ASSET PRICING MODELS

Size: px
Start display at page:

Download "ASSET PRICING MODELS"

Transcription

1 ASSE PRICING MODELS [1] CAPM (1) Some notation: R it = (gross) return on asset i at time t. R mt = (gross) return on the market portfolio at time t. R ft = return on risk-free asset at time t. X it = R it R ft = excess return on asset i. X mt = R mt R ft = excess return on the market portfolio. R1 t X1 t 1 R 2t X 2t 1 Rt = ; Xt = ; en = : : : R X 1 Nt N 1 Nt N For simplicity, we assume that (R t,r ft,r mt ) is iid over time. 1 (2) Sharpe-Lintner version of CAPM Lintner, 1965, Review of Economics and Statistics Sharpe, 1964, Journal of Finance Campbell, Lo and Mackinlay (CLM), 1997, book, chapter 5. ASSE PRICING-1

2 1) Basic idea: var( R mt ) = risk from the market portfolio of risky asset. risk price = p. cost of bearing the market risk = pvar( R mt ). At equilibrium, cost of risk = expected gain from risk. pvar( R ) = E( R ) R mt mt ft E( Rmt ) Rft p =. var( R ) Systematic risk of an individual asset i: mt he risk of asset i due to correlation between returns on asset i and the whole risky-asset market cov( R, R ). it mt Let β i be the systematic risk of an individual asset i relative to the market risk: cov( Rit, Rmt ) β i =. var( R ) mt his β i can be estimated by the time-series OLS on: R it = α i + β i R mt + ε it. Cost of bearing the (systematic) risk of asset i: β var( R ) p = β [ E( R ) R ]. i mt i mt ft ASSE PRICING-2

3 Equilibrium condition: ER ( ) β [ ER ( ) R] = R, for all i = 1,..., N it i mt ft ft ER ( ) = R + β [ ER ( ) R] or E( X ) = β E( X ). it ft i mt ft [Capital Asset Pricing Model] it i mt 2) Empirical Model Model: X 1t = α 1 + β 1 X mt + ε 1t ; X 2t = α 2 + β 2 X mt + ε 2t ; : X Nt = α N + β N X mt + ε 3t. X t = α + βx mt + ε t, where α = ( α1,..., α N ), β = ( β1,..., β N ) and εt = ( ε1 t,..., ε Nt). Assume that the ε t are iid over time with Cov( εt) = Σ= [ σ ii] N N. Comments. No heteroskedasticity over time. Reasonable if ε t is normal. If ε t is t-distributed, heteroskedasticity should exist. [MacKinlay and Richardson (1991, JF).] ASSE PRICING-3

4 Equilibrium condition: ER ( ) β [ ER ( ) R] = R it i mt ft ft, for all i = 1,..., N ER ( ) = R + β [ ER ( ) R] or E( X ) = β E( X ). it ft i mt ft [Capital Asset Pricing Model] it i mt 2) Empirical Model Model: X 1t = α 1 + β 1 X mt + ε 1t ; X 2t = α 2 + β 2 X mt + ε 2t ; : X Nt = α N + β N X mt + ε 3t. X t = α + βx mt + ε t, where α = ( α1,..., α ), β = ( β1,..., β ) and ε = ( ε1,..., ε ). N N t t Nt Assume that the ε t are iid over time with Cov( ε t) = Σ= [ σ ii] N N. Comments. No heteroskedasticity over time. Reasonable if ε t is normal. If ε t is t-distributed, heteroskedasticity should exist. [MacKinlay and Richardson (1991, JF).] ASSE PRICING-4

5 Estimation: SUR model with the same regressor: GLS = OLS. Use MLE or OLS. CAPM implies H o : α 1 =... = α N = 0. Can test these restrictions by Wald or LR. [See Ch. 4-5 of CLM.] If N is too large, the test result would be unreliable. [See Ahn and Gadarowski, 2004] wo-pass Regression Method (Fama- MacBeth, 1973, JPE) Suppose that β i s are known. hen, we can consider the following cross-sectional regression model for each t: (*) X = e γ 1 + βγ 2 + error, t N t t where β = ( β1,..., β ). N If the CAPM is correct, it should be the case that E(γ 1t ) = 0 and E(γ 2t ) 0. ASSE PRICING-5

6 Estimation procedure: SEP 1: SEP 2: For each i, do time-series OLS to estimate β i ( ˆi β ). For each t, do cross-section OLS to estimate γ 1t and γ 2t ( ˆ γ 1t and ˆ γ 2 t ). SEP 3: Compute: ˆ γ 1 ˆ ˆ 1 ˆ γ γ ( 1) γ γ ( ) 2 1 ;var( ) ˆ j = Σ t= jt j = Σt= 1 jt j SEP 4: Do t-tests to check whether γ 1 = 0 and γ Equivalent Procedure [Shanken, 1992, RFS] SEP 1: For each i, do time-series OLS to estimate β i ( ˆi β ). Let 1 t t Bˆ = ( e, ˆ N β ), γ = ( γ1, γ 2) and X = Σ = 1X SEP 2: Do OLS on X = Bˆ γ + error : ( BB ˆˆ) 1 ˆ γ = BX ˆ ; ( ) ( ˆˆ) ˆ 1 ˆ γ = Σ ˆ 2 1( )( ) ( ˆˆ t= t t ) 1 1 Cov B B B X X X X B B B he above covariance matrix is valid only if true β i s are used. Correct form of the covariance matrix will be discussed below. ASSE PRICING-6

7 (3) Black-version of CAPM: 1) Basic Model Model when there is no risk-free asset. R omt = return on the zero-beta portfolio associated with m. [portfolio that has the minimum variance of all portfolios uncorrelated with m] Let γ = E(R omt ). Black-Version of CAPM: E(R it ) = γ + β i [E(R mt )-γ] E(R it ) = γ(1-β i ) + β i E(R mt ). 2) Empirical estimation and testing. Empirical Model: R 1t = α 1 + β 1 R mt + ε 1t ; R 2t = α 2 + β 2 R mt + ε 2t ; : R mt = α n + β n R mt + ε 3t. R t = α + βr mt + ε t, Black-version of CAPM implies H o : (e N -β)γ = α. See CLM for how to test this hypothesis. ASSE PRICING-7

8 (3) When returns are heteroskedastic or autocorrelated over time. Estimate the parameters by GMM. Moment conditions: 1 E ( Xit αi βixmt = 0, i = 1,..., N X ) mt 1 E ( Xt α βxmt) = 0. X mt ASSE PRICING-8

9 [2] Multifactor Pricing Model (1) Arbitrage Pricing Model [Ross, JE, 1976] Assumption 1: R it = α i + β i1 f 1t + β i2 f 2t β ik f kt + ε it, where f 1t,... f kt are macroeconomic or portfolio factors. R t = α + β 1 f 1t β k f kt + ε t = α + Bf t + ε t, where B = (β 1,..., β k ) and f t = (f 1t,..., f kt ). Cov(ε t ) = Σ N N (ε it are cross-sectionally correlated). If there is no missing factor, Σ should be diagonal. R t and f t are covariance-stationary and ergodic. he factors in f t are strictly exogeous: E(f s ε it ) = 0 for all i = 1,..., N, and all t and s. E( f ε ) = 0. s t he beta matrix B is of full column. How could we test for rank(b)? What happens if B is not full column? [See below.] Assumption 2 (No Autocorrelation): Assumption 1 plus εε t s,..., = 0N N. E( f1 f ) ASSE PRICING-9

10 Assumption 3 (No Heteroskedasticity): Assumption 2 plus t 1 Cov( ε f,..., f ) =Σ, for all t. Assumption 4 (Autocorrelation in f t ): Let Σ ˆ F be the Newey-West estimator of 1 lim Var Σt= 1( ft E( ft))( ft E( ft )) Assumption 5 (No Autocorrelation in f t ): ˆ 1 Σ F = Σt= 1( ft f )( ft f ) 1 p lim Var Σ t= 1( ft E( ft))( ft E( ft)) Ross (1976) shows that the absence of arbitrage implies: γ 0 Ho: ER ( t) = enγ 0 + Bγ1 = ( en, B) Bcγ γ. Or equivalently, 1 α o : N o 1 H α = e λ + Bλ = B λ, where λ 1 = γ 1 E(f t ). c ASSE PRICING-10

11 (2) Estimation and esting [Ahn and Gadarowski, 2004] Let Z = (1, f ). t t 1 Let Ξ= lim Var Σt= 1Zt ε t. Let ˆΞ 1 be the Newey-West estimator of Ξ using OLS residuals instead of ε t. hen, it is consistent under Assumption 1. Under Assumption 2, ( ZZ εε ) ˆ 1 Ξ2 Σt= 1 t t t t p Ξ. Under Assumption 3, ˆ 1 1 Ξ ˆ ˆ 3 Σt 1ZZ = t t Σt= 1εε t t ZZ Σ p Ξ. ASSE PRICING-11

12 wo-pass Estimation of lambdas: Let Λ= ˆ ( ˆ α, B ˆ ) be the OLS estimator of α and B. Let A be any N N positive definite matrix. hen, a two-pass estimator of γ is given: ˆ γ ( B AB ) 1 = ˆ ˆ Bˆ Aˆ α. P c c c If A = I N, the P estimator is the Fama-MacBeth estimator. Cov( ˆ γ ) ˆ ˆ ˆ ( ) ˆ ˆ ˆ ˆ P B c ABc B c A ABc ( B c ABc ) where 1 1 = Ω, ˆ ˆ ˆ ˆ ˆ 1 1 Ω= ( λ* ZZ I N) Ξ( ZZλ* I N), * is any consistent estimator of λ 1. Asymptotically optimal choice of A = ( Ω ˆ ) 1. ˆ ˆ λ = (1, ˆ λ 1 ), and ˆ λ 1 λ be the optimal P estimator using ( ˆ ) 1 Let ˆOMD Ω. Estimation of gammas: ˆ λ 1 0, ˆ ( ˆ ) ˆ ˆ P γp = B c ABc B c AR = λp + Jf =, ˆ λ1, P + f where J 01 k = I. k ASSE PRICING-12

13 Under Assumption 4, ˆ 1 Cov( ˆ γ ) ( ) ˆ P = Cov λ P + JΣ J. F Under Assumption 5, ˆ 1 Cov( ˆ γ ) ( ) ˆ P = Cov λ P + JΣ F J. Model Specification test: 2 N + 1 ˆ 1 ˆ ˆ ( Q ( ˆ OMD Bc OMD Bc OMD) N k χ 1 ) α λ Ω α λ. N 1 k N 1 k ( ˆ ˆ ˆ ) Alternative test: Assume: α = e λ + Bλ + Sλ, N where S contains firsm specific variables such as firm sizes or book values. H o and H α o imply λ 2 = 0. For detailed test procedures, see Ahn and Gadarowski. ASSE PRICING-13

14 Empirical Suggestions from Ahn and Gadarowski Need to check persistency of factors. When factors follow unit root or near-unit-root processes, the P estimators are unreliable. Do not use too many assets (N). 25 or fewer would be appropriate. esting autocorrelation in time-series OLS residuals and factors are important. Heteroskedasticity-robust Q tests are more reliable than autocorrelation-robust Q tests. he Q tests generally have low power. he t-tests based on nonoptimal P estimators are more reliable than those based on the optimal P estimators. (3) What happens if the beta matrix B is not of full column? When? Some factors are in fact not the determinants of returns. Kan and Zhang (1999, JF) call such factors useless factors. he columns of B corresponding to useless factors are zero vectors. rank(b) < k. ASSE PRICING-14

15 Consequences? he P estimator is severely biased. he price of a useless factor would appear to be significant. How to find out correct factors? Conner and Korajczyk (1993, JF) What happens if some unimportant factors are used? he P estimators are severely biased. [Kan and Zhang, 1999, JF] Important to test how many factors to be used. How many factors to be used? When candidate factors are all observed: Connor and Korajczyk (1993, JF). Jagannathan and Wang (1996, JF). ASSE PRICING-15

16 [3] Estimating the Number of Factors Question: Suppose we do not observe factors. Wish to estimate factors. How may factors? Methods: MLE assuming factors are iid standard normal over time: Large and Small N. [See Campbell, Ch. 6.4]. Jones (2001, JFE): Large N and small. Bai (2003, ECON), and Bai and Ng: Both N and are large. Chi, Nardari and Shephard (2002, JEC): N small and large. ASSE PRICING-16

17 [4] Stochastic Discount Factor Model here are many asset pricing models (CAPM, AP, consumptionbased CAPM, intertemporal equilibrium model): See Ch. 8 of CLM. A particular asset pricing model typically implies: E[R t m t (f t δ)] = e N, where m(f t δ) is a scalar function of factors and a parameter vector δ, e N is the normalized price vector, and m(f t δ) is called stochastic discount factor (SDF). For linear factor models, m(f t δ) = δ 1 + f t δ 2, where δ = (δ 1,δ 2 ). he parameter vector δ and model specification can be tested by GMM. (1) Jagannathan and Wang (1996, JF): Let w t (δ) = R t m t (δ) e N ; then, E[w t (δ)] is the pricing error. If no pricing error, then, E[w t (δ)] = 0 N 1. HJ-distance (Hansen and Jagannathan, 1997): 1 HJ ( δ ) = E[ wt( δ)] G E( w t ( δ )), where G = E(R t R t ). Correct model has HJ(δ) = 0. For a given δ, this measure equals the maximum pricing error generated by a given asset pricing model. ASSE PRICING-17

18 Standard GMM test for no pricing error: 1 Let S be a consistent estimator of lim Cov Σt= 1wt( δ ). [by White (1980) or Newey and West (1987).] Let ˆ δ GMM be the optimal GMM estimator. hen, under the hypothesis of no pricing error, J = w ˆ S w ˆ N p, 1 2 ( δ ) GMM ( δgmm) d χ ( ) 1 where w ( δ ) = Σ t = 1w t ( δ ), and p is the # of parameters in δ. Jagannathan-Wang test: 1 HJ ( δ ) = w ( δ) G w ( δ). Let ˆHJ δ is the minimizer of HJ (δ). Under the hypothesis of no pricing error, SHJ [ HJ ( ˆ δ )] 2 = HJ weighted χ JW (1996) provides a simulation method to compute p-value for this statistic. JW conjecture that this HJ test would have better finite sample properties, because non-optimal GMM often has better finite sample properties than optimal GMM. 2. ASSE PRICING-18

19 Ahn and Gadarowski (2004, Journal of Empirical Finance) For linear factor models, the JW method has extremely poor finite sample properties, poorer than optimal GMM, especially when N is large. Better to use optimal GMM! ASSE PRICING-19

Financial Econometrics Lecture 6: Testing the CAPM model

Financial Econometrics Lecture 6: Testing the CAPM model Financial Econometrics Lecture 6: Testing the CAPM model Richard G. Pierse 1 Introduction The capital asset pricing model has some strong implications which are testable. The restrictions that can be tested

More information

Specification Test Based on the Hansen-Jagannathan Distance with Good Small Sample Properties

Specification Test Based on the Hansen-Jagannathan Distance with Good Small Sample Properties Specification Test Based on the Hansen-Jagannathan Distance with Good Small Sample Properties Yu Ren Department of Economics Queen s University Katsumi Shimotsu Department of Economics Queen s University

More information

R = µ + Bf Arbitrage Pricing Model, APM

R = µ + Bf Arbitrage Pricing Model, APM 4.2 Arbitrage Pricing Model, APM Empirical evidence indicates that the CAPM beta does not completely explain the cross section of expected asset returns. This suggests that additional factors may be required.

More information

Ross (1976) introduced the Arbitrage Pricing Theory (APT) as an alternative to the CAPM.

Ross (1976) introduced the Arbitrage Pricing Theory (APT) as an alternative to the CAPM. 4.2 Arbitrage Pricing Model, APM Empirical evidence indicates that the CAPM beta does not completely explain the cross section of expected asset returns. This suggests that additional factors may be required.

More information

Lecture Notes in Empirical Finance (PhD): Linear Factor Models

Lecture Notes in Empirical Finance (PhD): Linear Factor Models Contents Lecture Notes in Empirical Finance (PhD): Linear Factor Models Paul Söderlind 8 June 26 University of St Gallen Address: s/bf-hsg, Rosenbergstrasse 52, CH-9 St Gallen, Switzerland E-mail: PaulSoderlind@unisgch

More information

Factor Models for Asset Returns. Prof. Daniel P. Palomar

Factor Models for Asset Returns. Prof. Daniel P. Palomar Factor Models for Asset Returns Prof. Daniel P. Palomar The Hong Kong University of Science and Technology (HKUST) MAFS6010R- Portfolio Optimization with R MSc in Financial Mathematics Fall 2018-19, HKUST,

More information

Improvement in Finite Sample Properties of the. Hansen-Jagannathan Distance Test

Improvement in Finite Sample Properties of the. Hansen-Jagannathan Distance Test Improvement in Finite Sample Properties of the Hansen-Jagannathan Distance Test Yu Ren Katsumi Shimotsu March 21, 2007 The authors thank Christopher Gadarowski for providing the dataset for calibrating

More information

An Introduction to Generalized Method of Moments. Chen,Rong aronge.net

An Introduction to Generalized Method of Moments. Chen,Rong   aronge.net An Introduction to Generalized Method of Moments Chen,Rong http:// aronge.net Asset Pricing, 2012 Section 1 WHY GMM? 2 Empirical Studies 3 Econometric Estimation Strategies 4 5 Maximum Likelihood Estimation

More information

Multivariate Tests of the CAPM under Normality

Multivariate Tests of the CAPM under Normality Multivariate Tests of the CAPM under Normality Bernt Arne Ødegaard 6 June 018 Contents 1 Multivariate Tests of the CAPM 1 The Gibbons (198) paper, how to formulate the multivariate model 1 3 Multivariate

More information

Financial Econometrics Return Predictability

Financial Econometrics Return Predictability Financial Econometrics Return Predictability Eric Zivot March 30, 2011 Lecture Outline Market Efficiency The Forms of the Random Walk Hypothesis Testing the Random Walk Hypothesis Reading FMUND, chapter

More information

Multivariate GARCH models.

Multivariate GARCH models. Multivariate GARCH models. Financial market volatility moves together over time across assets and markets. Recognizing this commonality through a multivariate modeling framework leads to obvious gains

More information

Testing the APT with the Maximum Sharpe. Ratio of Extracted Factors

Testing the APT with the Maximum Sharpe. Ratio of Extracted Factors Testing the APT with the Maximum Sharpe Ratio of Extracted Factors Chu Zhang This version: April, 2008 Abstract. This paper develops a test of the asymptotic arbitrage pricing theory (APT) via the maximum

More information

Model Mis-specification

Model Mis-specification Model Mis-specification Carlo Favero Favero () Model Mis-specification 1 / 28 Model Mis-specification Each specification can be interpreted of the result of a reduction process, what happens if the reduction

More information

Chapter 11 GMM: General Formulas and Application

Chapter 11 GMM: General Formulas and Application Chapter 11 GMM: General Formulas and Application Main Content General GMM Formulas esting Moments Standard Errors of Anything by Delta Method Using GMM for Regressions Prespecified weighting Matrices and

More information

Econ671 Factor Models: Principal Components

Econ671 Factor Models: Principal Components Econ671 Factor Models: Principal Components Jun YU April 8, 2016 Jun YU () Econ671 Factor Models: Principal Components April 8, 2016 1 / 59 Factor Models: Principal Components Learning Objectives 1. Show

More information

Errata for Campbell, Financial Decisions and Markets, 01/02/2019.

Errata for Campbell, Financial Decisions and Markets, 01/02/2019. Errata for Campbell, Financial Decisions and Markets, 01/02/2019. Page xi, section title for Section 11.4.3 should be Endogenous Margin Requirements. Page 20, equation 1.49), expectations operator E should

More information

GARCH Models. Eduardo Rossi University of Pavia. December Rossi GARCH Financial Econometrics / 50

GARCH Models. Eduardo Rossi University of Pavia. December Rossi GARCH Financial Econometrics / 50 GARCH Models Eduardo Rossi University of Pavia December 013 Rossi GARCH Financial Econometrics - 013 1 / 50 Outline 1 Stylized Facts ARCH model: definition 3 GARCH model 4 EGARCH 5 Asymmetric Models 6

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

Empirical Methods in Finance Section 2 - The CAPM Model

Empirical Methods in Finance Section 2 - The CAPM Model Empirical Methods in Finance Section 2 - The CAPM Model René Garcia Professor of finance EDHEC Nice, March 2010 Estimation and Testing The CAPM model is a one-period model E [Z i ] = β im E [Z m] with

More information

Heteroscedasticity and Autocorrelation

Heteroscedasticity and Autocorrelation Heteroscedasticity and Autocorrelation Carlo Favero Favero () Heteroscedasticity and Autocorrelation 1 / 17 Heteroscedasticity, Autocorrelation, and the GLS estimator Let us reconsider the single equation

More information

Lecture 4: Heteroskedasticity

Lecture 4: Heteroskedasticity Lecture 4: Heteroskedasticity Econometric Methods Warsaw School of Economics (4) Heteroskedasticity 1 / 24 Outline 1 What is heteroskedasticity? 2 Testing for heteroskedasticity White Goldfeld-Quandt Breusch-Pagan

More information

MFE Financial Econometrics 2018 Final Exam Model Solutions

MFE Financial Econometrics 2018 Final Exam Model Solutions MFE Financial Econometrics 2018 Final Exam Model Solutions Tuesday 12 th March, 2019 1. If (X, ε) N (0, I 2 ) what is the distribution of Y = µ + β X + ε? Y N ( µ, β 2 + 1 ) 2. What is the Cramer-Rao lower

More information

Chapter 15 Panel Data Models. Pooling Time-Series and Cross-Section Data

Chapter 15 Panel Data Models. Pooling Time-Series and Cross-Section Data Chapter 5 Panel Data Models Pooling Time-Series and Cross-Section Data Sets of Regression Equations The topic can be introduced wh an example. A data set has 0 years of time series data (from 935 to 954)

More information

Financial Econometrics Short Course Lecture 3 Multifactor Pricing Model

Financial Econometrics Short Course Lecture 3 Multifactor Pricing Model Financial Econometrics Short Course Lecture 3 Multifactor Pricing Model Oliver Linton obl20@cam.ac.uk Renmin University Financial Econometrics Short Course Lecture 3 MultifactorRenmin Pricing University

More information

ORTHOGONALITY TESTS IN LINEAR MODELS SEUNG CHAN AHN ARIZONA STATE UNIVERSITY ABSTRACT

ORTHOGONALITY TESTS IN LINEAR MODELS SEUNG CHAN AHN ARIZONA STATE UNIVERSITY ABSTRACT ORTHOGONALITY TESTS IN LINEAR MODELS SEUNG CHAN AHN ARIZONA STATE UNIVERSITY ABSTRACT This paper considers several tests of orthogonality conditions in linear models where stochastic errors may be heteroskedastic

More information

GMM - Generalized method of moments

GMM - Generalized method of moments GMM - Generalized method of moments GMM Intuition: Matching moments You want to estimate properties of a data set {x t } T t=1. You assume that x t has a constant mean and variance. x t (µ 0, σ 2 ) Consider

More information

This paper develops a test of the asymptotic arbitrage pricing theory (APT) via the maximum squared Sharpe

This paper develops a test of the asymptotic arbitrage pricing theory (APT) via the maximum squared Sharpe MANAGEMENT SCIENCE Vol. 55, No. 7, July 2009, pp. 1255 1266 issn 0025-1909 eissn 1526-5501 09 5507 1255 informs doi 10.1287/mnsc.1090.1004 2009 INFORMS Testing the APT with the Maximum Sharpe Ratio of

More information

Inference on Risk Premia in the Presence of Omitted Factors

Inference on Risk Premia in the Presence of Omitted Factors Inference on Risk Premia in the Presence of Omitted Factors Stefano Giglio Dacheng Xiu Booth School of Business, University of Chicago Center for Financial and Risk Analytics Stanford University May 19,

More information

Drawing Inferences from Statistics Based on Multiyear Asset Returns

Drawing Inferences from Statistics Based on Multiyear Asset Returns Drawing Inferences from Statistics Based on Multiyear Asset Returns Matthew Richardson ames H. Stock FE 1989 1 Motivation Fama and French (1988, Poterba and Summer (1988 document significant negative correlations

More information

Generalized Method Of Moments (GMM)

Generalized Method Of Moments (GMM) Chapter 6 Generalized Method Of Moments GMM) Note: The primary reference text for these notes is Hall 005). Alternative, but less comprehensive, treatments can be found in chapter 14 of Hamilton 1994)

More information

7. GENERALIZED LEAST SQUARES (GLS)

7. GENERALIZED LEAST SQUARES (GLS) 7. GENERALIZED LEAST SQUARES (GLS) [1] ASSUMPTIONS: Assume SIC except that Cov(ε) = E(εε ) = σ Ω where Ω I T. Assume that E(ε) = 0 T 1, and that X Ω -1 X and X ΩX are all positive definite. Examples: Autocorrelation:

More information

Asset Pricing with Consumption and Robust Inference

Asset Pricing with Consumption and Robust Inference Asset Pricing with Consumption and Robust Inference Frank Kleibergen Zhaoguo Zhan January 9, 28 Abstract Alongside the National Income and Product Accounts (NIPA), we consider four consumption measures

More information

II.2. Empirical Testing for Asset Pricing Models. 2.1 The Capital Asset Pricing Model, CAPM

II.2. Empirical Testing for Asset Pricing Models. 2.1 The Capital Asset Pricing Model, CAPM II.2. Empirical Testing for Asset Pricing Models 2.1 The Capital Asset Pricing Model, CAPM Roots of CAPM are in the Markowitz (mean variance) portfolio theory in the 1950 s. CAPM is credited to Sharpe,

More information

A Non-Parametric Approach of Heteroskedasticity Robust Estimation of Vector-Autoregressive (VAR) Models

A Non-Parametric Approach of Heteroskedasticity Robust Estimation of Vector-Autoregressive (VAR) Models Journal of Finance and Investment Analysis, vol.1, no.1, 2012, 55-67 ISSN: 2241-0988 (print version), 2241-0996 (online) International Scientific Press, 2012 A Non-Parametric Approach of Heteroskedasticity

More information

Economics 582 Random Effects Estimation

Economics 582 Random Effects Estimation Economics 582 Random Effects Estimation Eric Zivot May 29, 2013 Random Effects Model Hence, the model can be re-written as = x 0 β + + [x ] = 0 (no endogeneity) [ x ] = = + x 0 β + + [x ] = 0 [ x ] = 0

More information

14 Week 5 Empirical methods notes

14 Week 5 Empirical methods notes 14 Week 5 Empirical methods notes 1. Motivation and overview 2. Time series regressions 3. Cross sectional regressions 4. Fama MacBeth 5. Testing factor models. 14.1 Motivation and Overview 1. Expected

More information

9. AUTOCORRELATION. [1] Definition of Autocorrelation (AUTO) 1) Model: y t = x t β + ε t. We say that AUTO exists if cov(ε t,ε s ) 0, t s.

9. AUTOCORRELATION. [1] Definition of Autocorrelation (AUTO) 1) Model: y t = x t β + ε t. We say that AUTO exists if cov(ε t,ε s ) 0, t s. 9. AUTOCORRELATION [1] Definition of Autocorrelation (AUTO) 1) Model: y t = x t β + ε t. We say that AUTO exists if cov(ε t,ε s ) 0, t s. ) Assumptions: All of SIC except SIC.3 (the random sample assumption).

More information

Network Connectivity and Systematic Risk

Network Connectivity and Systematic Risk Network Connectivity and Systematic Risk Monica Billio 1 Massimiliano Caporin 2 Roberto Panzica 3 Loriana Pelizzon 1,3 1 University Ca Foscari Venezia (Italy) 2 University of Padova (Italy) 3 Goethe University

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

Notes on empirical methods

Notes on empirical methods Notes on empirical methods Statistics of time series and cross sectional regressions 1. Time Series Regression (Fama-French). (a) Method: Run and interpret (b) Estimates: 1. ˆα, ˆβ : OLS TS regression.

More information

Using Bootstrap to Test Portfolio Efficiency *

Using Bootstrap to Test Portfolio Efficiency * ANNALS OF ECONOMICS AND FINANCE 2, 217 249 (2006) Using Bootstrap to est Portfolio Efficiency * Pin-Huang Chou National Central University, aiwan E-mail: choup@cc.ncu.edu.tw and Guofu Zhou Washington University

More information

Heteroskedasticity. y i = β 0 + β 1 x 1i + β 2 x 2i β k x ki + e i. where E(e i. ) σ 2, non-constant variance.

Heteroskedasticity. y i = β 0 + β 1 x 1i + β 2 x 2i β k x ki + e i. where E(e i. ) σ 2, non-constant variance. Heteroskedasticity y i = β + β x i + β x i +... + β k x ki + e i where E(e i ) σ, non-constant variance. Common problem with samples over individuals. ê i e ˆi x k x k AREC-ECON 535 Lec F Suppose y i =

More information

ZHAW Zurich University of Applied Sciences. Bachelor s Thesis Estimating Multi-Beta Pricing Models With or Without an Intercept:

ZHAW Zurich University of Applied Sciences. Bachelor s Thesis Estimating Multi-Beta Pricing Models With or Without an Intercept: ZHAW Zurich University of Applied Sciences School of Management and Law Bachelor s Thesis Estimating Multi-Beta Pricing Models With or Without an Intercept: Further Results from Simulations Submitted by:

More information

Linear Factor Models and the Estimation of Expected Returns

Linear Factor Models and the Estimation of Expected Returns Linear Factor Models and the Estimation of Expected Returns Cisil Sarisoy, Peter de Goeij and Bas Werker DP 03/2016-020 Linear Factor Models and the Estimation of Expected Returns Cisil Sarisoy a,, Peter

More information

Linear Factor Models and the Estimation of Expected Returns

Linear Factor Models and the Estimation of Expected Returns Linear Factor Models and the Estimation of Expected Returns Cisil Sarisoy a,, Peter de Goeij b, Bas J.M. Werker c a Department of Finance, CentER, Tilburg University b Department of Finance, Tilburg University

More information

Linear Factor Models and the Estimation of Expected Returns

Linear Factor Models and the Estimation of Expected Returns Linear Factor Models and the Estimation of Expected Returns Abstract Standard factor models in asset pricing imply a linear relationship between expected returns on assets and their exposures to one or

More information

Tests for Differing Sensitivity Among Asset Returns

Tests for Differing Sensitivity Among Asset Returns Southern Illinois University Carbondale OpenSIUC Discussion Papers Department of Economics 2002 Tests for Differing Sensitivity Among Asset Returns Scott Gilbert Southern Illinois University Carbondale

More information

Volume 30, Issue 1. Measuring the Intertemporal Elasticity of Substitution for Consumption: Some Evidence from Japan

Volume 30, Issue 1. Measuring the Intertemporal Elasticity of Substitution for Consumption: Some Evidence from Japan Volume 30, Issue 1 Measuring the Intertemporal Elasticity of Substitution for Consumption: Some Evidence from Japan Akihiko Noda Graduate School of Business and Commerce, Keio University Shunsuke Sugiyama

More information

Pricing Model Performance and the Two-Pass Cross-Sectional Regression Methodology

Pricing Model Performance and the Two-Pass Cross-Sectional Regression Methodology Pricing Model Performance and the Two-Pass Cross-Sectional Regression Methodology Raymond Kan, Cesare Robotti, and Jay Shanken First draft: April 2008 This version: February 2009 Kan is from the University

More information

An estimate of the long-run covariance matrix, Ω, is necessary to calculate asymptotic

An estimate of the long-run covariance matrix, Ω, is necessary to calculate asymptotic Chapter 6 ESTIMATION OF THE LONG-RUN COVARIANCE MATRIX An estimate of the long-run covariance matrix, Ω, is necessary to calculate asymptotic standard errors for the OLS and linear IV estimators presented

More information

Generalized Method of Moment

Generalized Method of Moment Generalized Method of Moment CHUNG-MING KUAN Department of Finance & CRETA National Taiwan University June 16, 2010 C.-M. Kuan (Finance & CRETA, NTU Generalized Method of Moment June 16, 2010 1 / 32 Lecture

More information

The Slow Convergence of OLS Estimators of α, β and Portfolio. β and Portfolio Weights under Long Memory Stochastic Volatility

The Slow Convergence of OLS Estimators of α, β and Portfolio. β and Portfolio Weights under Long Memory Stochastic Volatility The Slow Convergence of OLS Estimators of α, β and Portfolio Weights under Long Memory Stochastic Volatility New York University Stern School of Business June 21, 2018 Introduction Bivariate long memory

More information

Volatility. Gerald P. Dwyer. February Clemson University

Volatility. Gerald P. Dwyer. February Clemson University Volatility Gerald P. Dwyer Clemson University February 2016 Outline 1 Volatility Characteristics of Time Series Heteroskedasticity Simpler Estimation Strategies Exponentially Weighted Moving Average Use

More information

Unexplained factors and their effects on second pass R-squared s

Unexplained factors and their effects on second pass R-squared s Unexplained factors and their effects on second pass R-squared s Frank Kleibergen Zhaoguo Zhan November 6, 14 Abstract We construct the large sample distributions of the OLS and GLS R s of the second pass

More information

Motivation Non-linear Rational Expectations The Permanent Income Hypothesis The Log of Gravity Non-linear IV Estimation Summary.

Motivation Non-linear Rational Expectations The Permanent Income Hypothesis The Log of Gravity Non-linear IV Estimation Summary. Econometrics I Department of Economics Universidad Carlos III de Madrid Master in Industrial Economics and Markets Outline Motivation 1 Motivation 2 3 4 5 Motivation Hansen's contributions GMM was developed

More information

Lecture 6: Recursive Preferences

Lecture 6: Recursive Preferences Lecture 6: Recursive Preferences Simon Gilchrist Boston Univerity and NBER EC 745 Fall, 2013 Basics Epstein and Zin (1989 JPE, 1991 Ecta) following work by Kreps and Porteus introduced a class of preferences

More information

Econ 424 Time Series Concepts

Econ 424 Time Series Concepts Econ 424 Time Series Concepts Eric Zivot January 20 2015 Time Series Processes Stochastic (Random) Process { 1 2 +1 } = { } = sequence of random variables indexed by time Observed time series of length

More information

Econ 583 Final Exam Fall 2008

Econ 583 Final Exam Fall 2008 Econ 583 Final Exam Fall 2008 Eric Zivot December 11, 2008 Exam is due at 9:00 am in my office on Friday, December 12. 1 Maximum Likelihood Estimation and Asymptotic Theory Let X 1,...,X n be iid random

More information

APT looking for the factors

APT looking for the factors APT looking for the factors February 5, 2018 Contents 1 the Arbitrage Pricing Theory 2 1.1 One factor models............................................... 2 1.2 2 factor models.................................................

More information

Identifying Financial Risk Factors

Identifying Financial Risk Factors Identifying Financial Risk Factors with a Low-Rank Sparse Decomposition Lisa Goldberg Alex Shkolnik Berkeley Columbia Meeting in Engineering and Statistics 24 March 2016 Outline 1 A Brief History of Factor

More information

Heteroskedasticity- and Autocorrelation-Robust Inference or Three Decades of HAC and HAR: What Have We Learned?

Heteroskedasticity- and Autocorrelation-Robust Inference or Three Decades of HAC and HAR: What Have We Learned? AEA Continuing Education Course ime Series Econometrics Lecture 4 Heteroskedasticity- and Autocorrelation-Robust Inference or hree Decades of HAC and HAR: What Have We Learned? James H. Stock Harvard University

More information

A Test of APT with Maximum Sharpe Ratio

A Test of APT with Maximum Sharpe Ratio A Test of APT with Maximum Sharpe Ratio CHU ZHANG This version: January, 2006 Department of Finance, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong (phone: 852-2358-7684,

More information

Unexplained factors and their effects on second pass R-squared's and t-tests Kleibergen, F.R.; Zhan, Z.

Unexplained factors and their effects on second pass R-squared's and t-tests Kleibergen, F.R.; Zhan, Z. UvA-DARE (Digital Academic Repository) Unexplained factors and their effects on second pass R-squared's and t-tests Kleibergen, F.R.; Zhan, Z. Link to publication Citation for published version (APA):

More information

Interpreting Regression Results

Interpreting Regression Results Interpreting Regression Results Carlo Favero Favero () Interpreting Regression Results 1 / 42 Interpreting Regression Results Interpreting regression results is not a simple exercise. We propose to split

More information

Peter S. Karlsson Jönköping University SE Jönköping Sweden

Peter S. Karlsson Jönköping University SE Jönköping Sweden Peter S. Karlsson Jönköping University SE-55 Jönköping Sweden Abstract: The Arbitrage Pricing Theory provides a theory to quantify risk and the reward for taking it. While the theory itself is sound from

More information

A Guide to Modern Econometric:

A Guide to Modern Econometric: A Guide to Modern Econometric: 4th edition Marno Verbeek Rotterdam School of Management, Erasmus University, Rotterdam B 379887 )WILEY A John Wiley & Sons, Ltd., Publication Contents Preface xiii 1 Introduction

More information

Theory and Applications of High Dimensional Covariance Matrix Estimation

Theory and Applications of High Dimensional Covariance Matrix Estimation 1 / 44 Theory and Applications of High Dimensional Covariance Matrix Estimation Yuan Liao Princeton University Joint work with Jianqing Fan and Martina Mincheva December 14, 2011 2 / 44 Outline 1 Applications

More information

ECON 4551 Econometrics II Memorial University of Newfoundland. Panel Data Models. Adapted from Vera Tabakova s notes

ECON 4551 Econometrics II Memorial University of Newfoundland. Panel Data Models. Adapted from Vera Tabakova s notes ECON 4551 Econometrics II Memorial University of Newfoundland Panel Data Models Adapted from Vera Tabakova s notes 15.1 Grunfeld s Investment Data 15.2 Sets of Regression Equations 15.3 Seemingly Unrelated

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

Econometrics of Panel Data

Econometrics of Panel Data Econometrics of Panel Data Jakub Mućk Meeting # 2 Jakub Mućk Econometrics of Panel Data Meeting # 2 1 / 26 Outline 1 Fixed effects model The Least Squares Dummy Variable Estimator The Fixed Effect (Within

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

Chapter 2. Dynamic panel data models

Chapter 2. Dynamic panel data models Chapter 2. Dynamic panel data models School of Economics and Management - University of Geneva Christophe Hurlin, Université of Orléans University of Orléans April 2018 C. Hurlin (University of Orléans)

More information

Econ 423 Lecture Notes: Additional Topics in Time Series 1

Econ 423 Lecture Notes: Additional Topics in Time Series 1 Econ 423 Lecture Notes: Additional Topics in Time Series 1 John C. Chao April 25, 2017 1 These notes are based in large part on Chapter 16 of Stock and Watson (2011). They are for instructional purposes

More information

Misspecification-Robust Inference in Linear Asset-Pricing Models with Irrelevant Risk Factors

Misspecification-Robust Inference in Linear Asset-Pricing Models with Irrelevant Risk Factors Misspecification-Robust Inference in Linear Asset-Pricing Models with Irrelevant Risk Factors Nikolay Gospodinov Federal Reserve Bank of Atlanta Raymond Kan University of Toronto Cesare Robotti Imperial

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

Chapter 2: Unit Roots

Chapter 2: Unit Roots Chapter 2: Unit Roots 1 Contents: Lehrstuhl für Department Empirische of Wirtschaftsforschung Empirical Research and undeconometrics II. Unit Roots... 3 II.1 Integration Level... 3 II.2 Nonstationarity

More information

Regression with time series

Regression with time series Regression with time series Class Notes Manuel Arellano February 22, 2018 1 Classical regression model with time series Model and assumptions The basic assumption is E y t x 1,, x T = E y t x t = x tβ

More information

Generalized Method of Moments Estimation

Generalized Method of Moments Estimation Generalized Method of Moments Estimation Lars Peter Hansen March 0, 2007 Introduction Generalized methods of moments (GMM) refers to a class of estimators which are constructed from exploiting the sample

More information

Prof. Dr. Roland Füss Lecture Series in Applied Econometrics Summer Term Introduction to Time Series Analysis

Prof. Dr. Roland Füss Lecture Series in Applied Econometrics Summer Term Introduction to Time Series Analysis Introduction to Time Series Analysis 1 Contents: I. Basics of Time Series Analysis... 4 I.1 Stationarity... 5 I.2 Autocorrelation Function... 9 I.3 Partial Autocorrelation Function (PACF)... 14 I.4 Transformation

More information

Empirical Asset Pricing and Statistical Power in the Presence of Weak Risk Factors

Empirical Asset Pricing and Statistical Power in the Presence of Weak Risk Factors Empirical Asset Pricing and Statistical Power in the Presence of Weak Risk Factors Craig Burnside y Duke University August 27 Abstract The risk factors in many consumption-based asset pricing models display

More information

Econ 582 Fixed Effects Estimation of Panel Data

Econ 582 Fixed Effects Estimation of Panel Data Econ 582 Fixed Effects Estimation of Panel Data Eric Zivot May 28, 2012 Panel Data Framework = x 0 β + = 1 (individuals); =1 (time periods) y 1 = X β ( ) ( 1) + ε Main question: Is x uncorrelated with?

More information

Using all observations when forecasting under structural breaks

Using all observations when forecasting under structural breaks Using all observations when forecasting under structural breaks Stanislav Anatolyev New Economic School Victor Kitov Moscow State University December 2007 Abstract We extend the idea of the trade-off window

More information

Network Connectivity, Systematic Risk and Diversification

Network Connectivity, Systematic Risk and Diversification Network Connectivity, Systematic Risk and Diversification Monica Billio 1 Massimiliano Caporin 2 Roberto Panzica 3 Loriana Pelizzon 1,3 1 University Ca Foscari Venezia (Italy) 2 University of Padova (Italy)

More information

Asset Pricing. Chapter IX. The Consumption Capital Asset Pricing Model. June 20, 2006

Asset Pricing. Chapter IX. The Consumption Capital Asset Pricing Model. June 20, 2006 Chapter IX. The Consumption Capital Model June 20, 2006 The Representative Agent Hypothesis and its Notion of Equilibrium 9.2.1 An infinitely lived Representative Agent Avoid terminal period problem Equivalence

More information

Econometrics of Panel Data

Econometrics of Panel Data Econometrics of Panel Data Jakub Mućk Meeting # 3 Jakub Mućk Econometrics of Panel Data Meeting # 3 1 / 21 Outline 1 Fixed or Random Hausman Test 2 Between Estimator 3 Coefficient of determination (R 2

More information

GMM Tests of Stochastic Discount Factor Models with Useless Factors 1

GMM Tests of Stochastic Discount Factor Models with Useless Factors 1 Journal of Financial Economics 00 (1999) 000 000 GMM ests of Stochastic Discount Factor Models with Useless Factors 1 Raymond Kan a, Chu Zhang b,c,* a Joseph L. Rotman School of Management, University

More information

GMM, HAC estimators, & Standard Errors for Business Cycle Statistics

GMM, HAC estimators, & Standard Errors for Business Cycle Statistics GMM, HAC estimators, & Standard Errors for Business Cycle Statistics Wouter J. Den Haan London School of Economics c Wouter J. Den Haan Overview Generic GMM problem Estimation Heteroskedastic and Autocorrelation

More information

Generalized Method of Moments: I. Chapter 9, R. Davidson and J.G. MacKinnon, Econometric Theory and Methods, 2004, Oxford.

Generalized Method of Moments: I. Chapter 9, R. Davidson and J.G. MacKinnon, Econometric Theory and Methods, 2004, Oxford. Generalized Method of Moments: I References Chapter 9, R. Davidson and J.G. MacKinnon, Econometric heory and Methods, 2004, Oxford. Chapter 5, B. E. Hansen, Econometrics, 2006. http://www.ssc.wisc.edu/~bhansen/notes/notes.htm

More information

Regression: Ordinary Least Squares

Regression: Ordinary Least Squares Regression: Ordinary Least Squares Mark Hendricks Autumn 2017 FINM Intro: Regression Outline Regression OLS Mathematics Linear Projection Hendricks, Autumn 2017 FINM Intro: Regression: Lecture 2/32 Regression

More information

Estimating Deep Parameters: GMM and SMM

Estimating Deep Parameters: GMM and SMM Estimating Deep Parameters: GMM and SMM 1 Parameterizing a Model Calibration Choose parameters from micro or other related macro studies (e.g. coeffi cient of relative risk aversion is 2). SMM with weighting

More information

2. IV ESTIMATION AND TWO STAGE LEAST SQUARES

2. IV ESTIMATION AND TWO STAGE LEAST SQUARES 2. IV ESTIMATION AND TWO STAGE LEAST SQUARES [1] Motivation (1) Consider a regression model: yt = β1+ β2xt2 +... + βkxtk + εt = xt β + εt. In what cases is the OLS estimator of β ( ˆ β ) consistent? E(x

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

The Forward Premium is Still a Puzzle Appendix

The Forward Premium is Still a Puzzle Appendix The Forward Premium is Still a Puzzle Appendix Craig Burnside June 211 Duke University and NBER. 1 Results Alluded to in the Main Text 1.1 First-Pass Estimates o Betas Table 1 provides rst-pass estimates

More information

Eksamen på Økonomistudiet 2006-II Econometrics 2 June 9, 2006

Eksamen på Økonomistudiet 2006-II Econometrics 2 June 9, 2006 Eksamen på Økonomistudiet 2006-II Econometrics 2 June 9, 2006 This is a four hours closed-book exam (uden hjælpemidler). Please answer all questions. As a guiding principle the questions 1 to 4 have equal

More information

Beta Is Alive, Well and Healthy

Beta Is Alive, Well and Healthy Beta Is Alive, Well and Healthy Soosung Hwang * Cass Business School, UK Abstract In this study I suggest some evidence that the popular cross-sectional asset pricing test proposed by Black, Jensen, and

More information

Heteroskedasticity and Autocorrelation Consistent Standard Errors

Heteroskedasticity and Autocorrelation Consistent Standard Errors NBER Summer Institute Minicourse What s New in Econometrics: ime Series Lecture 9 July 6, 008 Heteroskedasticity and Autocorrelation Consistent Standard Errors Lecture 9, July, 008 Outline. What are HAC

More information

Econometrics II - EXAM Answer each question in separate sheets in three hours

Econometrics II - EXAM Answer each question in separate sheets in three hours Econometrics II - EXAM Answer each question in separate sheets in three hours. Let u and u be jointly Gaussian and independent of z in all the equations. a Investigate the identification of the following

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

Inference on Risk Premia in the Presence of Omitted Factors

Inference on Risk Premia in the Presence of Omitted Factors Inference on Risk Premia in the Presence of Omitted Factors Stefano Giglio Yale School of Management NBER and CEPR Dacheng Xiu Booth School of Business University of Chicago First version: November 216

More information