ON EFFICIENT FORECASTING IN LINEAR REGRESSION MODELS

Size: px
Start display at page:

Download "ON EFFICIENT FORECASTING IN LINEAR REGRESSION MODELS"

Transcription

1 Journal of Quantitative Economics, Vol. 13, No.2 (July ON EFFICIENT FORECASTING IN LINEAR REGRESSION MODELS SHALABH Department of Statistics, University of Jammu, Jammu , India In this article, we present efficient forecasts for some future values of study variable in a linear regression model and analyze its performance with respect to forecasts derived from least squares and Stain-rule procedures. 1. INTRODUCTION Forecasting the future values of study variable corresponding to a given set of values of explanatory variables is an important aspect of regression analysis. Traditionally these forecasts are constructed from the least squares estimation of parameters employing the available observations. Such forecasts are linear and unbiased for both the actual and average values of the study variable. However, they may often be far less efficient with respect to the criterion of variability in comparison to some non-linear and biased forecasts such as those based on Stain-rule estimation of parameters. This articles presents a biased and nonlinear family of forecasts and analyses its performance properties. The organisation of our presentation it as follows. In Section 2, we specify the model and present the forecasts arising form least squares and Stain-rule estimation of regression coefficients. We also propose an alternative forecasting procedure. This provides a kind of extension of forecasts based on Stain-rule method. Taking the objective as forecasting of a weighted combination of the actual and average values of study variable, we analyze the performance properties of three forecasts in Section 3. All the three forecasts are found to share the same asymptotic properties. We have therefore considered higher order approximations employing the small disturbances asymptotic theory. First the bias vectors are examined and then the average forecasts risks are studied. Sufficient conditions for the superiority of one forecast over the other are derived in each case. The conditions are easy to verify in practice and may possibly help in making a suitable choice of forecasting procedures. 2. MODEL SPECIFICATIONAND FORECASTS

2 134 JOURNAL OF QUANTITATIVE ECONOMICS Let us consider the following linear regression model (2.1 Y = x(3 + (1 U where Y is a n x 1 vector of n observations on the study variable, X is a n x p full column rank matrix of n observations on p explanatory variables, {3 is a p x 1 vector of unknown regression coefficients,(1 is an unknown positive scalar and U is n x 1 vector of disturbances assumed to be independently, identically and normally distributed with mean zero and variance one. In addition to the n observation, we have another column vector Yf of nf unobserved of future values of study variable and a n f x p matrix xf p explanatory variables. Thus we can write (2.2 Yf = Xf{3 + (1 Uf of nf prespecified values of where Ut is a nf x 1 vector of disturbances possessing the same distributional properties as the elements of u. The least squares estimator of (3 in (2.1 is given by (2.3 b = (X' X-1 X'Y which is linear and unbiased. The Stain-rule estimator of {3 characterized by a positive and nonstochastic scalar k is defined by (2.4 b = [ 1-2k Y' (1- H Y ] b' H = X ( X' X -1 X' S (n - p + 2 Y' HY, which is neither linear nor unbiased: see, s.g., Judge and Bock (1978. Based on (2.3 and (2.4, the forecast vectors for the nf values of study variable are formulated as follows: (2.5 2k Y' (I - H Y (2.6 Fs = Xf bs = [1 - (n - p + 2 Y' H Y ] X f' b The vectors F and Fs can be used for forecasting the vector of actual values Yf as well as the average values E ( Yf = Xf p; see, e.g., Srivastavaand Shalabh (1996 and Trenkler and Toutenburg (1992. In order to provide a unified treatment, Shalabh (1995 has considered the following function: (2.7 with A as a nonstochastic scalar between a and 1, and has analyzed the performance

3 ON EFFICIENT FORECASTING IN LINEAR REGRESSION MODELS 135 properties of F and FS as forecasts for T. Notice that T reduces to the vector of average values of study variable when A. = 0 while it becomes the vector of actual values when A. = 1. If we consider gf as the forecast vector for T and choose the scalar such that the quantity (2.8 E (ef - T' (ef - T - e2 tr ( X'X -1 X' X + ( 1-e 2 f3 ' X' X f3+a.2n - ff a ff f is minimum, this yields the optimum value of g as ~ tr (X' X :-1X' X (2.9 = eo (say. It is easy to see that e=1- f f f3' X/ Xf f3 + a 2 tr (X' X -1 X I f X f (2.10 E [Y' (J - H Y ] = (n - p a 2 (2.11 E [y, X (X I X -1 X 'f Xf ( X' X -1 X' Y ] = f3 ' X 'f X f f3+ a 2 tr (X' X -1 X' f X f so that eo can be consistently estimated by '" Y' (1- H Y tr (X' X -1 X' X (2.12 e = 1 - f f o (n - p Y' X (X' X -1 X'f X f (X I X -1 X' Y We thus find eo F as a forecast vector for T. Stemming from it in the spirit of Stain-rule estimation we can define the following family of forecasts: (2.13 F*= [ where 1-2gY'(I-HY Xb (n-p+2 Y'H* yj f (2.14 H * = X (X' X -1 X'f Xf (X' X -1 X' and 9 is any positive nonstochastic scalar characterizing the forecasts. 3. EFFICIENCY PROPERTIES It is easy to see that the forecast vector F is, while Fsand unbiasedin the sensethat E (F - T = 0 F * are not, weakly

4 136 JOURNAL OF QUANTITATIVE ECONOMICS (3.1 E(FS-T=Jt:O E(F*-T=Jt:O. A Next, we consider the average forecast risk associated with any forecast vector T: A A A R(T=E(T-T' (T-T which means that all the nf values are errors are assigned identical weightage. It can be easily seen that forecasted collectively and all the forecasting (3.2 Similar results for Fsand F * can be derived utilizing the normality of disturbances but the expression -in case of F * may be sufficiently intricate and may not permit us to deduce any clear inference. We therefore propose to employ the small disturbance asymptotic theory. Accordingly, it can be easily seen that plim (F-T = plim (Fs - r = plim(f*-t = 0 implying the weak consistency of F, Fs and F* for T. Further, their asymptotic variance covariance matrices are identical and equal to a 2 V with V = fa.2 I p + Xf (X' X -1 X t' ]. Thus all the three forecasts are asymptotically equivalent in the sense that they have same asymptotic distribution. We therefore need to consider higher order approximations so as to discriminate their performance. These approximations are obtained in Appendix and are presented below. Let us first introduce the following notation: m = tr (X' X -1 X f' X f (3.3 q = (3'Xf' Xf(X' X-1 Xt' Xf (3 (3' Xt' Xf(3 Theorem: The small disturbance asymptotic approxiamtions for the bias for forecast

5 ON EFFICIENT FORECASTING IN LINEAR REGRESSION MODELS 137 vectors Fsand F * to order B ( a 2 are given by (3.4 8(FS = E(Fs - T 2 n-p k = - 2 a n B ' X I X~ X f {3 ( ( (3.5 8(F* = E(F*- T ( n-p n-p+2 while their average forecast risks to order 0 ( a 4 are given by (3.6 (3.7 R(Fs=R(F-4a 4 ( n-p n-p+2 4 n-p R(F* = R(F - 4a (n-p+2 ( {3, Xk,X{3 [m - ( k + 2 (BIX:'X,B [m-(g+2q». It is interesting to observe that the relative performance properties of F and Fs remain unaltered whether F, Fsand F * are used for forecasting the actual values or average values or a weighted combination of the two values. The expression (3.4 and (3.5 provide us an idea about the nature of bias in forecasting T by Fsand F *. If we take fj..= k, it is seen that Fs is superior to F * with respect to the criterion of magnitude of bias to the order of approximation so long as the largest eigen values of (X t' X f in the metric of (X I X is less than one. The reverse is true, Le., F *is superior to Fs when the smallest eigen value of (X f' Xf the metric of (X I X exceeds one. Looking at the expression (3.6, we observe that Fs is superior to F according to the criterion of average forecast risk to the order of our approximation when in (3.8 k«m-2;m>2. The converse is true, Le., F is superior to Fs when k exceeds (m - 2. Similarly, it follows from (3.7 that F * has 'smaller risk than F, to the order of our approximation, when (3.9 g < (m - 2q ; m > 2q. As q involves unknown {3, this condition is hard to check in practice. A sufficient

6 138 JOURNAL OF QUANTITATIVE ECONOMICS version of it can, however, be obtained as follows. If C1 s C2 S... s Cpdenote the eigen values of (X f' Xf in the metric of ( X ' X, we observe that (3.10 {3' X ' X ( X' X -1 X ' X {3 < - ff f f < C1 - q - {3' X / X f {3 - Cp' Thus the condition (3,9 is satisfied at least as long as p-1 (3.11 g < (m - 2 C - ( ~ C. - C - 2 P i=1 I P provided that m exceeds 2 Cp' On the other hand, F is better than F * when g exceeds (m - 2q so long as (3.12 p g > (m - 2 C1 = ( ~ i=2 Ci - C1-2. which is satisfied For compari~g Fsand F *, lest us assume that g and k are equal so that from (3.6 and (3.7 we have * 4 (3.13 ( n-p g R(Fs-R(F =4(1 n-p+2 ({3' Xf' Xf {3 {3' Xf' Xf {3 {3' Xf' Xf{3 [(1- B'X'XB (m-g+2(q- /3'X'X/3 J. This expression is positive implying the superiority of F * over Fs when (3.14 {3'X/Xf{3 {3'X/Xf{3 {3'X/Xf{3 (1- B'X'XB g< (1- B'X'XBm+2(q- B'X'XB' This inequality will be satisfied so long as or (3.15 (3.16 g < (1 ~ c g>(c~1 1

7 ON EFFICIENT FORECASTING IN LINEAR REGRESSION MODELS 139 The opposite is true, i.e., FS is superior to F * when the inequality (3.14 holds with a reversed sign. Such condition is satisfied as long as (3.17 (3.18 g>(1~c g«c~1 p p It may be remarked that the conditions such as (3.8, (3.11, (3.12, (3.15, (3.16, (3.17 and (3.18 for the superiority of one forecast over the other with respect to criteria like bias and average forecast risk, to the order of our approximation, are easy to check in- any given application as all that we need is certain eigen values. These conditions may also help us in finding forecasts with improved performance. APPENDIX In order to derive small disturbance asymptotic approximations for functions, we first observe from (2.1 that Y' (I-H Y - a2u' (/-Hu Y'H*Y - f3ix'xh*xf3 + 2aBIX'H*u + a2u'h*u 2 U' (1- H u [ 1 2 f3 I X' H * U 2 U I H * u =a + a +a f3'x'h*xf3 f3'x' H*Xf3 f3'x'h*xf3 bias and risk ] -1 (F- T 2 u'(i-hu 3 2 u'(i-hu, f3ix'h*u 4 =a - a + 0 ( a f3ix'h*xf3 (f3'x'h* X(32 P = Xf(b-f3 - aluf so that we can express = a [Xf (X I X -1 X' U- l u f ] (A.1 2 gu'(l-hu X f3 (F*-T=a[Xf(X'X-1 X'u-lUf] -2a (n-p+2 f3' X' H*Xf3 f Thus we have E(F*-T = -2a2 ( n-p+2 n-p which provides the result (3.5 of Theorem. ( 9 f3' X'H* X(3 Xff3 + 0(a3 + Op(a3

8 140 JOURNAL OF QUANTITATIVEECONOMICS Next, we observe that (A.2 0= (F-T' (F-T - (F*-T' (F*-T 4gy ' (/-H y Y'(I-HYb'X f 'X f b = b'x' (F-T -g [ (n-p+2 Y'H*Y f (n-p+2 Y'H*Y 4gU'(I-Hu [ = a a +a a + 0 a ] (n-p+2[3ix'h*x'f3 3 4 p( where J a3 = [31 X f' [Xf (X' X -1 X' U - AUf [X(X' X' -1-2 H* [3f3'J[X' X (X' X-1 f3'x' H*Xf3 f f X'U-AX'U f f] J g u'(i-hu. f3'xf' Xf[3 (n-p+2 [3'X'H* X[3. Utilizing the stochastic independence of U and U f along with their normality, it is easy to see that E [ U 1 (I - H U a3 = 0 E [u 1 (1- H U a 4 = (n - p tr (X' X -1 X f' X f - (n-p [2f3'X'X X'X-1X'H*X[3 f3'x'h*x[3 f f + g[3' Xt' Xff3J. Substituting these results in '(A.2, we find the result (3.7 stated in Theorem. The other two resultsmentioned in the Theorem can be derived in a similarmanner. REFERENCES JUDGE,G.G.AND M.E.BOCK (1978 : The Statistical Implications of Pre-Test and Stain-Rule Estimator in Econometrics, North-Holland Publishing Company, New York. SHALABH (1995 : 'Performance of Stain-Rule Procedure for Simultaneous Prediction of Actual and Average Values of Study Variable in Unear Regression Model' Proceedings of the Fiftieth Session of the International Statistical Institute, pp SRIVASTAVE,A.K. AND SHALABH (1996 : 'Efficiency Properties of Least Squares and Stein-Rule Predictions in Linear Regression Models' Journal of the Applied Statistical Science, 4, TRENKLAR, C. AND H. TOUTENBURG (1992 : 'Pre-test Procedures and Forecasting in the Regression Model under Restrictions' Journal of Statistical Planning and Inference, 30,

9 ~ c0u. -t'&p ~ d '"t\a'.1:,~ cj ~ ~ 1M ~ p~. YtW 'W\""Y ~ "IN- -to ~- f(1 -t1a <9 ~ ojh ~ C{ ~ D.. I \ t k., t:x.(. I "\.1 ' A,t kcj..~b~ 1 Q ~C{ ~ 00. Uf\M / De.-pa.h.:!:~&-6 tv\.~u, 2< ~-\--a;i-v:>-t1~ 'IA.cJ {0\", IM\itv-:te 01 T~V\{ 1 '0'1- K<A"'fcUL - 2-0'0 Ol~ t ~oti 0.

of Restricted and Mixed Regression Estimators

of Restricted and Mixed Regression Estimators Biom. J. 38 (1996) 8, 951-959 Akademie Verlag \ Predictive Performance of the Methods of Restricted and Mixed Regression Estimators H. TOUTENBURG Institut fur Statistik Universitat Miinchen Germany SHALABH

More information

Unbiased prediction in linear regression models with equi-correlated responses

Unbiased prediction in linear regression models with equi-correlated responses ') -t CAA\..-ll' ~ j... "1-' V'~ /'. uuo. ;). I ''''- ~ ( \ '.. /' I ~, Unbiased prediction in linear regression models with equi-correlated responses Shalabh Received: May 13, 1996; revised version: December

More information

Mean squared error matrix comparison of least aquares and Stein-rule estimators for regression coefficients under non-normal disturbances

Mean squared error matrix comparison of least aquares and Stein-rule estimators for regression coefficients under non-normal disturbances METRON - International Journal of Statistics 2008, vol. LXVI, n. 3, pp. 285-298 SHALABH HELGE TOUTENBURG CHRISTIAN HEUMANN Mean squared error matrix comparison of least aquares and Stein-rule estimators

More information

Sociedad de Estadística e Investigación Operativa

Sociedad de Estadística e Investigación Operativa Sociedad de Estadística e Investigación Operativa Test Volume 14, Number 2. December 2005 Estimation of Regression Coefficients Subject to Exact Linear Restrictions when Some Observations are Missing and

More information

Stein-Rule Estimation under an Extended Balanced Loss Function

Stein-Rule Estimation under an Extended Balanced Loss Function Shalabh & Helge Toutenburg & Christian Heumann Stein-Rule Estimation under an Extended Balanced Loss Function Technical Report Number 7, 7 Department of Statistics University of Munich http://www.stat.uni-muenchen.de

More information

Chapter 14 Stein-Rule Estimation

Chapter 14 Stein-Rule Estimation Chapter 14 Stein-Rule Estimation The ordinary least squares estimation of regression coefficients in linear regression model provides the estimators having minimum variance in the class of linear and unbiased

More information

Projektpartner. Sonderforschungsbereich 386, Paper 163 (1999) Online unter:

Projektpartner. Sonderforschungsbereich 386, Paper 163 (1999) Online unter: Toutenburg, Shalabh: Estimation of Regression Coefficients Subject to Exact Linear Restrictions when some Observations are Missing and Balanced Loss Function is Used Sonderforschungsbereich 386, Paper

More information

Bayesian Estimation of Regression Coefficients Under Extended Balanced Loss Function

Bayesian Estimation of Regression Coefficients Under Extended Balanced Loss Function Communications in Statistics Theory and Methods, 43: 4253 4264, 2014 Copyright Taylor & Francis Group, LLC ISSN: 0361-0926 print / 1532-415X online DOI: 10.1080/03610926.2012.725498 Bayesian Estimation

More information

Business Economics BUSINESS ECONOMICS. PAPER No. : 8, FUNDAMENTALS OF ECONOMETRICS MODULE No. : 3, GAUSS MARKOV THEOREM

Business Economics BUSINESS ECONOMICS. PAPER No. : 8, FUNDAMENTALS OF ECONOMETRICS MODULE No. : 3, GAUSS MARKOV THEOREM Subject Business Economics Paper No and Title Module No and Title Module Tag 8, Fundamentals of Econometrics 3, The gauss Markov theorem BSE_P8_M3 1 TABLE OF CONTENTS 1. INTRODUCTION 2. ASSUMPTIONS OF

More information

OMISSION OF RELEVANT EXPLANATORY VARIABLES IN SUR MODELS: OBTAINING THE BIAS USING A TRANSFORMATION

OMISSION OF RELEVANT EXPLANATORY VARIABLES IN SUR MODELS: OBTAINING THE BIAS USING A TRANSFORMATION - I? t OMISSION OF RELEVANT EXPLANATORY VARIABLES IN SUR MODELS: OBTAINING THE BIAS USING A TRANSFORMATION Richard Green LUniversity of California, Davis,. ABSTRACT This paper obtains an expression of

More information

Improved Multivariate Prediction in a General Linear Model with an Unknown Error Covariance Matrix

Improved Multivariate Prediction in a General Linear Model with an Unknown Error Covariance Matrix Journal of Multivariate Analysis 83, 166 182 (2002) doi:10.1006/jmva.2001.2042 Improved Multivariate Prediction in a General Linear Model with an Unknown Error Covariance Matrix Anoop Chaturvedi University

More information

Introduction to Estimation Methods for Time Series models. Lecture 1

Introduction to Estimation Methods for Time Series models. Lecture 1 Introduction to Estimation Methods for Time Series models Lecture 1 Fulvio Corsi SNS Pisa Fulvio Corsi Introduction to Estimation () Methods for Time Series models Lecture 1 SNS Pisa 1 / 19 Estimation

More information

Final Exam. Economics 835: Econometrics. Fall 2010

Final Exam. Economics 835: Econometrics. Fall 2010 Final Exam Economics 835: Econometrics Fall 2010 Please answer the question I ask - no more and no less - and remember that the correct answer is often short and simple. 1 Some short questions a) For each

More information

Specification errors in linear regression models

Specification errors in linear regression models Specification errors in linear regression models Jean-Marie Dufour McGill University First version: February 2002 Revised: December 2011 This version: December 2011 Compiled: December 9, 2011, 22:34 This

More information

Inverse of a Square Matrix. For an N N square matrix A, the inverse of A, 1

Inverse of a Square Matrix. For an N N square matrix A, the inverse of A, 1 Inverse of a Square Matrix For an N N square matrix A, the inverse of A, 1 A, exists if and only if A is of full rank, i.e., if and only if no column of A is a linear combination 1 of the others. A is

More information

Pseudo-minimax linear and mixed regression estimation of regression coecients when prior estimates are available

Pseudo-minimax linear and mixed regression estimation of regression coecients when prior estimates are available Statistics & Probability Letters 63 003 35 39 Pseudo-minimax linear and mixed regression estimation of regression coecients when prior estimates are available H. Shalabh a, H. Toutenburg b; a Department

More information

An Introduction to Parameter Estimation

An Introduction to Parameter Estimation Introduction Introduction to Econometrics An Introduction to Parameter Estimation This document combines several important econometric foundations and corresponds to other documents such as the Introduction

More information

1. The OLS Estimator. 1.1 Population model and notation

1. The OLS Estimator. 1.1 Population model and notation 1. The OLS Estimator OLS stands for Ordinary Least Squares. There are 6 assumptions ordinarily made, and the method of fitting a line through data is by least-squares. OLS is a common estimation methodology

More information

Variable Selection and Model Building

Variable Selection and Model Building LINEAR REGRESSION ANALYSIS MODULE XIII Lecture - 37 Variable Selection and Model Building Dr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur The complete regression

More information

ECONOMETRIC THEORY. MODULE XVII Lecture - 43 Simultaneous Equations Models

ECONOMETRIC THEORY. MODULE XVII Lecture - 43 Simultaneous Equations Models ECONOMETRIC THEORY MODULE XVII Lecture - 43 Simultaneous Equations Models Dr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur 2 Estimation of parameters To estimate

More information

Econometric Methods. Prediction / Violation of A-Assumptions. Burcu Erdogan. Universität Trier WS 2011/2012

Econometric Methods. Prediction / Violation of A-Assumptions. Burcu Erdogan. Universität Trier WS 2011/2012 Econometric Methods Prediction / Violation of A-Assumptions Burcu Erdogan Universität Trier WS 2011/2012 (Universität Trier) Econometric Methods 30.11.2011 1 / 42 Moving on to... 1 Prediction 2 Violation

More information

Econometrics I KS. Module 2: Multivariate Linear Regression. Alexander Ahammer. This version: April 16, 2018

Econometrics I KS. Module 2: Multivariate Linear Regression. Alexander Ahammer. This version: April 16, 2018 Econometrics I KS Module 2: Multivariate Linear Regression Alexander Ahammer Department of Economics Johannes Kepler University of Linz This version: April 16, 2018 Alexander Ahammer (JKU) Module 2: Multivariate

More information

COMPARING TRANSFORMATIONS USING TESTS OF SEPARATE FAMILIES. Department of Biostatistics, University of North Carolina at Chapel Hill, NC.

COMPARING TRANSFORMATIONS USING TESTS OF SEPARATE FAMILIES. Department of Biostatistics, University of North Carolina at Chapel Hill, NC. COMPARING TRANSFORMATIONS USING TESTS OF SEPARATE FAMILIES by Lloyd J. Edwards and Ronald W. Helms Department of Biostatistics, University of North Carolina at Chapel Hill, NC. Institute of Statistics

More information

Toutenburg, Srivastava: Estimation of Ratio of Population Means in Survey Sampling When Some Observations are Missing

Toutenburg, Srivastava: Estimation of Ratio of Population Means in Survey Sampling When Some Observations are Missing Toutenburg, Srivastava: Estimation of atio of Population Means in Survey Sampling When Some Observations are Missing Sonderforschungsbereich 386, Paper 9 998) Online unter: http://epub.ub.uni-muenchen.de/

More information

Christopher Dougherty London School of Economics and Political Science

Christopher Dougherty London School of Economics and Political Science Introduction to Econometrics FIFTH EDITION Christopher Dougherty London School of Economics and Political Science OXFORD UNIVERSITY PRESS Contents INTRODU CTION 1 Why study econometrics? 1 Aim of this

More information

Predicate Logic. 1 Predicate Logic Symbolization

Predicate Logic. 1 Predicate Logic Symbolization 1 Predicate Logic Symbolization innovation of predicate logic: analysis of simple statements into two parts: the subject and the predicate. E.g. 1: John is a giant. subject = John predicate =... is a giant

More information

Simultaneous Equation Models Learning Objectives Introduction Introduction (2) Introduction (3) Solving the Model structural equations

Simultaneous Equation Models Learning Objectives Introduction Introduction (2) Introduction (3) Solving the Model structural equations Simultaneous Equation Models. Introduction: basic definitions 2. Consequences of ignoring simultaneity 3. The identification problem 4. Estimation of simultaneous equation models 5. Example: IS LM model

More information

Quantitative Analysis of Financial Markets. Summary of Part II. Key Concepts & Formulas. Christopher Ting. November 11, 2017

Quantitative Analysis of Financial Markets. Summary of Part II. Key Concepts & Formulas. Christopher Ting. November 11, 2017 Summary of Part II Key Concepts & Formulas Christopher Ting November 11, 2017 christopherting@smu.edu.sg http://www.mysmu.edu/faculty/christophert/ Christopher Ting 1 of 16 Why Regression Analysis? Understand

More information

Econometrics Summary Algebraic and Statistical Preliminaries

Econometrics Summary Algebraic and Statistical Preliminaries Econometrics Summary Algebraic and Statistical Preliminaries Elasticity: The point elasticity of Y with respect to L is given by α = ( Y/ L)/(Y/L). The arc elasticity is given by ( Y/ L)/(Y/L), when L

More information

Dynamic Regression Models (Lect 15)

Dynamic Regression Models (Lect 15) Dynamic Regression Models (Lect 15) Ragnar Nymoen University of Oslo 21 March 2013 1 / 17 HGL: Ch 9; BN: Kap 10 The HGL Ch 9 is a long chapter, and the testing for autocorrelation part we have already

More information

Bootstrap Approach to Comparison of Alternative Methods of Parameter Estimation of a Simultaneous Equation Model

Bootstrap Approach to Comparison of Alternative Methods of Parameter Estimation of a Simultaneous Equation Model Bootstrap Approach to Comparison of Alternative Methods of Parameter Estimation of a Simultaneous Equation Model Olubusoye, O. E., J. O. Olaomi, and O. O. Odetunde Abstract A bootstrap simulation approach

More information

LOWELL WEEKLY JOURNAL. ^Jberxy and (Jmott Oao M d Ccmsparftble. %m >ai ruv GEEAT INDUSTRIES

LOWELL WEEKLY JOURNAL. ^Jberxy and (Jmott Oao M d Ccmsparftble. %m >ai ruv GEEAT INDUSTRIES ? (») /»» 9 F ( ) / ) /»F»»»»»# F??»»» Q ( ( »»» < 3»» /» > > } > Q ( Q > Z F 5

More information

Econometrics I KS. Module 1: Bivariate Linear Regression. Alexander Ahammer. This version: March 12, 2018

Econometrics I KS. Module 1: Bivariate Linear Regression. Alexander Ahammer. This version: March 12, 2018 Econometrics I KS Module 1: Bivariate Linear Regression Alexander Ahammer Department of Economics Johannes Kepler University of Linz This version: March 12, 2018 Alexander Ahammer (JKU) Module 1: Bivariate

More information

Economics 113. Simple Regression Assumptions. Simple Regression Derivation. Changing Units of Measurement. Nonlinear effects

Economics 113. Simple Regression Assumptions. Simple Regression Derivation. Changing Units of Measurement. Nonlinear effects Economics 113 Simple Regression Models Simple Regression Assumptions Simple Regression Derivation Changing Units of Measurement Nonlinear effects OLS and unbiased estimates Variance of the OLS estimates

More information

Problem Set #6: OLS. Economics 835: Econometrics. Fall 2012

Problem Set #6: OLS. Economics 835: Econometrics. Fall 2012 Problem Set #6: OLS Economics 835: Econometrics Fall 202 A preliminary result Suppose we have a random sample of size n on the scalar random variables (x, y) with finite means, variances, and covariance.

More information

Correlation: Copulas and Conditioning

Correlation: Copulas and Conditioning Correlation: Copulas and Conditioning This note reviews two methods of simulating correlated variates: copula methods and conditional distributions, and the relationships between them. Particular emphasis

More information

COMPARISON OF GMM WITH SECOND-ORDER LEAST SQUARES ESTIMATION IN NONLINEAR MODELS. Abstract

COMPARISON OF GMM WITH SECOND-ORDER LEAST SQUARES ESTIMATION IN NONLINEAR MODELS. Abstract Far East J. Theo. Stat. 0() (006), 179-196 COMPARISON OF GMM WITH SECOND-ORDER LEAST SQUARES ESTIMATION IN NONLINEAR MODELS Department of Statistics University of Manitoba Winnipeg, Manitoba, Canada R3T

More information

Mathematical Analysis Outline. William G. Faris

Mathematical Analysis Outline. William G. Faris Mathematical Analysis Outline William G. Faris January 8, 2007 2 Chapter 1 Metric spaces and continuous maps 1.1 Metric spaces A metric space is a set X together with a real distance function (x, x ) d(x,

More information

Topic 7 - Matrix Approach to Simple Linear Regression. Outline. Matrix. Matrix. Review of Matrices. Regression model in matrix form

Topic 7 - Matrix Approach to Simple Linear Regression. Outline. Matrix. Matrix. Review of Matrices. Regression model in matrix form Topic 7 - Matrix Approach to Simple Linear Regression Review of Matrices Outline Regression model in matrix form - Fall 03 Calculations using matrices Topic 7 Matrix Collection of elements arranged in

More information

Financial Econometrics

Financial Econometrics Financial Econometrics Estimation and Inference Gerald P. Dwyer Trinity College, Dublin January 2013 Who am I? Visiting Professor and BB&T Scholar at Clemson University Federal Reserve Bank of Atlanta

More information

PARTIAL RIDGE REGRESSION 1

PARTIAL RIDGE REGRESSION 1 1 2 This work was supported by NSF Grants GU-2059 and GU-19568 and by U.S. Air Force Grant No. AFOSR-68-1415. On leave from Punjab Agricultural University (India). Reproduction in whole or in part is permitted

More information

Simple Linear Regression

Simple Linear Regression Simple Linear Regression Christopher Ting Christopher Ting : christophert@smu.edu.sg : 688 0364 : LKCSB 5036 January 7, 017 Web Site: http://www.mysmu.edu/faculty/christophert/ Christopher Ting QF 30 Week

More information

Simple Linear Regression Analysis

Simple Linear Regression Analysis LINEAR REGRESSION ANALYSIS MODULE II Lecture - 6 Simple Linear Regression Analysis Dr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur Prediction of values of study

More information

A Course on Advanced Econometrics

A Course on Advanced Econometrics A Course on Advanced Econometrics Yongmiao Hong The Ernest S. Liu Professor of Economics & International Studies Cornell University Course Introduction: Modern economies are full of uncertainties and risk.

More information

ECON The Simple Regression Model

ECON The Simple Regression Model ECON 351 - The Simple Regression Model Maggie Jones 1 / 41 The Simple Regression Model Our starting point will be the simple regression model where we look at the relationship between two variables In

More information

Statistics 910, #5 1. Regression Methods

Statistics 910, #5 1. Regression Methods Statistics 910, #5 1 Overview Regression Methods 1. Idea: effects of dependence 2. Examples of estimation (in R) 3. Review of regression 4. Comparisons and relative efficiencies Idea Decomposition Well-known

More information

Advanced Econometrics I

Advanced Econometrics I Lecture Notes Autumn 2010 Dr. Getinet Haile, University of Mannheim 1. Introduction Introduction & CLRM, Autumn Term 2010 1 What is econometrics? Econometrics = economic statistics economic theory mathematics

More information

ECONOMETRIC THEORY. MODULE VI Lecture 19 Regression Analysis Under Linear Restrictions

ECONOMETRIC THEORY. MODULE VI Lecture 19 Regression Analysis Under Linear Restrictions ECONOMETRIC THEORY MODULE VI Lecture 9 Regression Analysis Under Linear Restrictions Dr Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur One of the basic objectives

More information

Review of Classical Least Squares. James L. Powell Department of Economics University of California, Berkeley

Review of Classical Least Squares. James L. Powell Department of Economics University of California, Berkeley Review of Classical Least Squares James L. Powell Department of Economics University of California, Berkeley The Classical Linear Model The object of least squares regression methods is to model and estimate

More information

statistical sense, from the distributions of the xs. The model may now be generalized to the case of k regressors:

statistical sense, from the distributions of the xs. The model may now be generalized to the case of k regressors: Wooldridge, Introductory Econometrics, d ed. Chapter 3: Multiple regression analysis: Estimation In multiple regression analysis, we extend the simple (two-variable) regression model to consider the possibility

More information

ECON 3150/4150, Spring term Lecture 6

ECON 3150/4150, Spring term Lecture 6 ECON 3150/4150, Spring term 2013. Lecture 6 Review of theoretical statistics for econometric modelling (II) Ragnar Nymoen University of Oslo 31 January 2013 1 / 25 References to Lecture 3 and 6 Lecture

More information

Linear Algebra Review

Linear Algebra Review Linear Algebra Review Yang Feng http://www.stat.columbia.edu/~yangfeng Yang Feng (Columbia University) Linear Algebra Review 1 / 45 Definition of Matrix Rectangular array of elements arranged in rows and

More information

Regression and Statistical Inference

Regression and Statistical Inference Regression and Statistical Inference Walid Mnif wmnif@uwo.ca Department of Applied Mathematics The University of Western Ontario, London, Canada 1 Elements of Probability 2 Elements of Probability CDF&PDF

More information

Making sense of Econometrics: Basics

Making sense of Econometrics: Basics Making sense of Econometrics: Basics Lecture 2: Simple Regression Egypt Scholars Economic Society Happy Eid Eid present! enter classroom at http://b.socrative.com/login/student/ room name c28efb78 Outline

More information

Marcia Gumpertz and Sastry G. Pantula Department of Statistics North Carolina State University Raleigh, NC

Marcia Gumpertz and Sastry G. Pantula Department of Statistics North Carolina State University Raleigh, NC A Simple Approach to Inference in Random Coefficient Models March 8, 1988 Marcia Gumpertz and Sastry G. Pantula Department of Statistics North Carolina State University Raleigh, NC 27695-8203 Key Words

More information

ARIMA Modelling and Forecasting

ARIMA Modelling and Forecasting ARIMA Modelling and Forecasting Economic time series often appear nonstationary, because of trends, seasonal patterns, cycles, etc. However, the differences may appear stationary. Δx t x t x t 1 (first

More information

Föreläsning /31

Föreläsning /31 1/31 Föreläsning 10 090420 Chapter 13 Econometric Modeling: Model Speci cation and Diagnostic testing 2/31 Types of speci cation errors Consider the following models: Y i = β 1 + β 2 X i + β 3 X 2 i +

More information

LECTURE 2 LINEAR REGRESSION MODEL AND OLS

LECTURE 2 LINEAR REGRESSION MODEL AND OLS SEPTEMBER 29, 2014 LECTURE 2 LINEAR REGRESSION MODEL AND OLS Definitions A common question in econometrics is to study the effect of one group of variables X i, usually called the regressors, on another

More information

Economics 620, Lecture 2: Regression Mechanics (Simple Regression)

Economics 620, Lecture 2: Regression Mechanics (Simple Regression) 1 Economics 620, Lecture 2: Regression Mechanics (Simple Regression) Observed variables: y i ; x i i = 1; :::; n Hypothesized (model): Ey i = + x i or y i = + x i + (y i Ey i ) ; renaming we get: y i =

More information

Least Squares Estimation-Finite-Sample Properties

Least Squares Estimation-Finite-Sample Properties Least Squares Estimation-Finite-Sample Properties Ping Yu School of Economics and Finance The University of Hong Kong Ping Yu (HKU) Finite-Sample 1 / 29 Terminology and Assumptions 1 Terminology and Assumptions

More information

WEAKER MSE CRITERIA AND TESTS FOR LINEAR RESTRICTIONS IN REGRESSION MODELS WITH NON-SPHERICAL DISTURBANCES. Marjorie B. MCELROY *

WEAKER MSE CRITERIA AND TESTS FOR LINEAR RESTRICTIONS IN REGRESSION MODELS WITH NON-SPHERICAL DISTURBANCES. Marjorie B. MCELROY * Journal of Econometrics 6 (1977) 389-394. 0 North-Holland Publishing Company WEAKER MSE CRITERIA AND TESTS FOR LINEAR RESTRICTIONS IN REGRESSION MODELS WITH NON-SPHERICAL DISTURBANCES Marjorie B. MCELROY

More information

Ordinary Least Squares Regression

Ordinary Least Squares Regression Ordinary Least Squares Regression Goals for this unit More on notation and terminology OLS scalar versus matrix derivation Some Preliminaries In this class we will be learning to analyze Cross Section

More information

Quick Review on Linear Multiple Regression

Quick Review on Linear Multiple Regression Quick Review on Linear Multiple Regression Mei-Yuan Chen Department of Finance National Chung Hsing University March 6, 2007 Introduction for Conditional Mean Modeling Suppose random variables Y, X 1,

More information

ECONOMETRICS FIELD EXAM Michigan State University August 21, 2009

ECONOMETRICS FIELD EXAM Michigan State University August 21, 2009 ECONOMETRICS FIELD EXAM Michigan State University August 21, 2009 Instructions: Answer all four (4) questions. Point totals for each question are given in parentheses; there are 100 points possible. Within

More information

Ridge Estimator in Logistic Regression under Stochastic Linear Restrictions

Ridge Estimator in Logistic Regression under Stochastic Linear Restrictions British Journal of Mathematics & Computer Science 15(3): 1-14, 2016, Article no.bjmcs.24585 ISSN: 2231-0851 SCIENCEDOMAIN international www.sciencedomain.org Ridge Estimator in Logistic Regression under

More information

NUCLEAR NORM PENALIZED ESTIMATION OF INTERACTIVE FIXED EFFECT MODELS. Incomplete and Work in Progress. 1. Introduction

NUCLEAR NORM PENALIZED ESTIMATION OF INTERACTIVE FIXED EFFECT MODELS. Incomplete and Work in Progress. 1. Introduction NUCLEAR NORM PENALIZED ESTIMATION OF IERACTIVE FIXED EFFECT MODELS HYUNGSIK ROGER MOON AND MARTIN WEIDNER Incomplete and Work in Progress. Introduction Interactive fixed effects panel regression models

More information

304 A^VÇÚO 1n ò while the commonly employed loss function for the precision of estimation is squared error loss function ( β β) ( β β) (1.3) or weight

304 A^VÇÚO 1n ò while the commonly employed loss function for the precision of estimation is squared error loss function ( β β) ( β β) (1.3) or weight A^VÇÚO 1n ò 1nÏ 2014c6 Chinese Journal of Applied Probability and Statistics Vol.30 No.3 Jun. 2014 The Best Linear Unbiased Estimation of Regression Coefficient under Weighted Balanced Loss Function Fang

More information

Linear Model Under General Variance

Linear Model Under General Variance Linear Model Under General Variance We have a sample of T random variables y 1, y 2,, y T, satisfying the linear model Y = X β + e, where Y = (y 1,, y T )' is a (T 1) vector of random variables, X = (T

More information

1. The Multivariate Classical Linear Regression Model

1. The Multivariate Classical Linear Regression Model Business School, Brunel University MSc. EC550/5509 Modelling Financial Decisions and Markets/Introduction to Quantitative Methods Prof. Menelaos Karanasos (Room SS69, Tel. 08956584) Lecture Notes 5. The

More information

Multicollinearity and A Ridge Parameter Estimation Approach

Multicollinearity and A Ridge Parameter Estimation Approach Journal of Modern Applied Statistical Methods Volume 15 Issue Article 5 11-1-016 Multicollinearity and A Ridge Parameter Estimation Approach Ghadban Khalaf King Khalid University, albadran50@yahoo.com

More information

INTRODUCTORY ECONOMETRICS

INTRODUCTORY ECONOMETRICS INTRODUCTORY ECONOMETRICS Lesson 2b Dr Javier Fernández etpfemaj@ehu.es Dpt. of Econometrics & Statistics UPV EHU c J Fernández (EA3-UPV/EHU), February 21, 2009 Introductory Econometrics - p. 1/192 GLRM:

More information

Research Article An Unbiased Two-Parameter Estimation with Prior Information in Linear Regression Model

Research Article An Unbiased Two-Parameter Estimation with Prior Information in Linear Regression Model e Scientific World Journal, Article ID 206943, 8 pages http://dx.doi.org/10.1155/2014/206943 Research Article An Unbiased Two-Parameter Estimation with Prior Information in Linear Regression Model Jibo

More information

Linear models. Linear models are computationally convenient and remain widely used in. applied econometric research

Linear models. Linear models are computationally convenient and remain widely used in. applied econometric research Linear models Linear models are computationally convenient and remain widely used in applied econometric research Our main focus in these lectures will be on single equation linear models of the form y

More information

Lecture 13: Simple Linear Regression in Matrix Format. 1 Expectations and Variances with Vectors and Matrices

Lecture 13: Simple Linear Regression in Matrix Format. 1 Expectations and Variances with Vectors and Matrices Lecture 3: Simple Linear Regression in Matrix Format To move beyond simple regression we need to use matrix algebra We ll start by re-expressing simple linear regression in matrix form Linear algebra is

More information

Generalized Method of Moments (GMM) Estimation

Generalized Method of Moments (GMM) Estimation Econometrics 2 Fall 2004 Generalized Method of Moments (GMM) Estimation Heino Bohn Nielsen of29 Outline of the Lecture () Introduction. (2) Moment conditions and methods of moments (MM) estimation. Ordinary

More information

Economic modelling and forecasting

Economic modelling and forecasting Economic modelling and forecasting 2-6 February 2015 Bank of England he generalised method of moments Ole Rummel Adviser, CCBS at the Bank of England ole.rummel@bankofengland.co.uk Outline Classical estimation

More information

Multivariate Regression Analysis

Multivariate Regression Analysis Matrices and vectors The model from the sample is: Y = Xβ +u with n individuals, l response variable, k regressors Y is a n 1 vector or a n l matrix with the notation Y T = (y 1,y 2,...,y n ) 1 x 11 x

More information

Regression Analysis. y t = β 1 x t1 + β 2 x t2 + β k x tk + ϵ t, t = 1,..., T,

Regression Analysis. y t = β 1 x t1 + β 2 x t2 + β k x tk + ϵ t, t = 1,..., T, Regression Analysis The multiple linear regression model with k explanatory variables assumes that the tth observation of the dependent or endogenous variable y t is described by the linear relationship

More information

Suggested Solution for PS #5

Suggested Solution for PS #5 Cornell University Department of Economics Econ 62 Spring 28 TA: Jae Ho Yun Suggested Solution for S #5. (Measurement Error, IV) (a) This is a measurement error problem. y i x i + t i + " i t i t i + i

More information

Scanner Data and the Estimation of Demand Parameters

Scanner Data and the Estimation of Demand Parameters CARD Working Papers CARD Reports and Working Papers 4-1991 Scanner Data and the Estimation of Demand Parameters Richard Green Iowa State University Zuhair A. Hassan Iowa State University Stanley R. Johnson

More information

Economics 620, Lecture 8: Asymptotics I

Economics 620, Lecture 8: Asymptotics I Economics 620, Lecture 8: Asymptotics I Nicholas M. Kiefer Cornell University Professor N. M. Kiefer (Cornell University) Lecture 8: Asymptotics I 1 / 17 We are interested in the properties of estimators

More information

Simple Linear Regression: The Model

Simple Linear Regression: The Model Simple Linear Regression: The Model task: quantifying the effect of change X in X on Y, with some constant β 1 : Y = β 1 X, linear relationship between X and Y, however, relationship subject to a random

More information

Exogeneity tests and weak-identification

Exogeneity tests and weak-identification Exogeneity tests and weak-identification Firmin Doko Université de Montréal Jean-Marie Dufour McGill University First version: September 2007 Revised: October 2007 his version: February 2007 Compiled:

More information

Journal of Multivariate Analysis. Use of prior information in the consistent estimation of regression coefficients in measurement error models

Journal of Multivariate Analysis. Use of prior information in the consistent estimation of regression coefficients in measurement error models Journal of Multivariate Analysis 00 (2009) 498 520 Contents lists available at ScienceDirect Journal of Multivariate Analysis journal homepage: www.elsevier.com/locate/jmva Use of prior information in

More information

Financial Econometrics

Financial Econometrics Material : solution Class : Teacher(s) : zacharias psaradakis, marian vavra Example 1.1: Consider the linear regression model y Xβ + u, (1) where y is a (n 1) vector of observations on the dependent variable,

More information

Lecture 15 Multiple regression I Chapter 6 Set 2 Least Square Estimation The quadratic form to be minimized is

Lecture 15 Multiple regression I Chapter 6 Set 2 Least Square Estimation The quadratic form to be minimized is Lecture 15 Multiple regression I Chapter 6 Set 2 Least Square Estimation The quadratic form to be minimized is Q = (Y i β 0 β 1 X i1 β 2 X i2 β p 1 X i.p 1 ) 2, which in matrix notation is Q = (Y Xβ) (Y

More information

Greene, Econometric Analysis (7th ed, 2012)

Greene, Econometric Analysis (7th ed, 2012) EC771: Econometrics, Spring 2012 Greene, Econometric Analysis (7th ed, 2012) Chapters 2 3: Classical Linear Regression The classical linear regression model is the single most useful tool in econometrics.

More information

Wooldridge, Introductory Econometrics, 4th ed. Appendix C: Fundamentals of mathematical statistics

Wooldridge, Introductory Econometrics, 4th ed. Appendix C: Fundamentals of mathematical statistics Wooldridge, Introductory Econometrics, 4th ed. Appendix C: Fundamentals of mathematical statistics A short review of the principles of mathematical statistics (or, what you should have learned in EC 151).

More information

Empirical Economic Research, Part II

Empirical Economic Research, Part II Based on the text book by Ramanathan: Introductory Econometrics Robert M. Kunst robert.kunst@univie.ac.at University of Vienna and Institute for Advanced Studies Vienna December 7, 2011 Outline Introduction

More information

LOWELL WEEKLY JOURNAL

LOWELL WEEKLY JOURNAL Y G q G Y Y 29 8 $ 29 G 6 q )

More information

Performance of the 2shi Estimator Under the Generalised Pitman Nearness Criterion

Performance of the 2shi Estimator Under the Generalised Pitman Nearness Criterion University of Wollongong Research Online Faculty of Business - Economics Working Papers Faculty of Business 1999 Performance of the 2shi Estimator Under the Generalised Pitman Nearness Criterion T. V.

More information

Chapter 5 Matrix Approach to Simple Linear Regression

Chapter 5 Matrix Approach to Simple Linear Regression STAT 525 SPRING 2018 Chapter 5 Matrix Approach to Simple Linear Regression Professor Min Zhang Matrix Collection of elements arranged in rows and columns Elements will be numbers or symbols For example:

More information

Econ 623 Econometrics II Topic 2: Stationary Time Series

Econ 623 Econometrics II Topic 2: Stationary Time Series 1 Introduction Econ 623 Econometrics II Topic 2: Stationary Time Series In the regression model we can model the error term as an autoregression AR(1) process. That is, we can use the past value of the

More information

Graduate Econometrics I: Unbiased Estimation

Graduate Econometrics I: Unbiased Estimation Graduate Econometrics I: Unbiased Estimation Yves Dominicy Université libre de Bruxelles Solvay Brussels School of Economics and Management ECARES Yves Dominicy Graduate Econometrics I: Unbiased Estimation

More information

TESTING FOR NORMALITY IN THE LINEAR REGRESSION MODEL: AN EMPIRICAL LIKELIHOOD RATIO TEST

TESTING FOR NORMALITY IN THE LINEAR REGRESSION MODEL: AN EMPIRICAL LIKELIHOOD RATIO TEST Econometrics Working Paper EWP0402 ISSN 1485-6441 Department of Economics TESTING FOR NORMALITY IN THE LINEAR REGRESSION MODEL: AN EMPIRICAL LIKELIHOOD RATIO TEST Lauren Bin Dong & David E. A. Giles Department

More information

Local Polynomial Regression

Local Polynomial Regression VI Local Polynomial Regression (1) Global polynomial regression We observe random pairs (X 1, Y 1 ),, (X n, Y n ) where (X 1, Y 1 ),, (X n, Y n ) iid (X, Y ). We want to estimate m(x) = E(Y X = x) based

More information

ECONOMETFUCS FIELD EXAM Michigan State University May 11, 2007

ECONOMETFUCS FIELD EXAM Michigan State University May 11, 2007 ECONOMETFUCS FIELD EXAM Michigan State University May 11, 2007 Instructions: Answer all four (4) questions. Point totals for each question are given in parenthesis; there are 100 points possible. Within

More information

Econometrics -- Final Exam (Sample)

Econometrics -- Final Exam (Sample) Econometrics -- Final Exam (Sample) 1) The sample regression line estimated by OLS A) has an intercept that is equal to zero. B) is the same as the population regression line. C) cannot have negative and

More information

Folie 1. Folie 2. Folie 3. Evaluating Econometric Forecasts of. Economic and Financial Variables. Chapter 2 (

Folie 1. Folie 2. Folie 3. Evaluating Econometric Forecasts of. Economic and Financial Variables. Chapter 2 ( Folie 1 Evaluating Econometric Forecasts of Economic and Financial Variables Michael P. CLEMENS Palgrave macmilian, Basingstoke, 005 Chapter (.1.3.) Point Forecasts Zenaty Patrik 010703 Folie CONEN Introduction

More information

Nonlinear Control. Nonlinear Control Lecture # 2 Stability of Equilibrium Points

Nonlinear Control. Nonlinear Control Lecture # 2 Stability of Equilibrium Points Nonlinear Control Lecture # 2 Stability of Equilibrium Points Basic Concepts ẋ = f(x) f is locally Lipschitz over a domain D R n Suppose x D is an equilibrium point; that is, f( x) = 0 Characterize and

More information