameterization... 3 SigmaRestricted Model... 3 Overparameterized Model... 4 Reference Coding... 4 Model Summary (Summary Tab)... 5 Summary
More informationGeneralized Linear Models. Today: definition of GLM, maximum likelihood estimation. Involves choice of a link function (systematic component)
Generalized Linear Models Last time: definition of exponential family, derivation of mean and variance (memorize) Today: definition of GLM, maximum likelihood estimation Include predictors x i through
More informationNumerical methods for finding the roots of a function
Numerical methods for finding the roots of a function The roots of a function f (x) are defined as the values for which the value of the function becomes equal to zero. So, finding the roots of f (x) means
More informationPower System Analysis Prof. A. K. Sinha Department of Electrical Engineering Indian Institute of Technology, Kharagpur. Lecture  19 Power Flow IV
Power System Analysis Prof. A. K. Sinha Department of Electrical Engineering Indian Institute of Technology, Kharagpur Lecture  19 Power Flow IV Welcome to lesson 19 on Power System Analysis. In this
More informationLecture 3: Linear methods for classification
Lecture 3: Linear methods for classification Rafael A. Irizarry and Hector Corrada Bravo February, 2010 Today we describe four specific algorithms useful for classification problems: linear regression,
More informationLogistic Regression (1/24/13)
STA63/CBB540: Statistical methods in computational biology Logistic Regression (/24/3) Lecturer: Barbara Engelhardt Scribe: Dinesh Manandhar Introduction Logistic regression is model for regression used
More information(Quasi)Newton methods
(Quasi)Newton methods 1 Introduction 1.1 Newton method Newton method is a method to find the zeros of a differentiable nonlinear function g, x such that g(x) = 0, where g : R n R n. Given a starting
More informationExample: Credit card default, we may be more interested in predicting the probabilty of a default than classifying individuals as default or not.
Statistical Learning: Chapter 4 Classification 4.1 Introduction Supervised learning with a categorical (Qualitative) response Notation:  Feature vector X,  qualitative response Y, taking values in C
More informationLinear Threshold Units
Linear Threshold Units w x hx (... w n x n w We assume that each feature x j and each weight w j is a real number (we will relax this later) We will study three different algorithms for learning linear
More informationi=1 In practice, the natural logarithm of the likelihood function, called the loglikelihood function and denoted by
Statistics 580 Maximum Likelihood Estimation Introduction Let y (y 1, y 2,..., y n be a vector of iid, random variables from one of a family of distributions on R n and indexed by a pdimensional parameter
More informationSTA 4273H: Statistical Machine Learning
STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.cs.toronto.edu/~rsalakhu/ Lecture 6 Three Approaches to Classification Construct
More information18 Generalised Linear Models
18 Generalised Linear Models Generalised linear models (GLM) is a generalisation of ordinary least squares regression. See also Davison, Section 10.110.4, Green (1984) and Dobson and Barnett (2008). To
More informationLinear Classification. Volker Tresp Summer 2015
Linear Classification Volker Tresp Summer 2015 1 Classification Classification is the central task of pattern recognition Sensors supply information about an object: to which class do the object belong
More informationRoots of Equations (Chapters 5 and 6)
Roots of Equations (Chapters 5 and 6) Problem: given f() = 0, find. In general, f() can be any function. For some forms of f(), analytical solutions are available. However, for other functions, we have
More informationPoisson Models for Count Data
Chapter 4 Poisson Models for Count Data In this chapter we study loglinear models for count data under the assumption of a Poisson error structure. These models have many applications, not only to the
More informationLecture 14: GLM Estimation and Logistic Regression
Lecture 14: GLM Estimation and Logistic Regression Dipankar Bandyopadhyay, Ph.D. BMTRY 711: Analysis of Categorical Data Spring 2011 Division of Biostatistics and Epidemiology Medical University of South
More informationPa8ern Recogni6on. and Machine Learning. Chapter 4: Linear Models for Classiﬁca6on
Pa8ern Recogni6on and Machine Learning Chapter 4: Linear Models for Classiﬁca6on Represen'ng the target values for classifica'on If there are only two classes, we typically use a single real valued output
More information(Refer Slide Time: 00:00:56 min)
Numerical Methods and Computation Prof. S.R.K. Iyengar Department of Mathematics Indian Institute of Technology, Delhi Lecture No # 3 Solution of Nonlinear Algebraic Equations (Continued) (Refer Slide
More informationOverview of Violations of the Basic Assumptions in the Classical Normal Linear Regression Model
Overview of Violations of the Basic Assumptions in the Classical Normal Linear Regression Model 1 September 004 A. Introduction and assumptions The classical normal linear regression model can be written
More informationTime Domain and Frequency Domain Techniques For Multi Shaker Time Waveform Replication
Time Domain and Frequency Domain Techniques For Multi Shaker Time Waveform Replication Thomas Reilly Data Physics Corporation 1741 Technology Drive, Suite 260 San Jose, CA 95110 (408) 2168440 This paper
More informationLOGISTIC REGRESSION. Nitin R Patel. where the dependent variable, y, is binary (for convenience we often code these values as
LOGISTIC REGRESSION Nitin R Patel Logistic regression extends the ideas of multiple linear regression to the situation where the dependent variable, y, is binary (for convenience we often code these values
More informationStatistical Machine Learning
Statistical Machine Learning UoC Stats 37700, Winter quarter Lecture 4: classical linear and quadratic discriminants. 1 / 25 Linear separation For two classes in R d : simple idea: separate the classes
More informationStatistics in Retail Finance. Chapter 2: Statistical models of default
Statistics in Retail Finance 1 Overview > We consider how to build statistical models of default, or delinquency, and how such models are traditionally used for credit application scoring and decision
More informationChapter 13 Introduction to Nonlinear Regression( 非 線 性 迴 歸 )
Chapter 13 Introduction to Nonlinear Regression( 非 線 性 迴 歸 ) and Neural Networks( 類 神 經 網 路 ) 許 湘 伶 Applied Linear Regression Models (Kutner, Nachtsheim, Neter, Li) hsuhl (NUK) LR Chap 10 1 / 35 13 Examples
More informationLogistic Regression. Jia Li. Department of Statistics The Pennsylvania State University. Logistic Regression
Logistic Regression Department of Statistics The Pennsylvania State University Email: jiali@stat.psu.edu Logistic Regression Preserve linear classification boundaries. By the Bayes rule: Ĝ(x) = arg max
More informationLocal classification and local likelihoods
Local classification and local likelihoods November 18 knearest neighbors The idea of local regression can be extended to classification as well The simplest way of doing so is called nearest neighbor
More informationSAS Software to Fit the Generalized Linear Model
SAS Software to Fit the Generalized Linear Model Gordon Johnston, SAS Institute Inc., Cary, NC Abstract In recent years, the class of generalized linear models has gained popularity as a statistical modeling
More informationLinear Dependence Tests
Linear Dependence Tests The book omits a few key tests for checking the linear dependence of vectors. These short notes discuss these tests, as well as the reasoning behind them. Our first test checks
More informationPattern Analysis. Logistic Regression. 12. Mai 2009. Joachim Hornegger. Chair of Pattern Recognition Erlangen University
Pattern Analysis Logistic Regression 12. Mai 2009 Joachim Hornegger Chair of Pattern Recognition Erlangen University Pattern Analysis 2 / 43 1 Logistic Regression Posteriors and the Logistic Function Decision
More informationAuxiliary Variables in Mixture Modeling: 3Step Approaches Using Mplus
Auxiliary Variables in Mixture Modeling: 3Step Approaches Using Mplus Tihomir Asparouhov and Bengt Muthén Mplus Web Notes: No. 15 Version 8, August 5, 2014 1 Abstract This paper discusses alternatives
More informationProbabilistic Linear Classification: Logistic Regression. Piyush Rai IIT Kanpur
Probabilistic Linear Classification: Logistic Regression Piyush Rai IIT Kanpur Probabilistic Machine Learning (CS772A) Jan 18, 2016 Probabilistic Machine Learning (CS772A) Probabilistic Linear Classification:
More informationNONLIFE INSURANCE PRICING USING THE GENERALIZED ADDITIVE MODEL, SMOOTHING SPLINES AND LCURVES
NONLIFE INSURANCE PRICING USING THE GENERALIZED ADDITIVE MODEL, SMOOTHING SPLINES AND LCURVES Kivan Kaivanipour A thesis submitted for the degree of Master of Science in Engineering Physics Department
More informationGeneralized Linear Models
Generalized Linear Models We have previously worked with regression models where the response variable is quantitative and normally distributed. Now we turn our attention to two types of models where the
More informationThe Gravity Model: Derivation and Calibration
The Gravity Model: Derivation and Calibration Philip A. Viton October 28, 2014 Philip A. Viton CRP/CE 5700 () Gravity Model October 28, 2014 1 / 66 Introduction We turn now to the Gravity Model of trip
More informationPATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 4: LINEAR MODELS FOR CLASSIFICATION
PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 4: LINEAR MODELS FOR CLASSIFICATION Introduction In the previous chapter, we explored a class of regression models having particularly simple analytical
More informationMexican Volatility Index
Mexican Volatility Index Definition of VIMEX The VIMEX is an index that measures the short term (90 days calendar) expected volatility for the Mexican stock market through the IPC Futures Options listed
More informationMultivariate Logistic Regression
1 Multivariate Logistic Regression As in univariate logistic regression, let π(x) represent the probability of an event that depends on p covariates or independent variables. Then, using an inv.logit formulation
More informationIntroduction to Logistic Regression
OpenStaxCNX module: m42090 1 Introduction to Logistic Regression Dan Calderon This work is produced by OpenStaxCNX and licensed under the Creative Commons Attribution License 3.0 Abstract Gives introduction
More informationSolving nonlinear equations in one variable
Chapter Solving nonlinear equations in one variable Contents.1 Bisection method............................. 7. Fixed point iteration........................... 8.3 NewtonRaphson method........................
More informationU.C. Berkeley CS276: Cryptography Handout 0.1 Luca Trevisan January, 2009. Notes on Algebra
U.C. Berkeley CS276: Cryptography Handout 0.1 Luca Trevisan January, 2009 Notes on Algebra These notes contain as little theory as possible, and most results are stated without proof. Any introductory
More informationG.A. Pavliotis. Department of Mathematics. Imperial College London
EE1 MATHEMATICS NUMERICAL METHODS G.A. Pavliotis Department of Mathematics Imperial College London 1. Numerical solution of nonlinear equations (iterative processes). 2. Numerical evaluation of integrals.
More informationTRANSACTIONAL DATA MINING AT LLOYDS BANKING GROUP
TRANSACTIONAL DATA MINING AT LLOYDS BANKING GROUP Csaba Főző csaba.fozo@lloydsbanking.com 15 October 2015 CONTENTS Introduction 04 Random Forest Methodology 06 Transactional Data Mining Project 17 Conclusions
More informationEconometric Analysis of Cross Section and Panel Data Second Edition. Jeffrey M. Wooldridge. The MIT Press Cambridge, Massachusetts London, England
Econometric Analysis of Cross Section and Panel Data Second Edition Jeffrey M. Wooldridge The MIT Press Cambridge, Massachusetts London, England Preface Acknowledgments xxi xxix I INTRODUCTION AND BACKGROUND
More informationPrinciple Component Analysis and Partial Least Squares: Two Dimension Reduction Techniques for Regression
Principle Component Analysis and Partial Least Squares: Two Dimension Reduction Techniques for Regression Saikat Maitra and Jun Yan Abstract: Dimension reduction is one of the major tasks for multivariate
More informationLecture 8 February 4
ICS273A: Machine Learning Winter 2008 Lecture 8 February 4 Scribe: Carlos Agell (Student) Lecturer: Deva Ramanan 8.1 Neural Nets 8.1.1 Logistic Regression Recall the logistic function: g(x) = 1 1 + e θt
More informationNewton s method and high order iterations
Newton s method and high order iterations Pascal Sebah and Xavier Gourdon numbers.computation.free.fr/constants/constants.html October, 001 Abstract An introduction to the famous method introduced by Newton
More informationStatistics in Retail Finance. Chapter 6: Behavioural models
Statistics in Retail Finance 1 Overview > So far we have focussed mainly on application scorecards. In this chapter we shall look at behavioural models. We shall cover the following topics: Behavioural
More informationLecture Notes to Accompany. Scientific Computing An Introductory Survey. by Michael T. Heath. Chapter 10
Lecture Notes to Accompany Scientific Computing An Introductory Survey Second Edition by Michael T. Heath Chapter 10 Boundary Value Problems for Ordinary Differential Equations Copyright c 2001. Reproduction
More informationMATHEMATICAL METHODS FOURIER SERIES
MATHEMATICAL METHODS FOURIER SERIES I YEAR B.Tech By Mr. Y. Prabhaker Reddy Asst. Professor of Mathematics Guru Nanak Engineering College Ibrahimpatnam, Hyderabad. SYLLABUS OF MATHEMATICAL METHODS (as
More informationAn extension of the factoring likelihood approach for nonmonotone missing data
An extension of the factoring likelihood approach for nonmonotone missing data Jae Kwang Kim Dong Wan Shin January 14, 2010 ABSTRACT We address the problem of parameter estimation in multivariate distributions
More informationPlease follow the directions once you locate the Stata software in your computer. Room 114 (Business Lab) has computers with Stata software
STATA Tutorial Professor Erdinç Please follow the directions once you locate the Stata software in your computer. Room 114 (Business Lab) has computers with Stata software 1.Wald Test Wald Test is used
More informationOrdinary Least Squares and Poisson Regression Models by Luc Anselin University of Illinois ChampaignUrbana, IL
Appendix C Ordinary Least Squares and Poisson Regression Models by Luc Anselin University of Illinois ChampaignUrbana, IL This note provides a brief description of the statistical background, estimators
More informationService courses for graduate students in degree programs other than the MS or PhD programs in Biostatistics.
Course Catalog In order to be assured that all prerequisites are met, students must acquire a permission number from the education coordinator prior to enrolling in any Biostatistics course. Courses are
More informationCSCI567 Machine Learning (Fall 2014)
CSCI567 Machine Learning (Fall 2014) Drs. Sha & Liu {feisha,yanliu.cs}@usc.edu September 22, 2014 Drs. Sha & Liu ({feisha,yanliu.cs}@usc.edu) CSCI567 Machine Learning (Fall 2014) September 22, 2014 1 /
More informationActuarial. Modeling Seminar Part 2. Matthew Morton FSA, MAAA Ben Williams
Actuarial Data Analytics / Predictive Modeling Seminar Part 2 Matthew Morton FSA, MAAA Ben Williams Agenda Introduction Overview of Seminar Traditional Experience Study Traditional vs. Predictive Modeling
More informationLinear and Piecewise Linear Regressions
Tarigan Statistical Consulting & Coaching statisticalcoaching.ch Doctoral Program in Computer Science of the Universities of Fribourg, Geneva, Lausanne, Neuchâtel, Bern and the EPFL Handson Data Analysis
More informationUSERV Auto Insurance Rule Model in Corticon
USERV Auto Insurance Rule Model in Corticon Mike Parish Progress Software Contents Introduction... 3 Vocabulary... 4 Database Connectivity... 4 Overall Structure of the Decision... 6 Preferred Clients...
More informationLas Vegas and Monte Carlo Randomized Algorithms for Systems and Control
Las Vegas and Monte Carlo Randomized Algorithms for Systems and Control Roberto Tempo IEIITCNR Politecnico di Torino roberto.tempo@polito.it BasarFest,, Urbana RT 2006 1 CSL UIUC Six months at CSL in
More informationMonte Carlo testing with Big Data
Monte Carlo testing with Big Data Patrick RubinDelanchy University of Bristol & Heilbronn Institute for Mathematical Research Joint work with: Axel Gandy (Imperial College London) with contributions from:
More informationScientific Computing: An Introductory Survey
Scientific Computing: An Introductory Survey Chapter 10 Boundary Value Problems for Ordinary Differential Equations Prof. Michael T. Heath Department of Computer Science University of Illinois at UrbanaChampaign
More information11. Analysis of Casecontrol Studies Logistic Regression
Research methods II 113 11. Analysis of Casecontrol Studies Logistic Regression This chapter builds upon and further develops the concepts and strategies described in Ch.6 of Mother and Child Health:
More information(57) (58) (59) (60) (61)
Module 4 : Solving Linear Algebraic Equations Section 5 : Iterative Solution Techniques 5 Iterative Solution Techniques By this approach, we start with some initial guess solution, say for solution and
More informationFactor analysis. Angela Montanari
Factor analysis Angela Montanari 1 Introduction Factor analysis is a statistical model that allows to explain the correlations between a large number of observed correlated variables through a small number
More informationECLT5810 ECommerce Data Mining Technique SAS Enterprise Miner  Regression Model I. Regression Node
Enterprise Miner  Regression 1 ECLT5810 ECommerce Data Mining Technique SAS Enterprise Miner  Regression Model I. Regression Node 1. Some background: Linear attempts to predict the value of a continuous
More informationMISSING DATA TECHNIQUES WITH SAS. IDRE Statistical Consulting Group
MISSING DATA TECHNIQUES WITH SAS IDRE Statistical Consulting Group ROAD MAP FOR TODAY To discuss: 1. Commonly used techniques for handling missing data, focusing on multiple imputation 2. Issues that could
More informationIntroduction to Generalized Linear Models
to Generalized Linear Models Heather Turner ESRC National Centre for Research Methods, UK and Department of Statistics University of Warwick, UK WU, 2008 04 2224 Copyright c Heather Turner, 2008 to Generalized
More informationANNUITY LAPSE RATE MODELING: TOBIT OR NOT TOBIT? 1. INTRODUCTION
ANNUITY LAPSE RATE MODELING: TOBIT OR NOT TOBIT? SAMUEL H. COX AND YIJIA LIN ABSTRACT. We devise an approach, using tobit models for modeling annuity lapse rates. The approach is based on data provided
More informationJava Modules for Time Series Analysis
Java Modules for Time Series Analysis Agenda Clustering Nonnormal distributions Multifactor modeling Implied ratings Time series prediction 1. Clustering + Cluster 1 Synthetic Clustering + Time series
More informationInstitute of Actuaries of India Subject CT3 Probability and Mathematical Statistics
Institute of Actuaries of India Subject CT3 Probability and Mathematical Statistics For 2015 Examinations Aim The aim of the Probability and Mathematical Statistics subject is to provide a grounding in
More information7.4 MÜLLER S METHOD. f(x 0 ) = a(x 0 x 2 ) 2 + b(x 0 x 2 ) + c (7.18)
7.4 MÜLLER S METHOD 181 When complex roots are possible, the bracketing methods cannot be used because of the obvious problem that the criterion for defining a bracket (that is, sign change) does not translate
More information7 Generalized Estimating Equations
Chapter 7 The procedure extends the generalized linear model to allow for analysis of repeated measurements or other correlated observations, such as clustered data. Example. Public health of cials can
More informationParameter Estimation: A Deterministic Approach using the LevenburgMarquardt Algorithm
Parameter Estimation: A Deterministic Approach using the LevenburgMarquardt Algorithm John Bardsley Department of Mathematical Sciences University of Montana Applied Math SeminarFeb. 2005 p.1/14 Outline
More informationDevelopment Period 1 2 3 4 5 6 7 8 9 Observed Payments
Pricing and reserving in the general insurance industry Solutions developed in The SAS System John Hansen & Christian Larsen, Larsen & Partners Ltd 1. Introduction The two business solutions presented
More informationOn Small Sample Properties of Permutation Tests: A Significance Test for Regression Models
On Small Sample Properties of Permutation Tests: A Significance Test for Regression Models Hisashi Tanizaki Graduate School of Economics Kobe University (tanizaki@kobeu.ac.p) ABSTRACT In this paper we
More informationTHE TINSPIRE PROGRAMS
THE TINSPIRE PROGRAMS JAMES KEESLING The purpose of this document is to list and document the programs that will be used in this class. For each program there is a screen shot containing an example and
More informationA Coefficient of Variation for Skewed and HeavyTailed Insurance Losses. Michael R. Powers[ 1 ] Temple University and Tsinghua University
A Coefficient of Variation for Skewed and HeavyTailed Insurance Losses Michael R. Powers[ ] Temple University and Tsinghua University Thomas Y. Powers Yale University [June 2009] Abstract We propose a
More informationGENERALIZED LINEAR MODELS IN VEHICLE INSURANCE
ACTA UNIVERSITATIS AGRICULTURAE ET SILVICULTURAE MENDELIANAE BRUNENSIS Volume 62 41 Number 2, 2014 http://dx.doi.org/10.11118/actaun201462020383 GENERALIZED LINEAR MODELS IN VEHICLE INSURANCE Silvie Kafková
More informationA Deeper Look Inside Generalized Linear Models
A Deeper Look Inside Generalized Linear Models University of Minnesota February 3 rd, 2012 Nathan Hubbell, FCAS Agenda Property & Casualty (P&C Insurance) in one slide The Actuarial Profession Travelers
More informationNonlinear Algebraic Equations. Lectures INF2320 p. 1/88
Nonlinear Algebraic Equations Lectures INF2320 p. 1/88 Lectures INF2320 p. 2/88 Nonlinear algebraic equations When solving the system u (t) = g(u), u(0) = u 0, (1) with an implicit Euler scheme we have
More informationFactorial experimental designs and generalized linear models
Statistics & Operations Research Transactions SORT 29 (2) JulyDecember 2005, 249268 ISSN: 16962281 www.idescat.net/sort Statistics & Operations Research c Institut d Estadística de Transactions Catalunya
More informationPartial Least Squares (PLS) Regression.
Partial Least Squares (PLS) Regression. Hervé Abdi 1 The University of Texas at Dallas Introduction Pls regression is a recent technique that generalizes and combines features from principal component
More information1 Short Introduction to Time Series
ECONOMICS 7344, Spring 202 Bent E. Sørensen January 24, 202 Short Introduction to Time Series A time series is a collection of stochastic variables x,.., x t,.., x T indexed by an integer value t. The
More informationOLS is not only unbiased it is also the most precise (efficient) unbiased estimation technique  ie the estimator has the smallest variance
Lecture 5: Hypothesis Testing What we know now: OLS is not only unbiased it is also the most precise (efficient) unbiased estimation technique  ie the estimator has the smallest variance (if the GaussMarkov
More information7 Gaussian Elimination and LU Factorization
7 Gaussian Elimination and LU Factorization In this final section on matrix factorization methods for solving Ax = b we want to take a closer look at Gaussian elimination (probably the best known method
More informationC A R I B B E A N E X A M I N A T I O N S C O U N C I L REPORT ON CANDIDATES WORK IN THE SECONDARY EDUCATION CERTIFICATE EXAMINATION MAY/JUNE 2011
C A R I B B E A N E X A M I N A T I O N S C O U N C I L REPORT ON CANDIDATES WORK IN THE SECONDARY EDUCATION CERTIFICATE EXAMINATION MAY/JUNE 2011 MATHEMATICS GENERAL PROFICIENCY EXAMINATION Copyright
More informationSpecifications for this HLM2 run
One way ANOVA model 1. How much do U.S. high schools vary in their mean mathematics achievement? 2. What is the reliability of each school s sample mean as an estimate of its true population mean? 3. Do
More informationInferential Statistics
Inferential Statistics Sampling and the normal distribution Zscores Confidence levels and intervals Hypothesis testing Commonly used statistical methods Inferential Statistics Descriptive statistics are
More informationCorrectly Compute Complex Samples Statistics
SPSS Complex Samples 16.0 Specifications Correctly Compute Complex Samples Statistics When you conduct sample surveys, use a statistics package dedicated to producing correct estimates for complex sample
More informationADVANCED LINEAR ALGEBRA FOR ENGINEERS WITH MATLAB. Sohail A. Dianat. Rochester Institute of Technology, New York, U.S.A. Eli S.
ADVANCED LINEAR ALGEBRA FOR ENGINEERS WITH MATLAB Sohail A. Dianat Rochester Institute of Technology, New York, U.S.A. Eli S. Saber Rochester Institute of Technology, New York, U.S.A. (g) CRC Press Taylor
More informationMultivariate Normal Distribution
Multivariate Normal Distribution Lecture 4 July 21, 2011 Advanced Multivariate Statistical Methods ICPSR Summer Session #2 Lecture #47/21/2011 Slide 1 of 41 Last Time Matrices and vectors Eigenvalues
More informationGamma Distribution Fitting
Chapter 552 Gamma Distribution Fitting Introduction This module fits the gamma probability distributions to a complete or censored set of individual or grouped data values. It outputs various statistics
More informationAn Iterative Image Registration Technique with an Application to Stereo Vision
An Iterative Image Registration Technique with an Application to Stereo Vision Bruce D. Lucas Takeo Kanade Computer Science Department CarnegieMellon University Pittsburgh, Pennsylvania 15213 Abstract
More informationSome facts about polynomials modulo m (Full proof of the Fingerprinting Theorem)
Some facts about polynomials modulo m (Full proof of the Fingerprinting Theorem) In order to understand the details of the Fingerprinting Theorem on fingerprints of different texts from Chapter 19 of the
More information" Y. Notation and Equations for Regression Lecture 11/4. Notation:
Notation: Notation and Equations for Regression Lecture 11/4 m: The number of predictor variables in a regression Xi: One of multiple predictor variables. The subscript i represents any number from 1 through
More informationComponent Ordering in Independent Component Analysis Based on Data Power
Component Ordering in Independent Component Analysis Based on Data Power Anne Hendrikse Raymond Veldhuis University of Twente University of Twente Fac. EEMCS, Signals and Systems Group Fac. EEMCS, Signals
More informationME128 ComputerAided Mechanical Design Course Notes Introduction to Design Optimization
ME128 Computerided Mechanical Design Course Notes Introduction to Design Optimization 2. OPTIMIZTION Design optimization is rooted as a basic problem for design engineers. It is, of course, a rare situation
More informationMATH4427 Notebook 2 Spring 2016. 2 MATH4427 Notebook 2 3. 2.1 Definitions and Examples... 3. 2.2 Performance Measures for Estimators...
MATH4427 Notebook 2 Spring 2016 prepared by Professor Jenny Baglivo c Copyright 20092016 by Jenny A. Baglivo. All Rights Reserved. Contents 2 MATH4427 Notebook 2 3 2.1 Definitions and Examples...................................
More informationDeterminants LECTURE Calculating the Area of a Parallelogram. Definition Let A be a 2 2 matrix. A = The determinant of A is the number
LECTURE 13 Determinants 1. Calculating the Area of a Parallelogram Definition 13.1. Let A be a matrix. [ a c b d ] The determinant of A is the number det A) = ad bc Now consider the parallelogram formed
More information10.3 POWER METHOD FOR APPROXIMATING EIGENVALUES
55 CHAPTER NUMERICAL METHODS. POWER METHOD FOR APPROXIMATING EIGENVALUES In Chapter 7 we saw that the eigenvalues of an n n matrix A are obtained by solving its characteristic equation n c n n c n n...
More informationMissing Data: Part 1 What to Do? Carol B. Thompson Johns Hopkins Biostatistics Center SON Brown Bag 3/20/13
Missing Data: Part 1 What to Do? Carol B. Thompson Johns Hopkins Biostatistics Center SON Brown Bag 3/20/13 Overview Missingness and impact on statistical analysis Missing data assumptions/mechanisms Conventional
More information