Economics 672 Fall 2017 Tauchen. Jump Regression

Similar documents
Economics 883 Spring 2016 Tauchen. Jump Regression

Econometrics. Week 4. Fall Institute of Economic Studies Faculty of Social Sciences Charles University in Prague

ECON The Simple Regression Model

Lecture 4: Heteroskedasticity

Linear Regression with 1 Regressor. Introduction to Econometrics Spring 2012 Ken Simons

Simple Linear Regression: The Model

Discussion of Bootstrap prediction intervals for linear, nonlinear, and nonparametric autoregressions, by Li Pan and Dimitris Politis

Financial Econometrics Lecture 6: Testing the CAPM model

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

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.

the error term could vary over the observations, in ways that are related

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

The method of lines (MOL) for the diffusion equation

Chapter 2: simple regression model

Ordinary Least Squares Regression

A Course on Advanced Econometrics

Financial Econometrics

Lectures 5 & 6: Hypothesis Testing

Lecture 13. Simple Linear Regression

Introduction to Econometrics

Bayesian Inference for DSGE Models. Lawrence J. Christiano

Uniform Inference for Conditional Factor Models with. Instrumental and Idiosyncratic Betas

Econometrics of Panel Data

Bayesian Inference for DSGE Models. Lawrence J. Christiano

A nonparametric method of multi-step ahead forecasting in diffusion processes

Heteroskedasticity and Autocorrelation

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

E c o n o m e t r i c s

Notes on Random Variables, Expectations, Probability Densities, and Martingales

Understanding Regressions with Observations Collected at High Frequency over Long Span

Discrete Dependent Variable Models

EC212: Introduction to Econometrics Review Materials (Wooldridge, Appendix)

Introduction to Linear Regression Analysis

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

Lecture 12. Functional form

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

Adaptive Estimation of Continuous-Time Regression Models using High-Frequency Data

The multiple regression model; Indicator variables as regressors

Inference with Simple Regression

Brownian Motion. An Undergraduate Introduction to Financial Mathematics. J. Robert Buchanan. J. Robert Buchanan Brownian Motion

LECTURE 3 RANDOM VARIABLES, CUMULATIVE DISTRIBUTION FUNCTIONS (CDFs)

9) Time series econometrics

Lecture 8: Instrumental Variables Estimation

Limit theorems for multipower variation in the presence of jumps

Uniform Inference for Conditional Factor Models with Instrumental and Idiosyncratic Betas

1 A Non-technical Introduction to Regression

Ultra High Dimensional Variable Selection with Endogenous Variables

LECTURE 2: LOCAL TIME FOR BROWNIAN MOTION

Specification errors in linear regression models

1 Outline. 1. Motivation. 2. SUR model. 3. Simultaneous equations. 4. Estimation

Lecture 1: OLS derivations and inference

Stochastic Integration and Stochastic Differential Equations: a gentle introduction

Financial Econometrics

Lecture 4: Introduction to stochastic processes and stochastic calculus

Supplementary Appendix to Dynamic Asset Price Jumps: the Performance of High Frequency Tests and Measures, and the Robustness of Inference

Bayesian Inference for DSGE Models. Lawrence J. Christiano

Topic 7: Heteroskedasticity

Multivariate Tests of the CAPM under Normality

Heteroskedasticity. Part VII. Heteroskedasticity

Fixed Effects Models for Panel Data. December 1, 2014

Lecture 11 Roy model, MTE, PRTE

Econ671 Factor Models: Principal Components

Nonstationary Time Series:

Sequential Monte Carlo Methods for Bayesian Computation

Scatter plot of data from the study. Linear Regression

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

Missing dependent variables in panel data models

MATH20411 PDEs and Vector Calculus B

On detection of unit roots generalizing the classic Dickey-Fuller approach

PhD/MA Econometrics Examination. January, 2015 PART A. (Answer any TWO from Part A)

PANEL DATA RANDOM AND FIXED EFFECTS MODEL. Professor Menelaos Karanasos. December Panel Data (Institute) PANEL DATA December / 1

Terminology. Experiment = Prior = Posterior =

Econometric Forecasting

Lecture 3: Multiple Regression

Questions and Answers on Heteroskedasticity, Autocorrelation and Generalized Least Squares

EQUITY MARKET STABILITY

The regression model with one fixed regressor cont d

ECON4515 Finance theory 1 Diderik Lund, 5 May Perold: The CAPM

Bessel Functions Michael Taylor. Lecture Notes for Math 524

GMM - Generalized method of moments

Week 1 Quantitative Analysis of Financial Markets Distributions A

Econometrics I Lecture 3: The Simple Linear Regression Model

Scatter plot of data from the study. Linear Regression

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

Statistical Inference with Regression Analysis

Math 353 Lecture Notes Week 6 Laplace Transform: Fundamentals

Bayesian Heteroskedasticity-Robust Regression. Richard Startz * revised February Abstract

Empirical Macroeconomics

Inference For High Dimensional M-estimates: Fixed Design Results

The exact bias of S 2 in linear panel regressions with spatial autocorrelation SFB 823. Discussion Paper. Christoph Hanck, Walter Krämer

Introductory Econometrics

Econometrics Summary Algebraic and Statistical Preliminaries

The BLP Method of Demand Curve Estimation in Industrial Organization

1 Correlation and Inference from Regression

Probability. Table of contents

Estimation of Dynamic Regression Models

4.8 Instrumental Variables

ECON 3150/4150, Spring term Lecture 6

Introduction to the Mathematical and Statistical Foundations of Econometrics Herman J. Bierens Pennsylvania State University

Regression and Statistical Inference

Transcription:

Economics 672 Fall 2017 Tauchen 1 Main Model In the jump regression setting we have Jump Regression X = ( Z Y where Z is the log of the market index and Y is the log of an asset price. The dynamics are dz t = σ zt dw 1t + Z t dy t = β c t dz c 1t + σ yt dw 2t + β J t Z t + Ỹt where the W s are independent Brownian motions and rest of the notation is as follows: σ zt : Market diffusive volatility Z t : jump part of the market return β c t : beta on diffusive (continuous) moves in Z dz c 1t : the diffusive (continuous) move in Z, dz c 1t = σ zt dw 1t σ yt : idiosyncratic diffusive volatility β J t : beta on jump moves in Z Ỹt : idiosyncratic jumps in the asset return The key aspect to understanding jump regression is that, by definition, the idiosyncratic jumps in Y are independent of the market jumps, and two independent processes never jump at the same time. Thus, Z t Ỹt = 0. t [0, T ]. Much of the consequences of the theory follow from this understanding. This setup fits into the general framework, where ) (1) (2) (3) dx t = c t dw t + X t (4) ( X t = ) Z t βt J Z t + Ỹt Determination of the c t process in terms of the processes of (2) is left as an exercise. We assume X is finitely active, which means that it only jumps a finite number of times on any time interval. It proves useful to separate X into its continuous and discontinuous parts, (5) X t = X c t + X d t. (6)

Economics 672, Fall 2017 2 Within this setup we have then that Y tp = β J t p Z tp (7) at the jump times t p of the Z process, t p, p = 1, 2,..., P. Of course at the jump times t r of Ỹ we have Y t = r Ỹt, and Y r t = 0 at all other times t t p t r. The above just defines βt J p, without empirical content. However, when we are willing to assume that there is a constant linear relationship so βt J p = β, constant, then we get Y tp = β Z tp (8) The relationship (8) is powerful, in that it means the relationship between the Z jumps and the Y jumps at the jump times is exact, without error. The strength of (8) will become apparent as move on through jump regression. There are two ways in which it can fail. First, the relationship is always linear but the slope varies over time, where we write Or the relationship is non-linear and we write We will explore these possibilities more later. 2 Detecting the Market Jumps Y tp = β tp Z tp. (9) Y tp = β( Z tp ) Z tp. (10) Under the usual sampling scheme we observe the 2 1 vector of returns n i X, i = 1, 2,..., nt. For the jump regression task, we only retain the data points where a jump in the market index is detected. To this end, let u ni denote the jump threshold for the market return as in our earlier work on separating returns into jump and diffusive parts. In other words, in the data the event n i Z > u ni marks a detected jump in the market return. Since we want to be sure to restrict the jump regression only to points where we are quite confident the market jumped, we set the the threshold quite high, i.e., use a high value of α. We need to be a little bit careful with the sets of jump indices and jump times. The true (unknown) jump times are T = {t [0, nt ] : Z t 0}, (11) The set T is a finite number of times with P elements. For large enough n, the jump times will lie in distinct discrete intervals, i.e., no discrete interval contains more than one actual jump; thus, to each t p T there is a unique index i p such that t p ((i p 1) n, i p n ). Let denote those P indices. Now let I = {i p } p=1,2,...,p, (12) I n = {i p I : Z > u n,ip }, (13)

Economics 672, Fall 2017 3 The set I n is the set of indexes of actual jumps that were detected by the jump detection scheme. Necessarily, I n I because some jumps might be missed by the detector. Lastly let I n = {1 i nt : n i Z > u n,i }, (14) In general, I n I because the detector might err in one of two ways: missing an actual jump or by incorrectly declaring an interval to contain a jump. Li et al. (2017) show that for large n both I n I and I n I. That is, the jump detector is correct in the limit. Using advanced methods, one can also show that the jump detector narrows in so fast onto the set of actual jumps that in much of what follows we can act as if I n coincides with I. 3 Inference for the Jump Beta 3.1 When c t is continuous and β c t = β The theory becomes simpler and easier to understand if we assume that the 2 2 variance matrix c t is continuous and that the diffusive beta equals the jump beta across the jump interval. The theory can handle deviations from these presumptions but at the expense of extra theoretical derivations that take us too far afield for now. Recall the classical linear regression model of basic econometrics, y = Xβ + u, Var(u) = Ω where Ω σ 2 I and we have non-spherical disturbances. The OLS estimator is b OLS = (X X) 1 X y and so b OLS β = (X X) 1 X u (15) Var(b OLS ) = (X X) 1 X ΩX (X X) 1, an expression in the Stock-Watson text and many others as well. Of course, we could do GLS, but let s set that aside for now because modern econometrics tends to use b OLS and estimate the covariance matrix above. Very similar expressions arise in jump regression, but the core theory is entirely different. The OLS jump beta estimator is b OLS = p=1 n i p Z Y. Keep in mind that the setup with constant jump beta implies the model Y t = β Z t + Ỹt, Z t Ỹt = 0, t [0, T ].

Economics 672, Fall 2017 4 After much tedious (but useful) calculations we can get and expression that is the analogue of (15) for the jump regression setting: p=1 b OLS β = n i p Z E, where E t = Y t βz t is the error process with time-varying error process c e,t. Note that E = Y β Z, and separating E into jump and continuous parts we have Since Y tp β Z tp = 0, then E = Y tp β Z tp + Y c β Z c. E = Y c β Z c. Jacod and Protter (2012) show that for continuous moves like E ip E n 1/2 σ e,p Z p where Z p N(0, 1) and σ e,p is the standard deviation: σ e,p = c e,tp. Using the above, the sampling error in the jump beta estimate is b OLS β p=1 n i p Z n 1/2 σ e,p Z p, we have that The (theoretical form) of asymptotic distribution of the jump regression OLS estimator is thus 1 1/2 n (b OLS β) N(0, V b ), V b = The applied form is σ 2 e,p = 1 (2k n + 1) n p=1 b OLS N β, ( n i p σ e,p 2 n ( Pn ) 2 k n j= k n P σe,p 2 ( P ) 2 ( +jy b OLS +j 1{ n ip+j Z u n,ip+j}. In practice we might set k n = 7 or so depending upon how smooth we think the diffusion variance is across the jump. 1 Although the asymptotic theory is quite different the result is to a large extent parallel to that of the usual textbook regression theory where the theoretical form of the asymptotic variance matrix is Mxx 1 M xx Mxx 1 where M xx = lim n X X/n and M xx = lim n X ΩX/n

Economics 672, Fall 2017 5 3.2 When c t is discontinuous at the jump times t p, p = 1, 2,..., P This topic will be considered separately in a subsequent lecture. References Jacod, J. and P. Protter (2012). Discretization of Processes. Springer-Verlag. Li, J., V. Todorov, and G. Tauchen (2017). Jump regressions. Econometrica 85, 173 195.