1 First-order di erence equation

Size: px
Start display at page:

Download "1 First-order di erence equation"

Transcription

1 References Hamilton, J. D., Time Series Analysis. Princeton University Press. (Chapter 1,2) The task facing the modern time-series econometrician is to develop reasonably simple and intuitive models capable of forecasting, interpreting and hypothesis testing regarding economic data. In this respect, the time-series econometrician is often concerned with the estimation of difference equations containing stochastic components. 1 First-order di erence equation The model: Suppose we are given the dynamic equation: y t = φ 1 y t 1 + w t (1) where y t is the value of variable at period t, w t is the value of variable at period t, t = 1,..., T. Difference equation: equation relating a variable y t to its previous (lagged) values. First order difference equation: only the first lag appears on the RHS of the equation. For now, the input variable, {w 1, w 2, w 3,...}, will simply be regarded as a sequence of deterministic numbers. Later on, we will assume that they are stochastic. 1.1 Solving a Di erence Equation by Recursive Substitution Assume that we know the starting value of y 1, called the initial condition. The, note the following y 0 = φ 1 y 1 + w 0 y 1 = φ 1 y 0 + w 1 = φ 1 (φ 1 y 1 + w 0 ) + w 1 = φ 2 1y 1 + φ 1 w 0 + w 1 y 2 = φ 1 y 1 + w 2 = φ 1 (φ 2 1y 1 + φ 1 w 0 + w 1 ) + w 2 = φ 3 1y 1 + φ 2 1w 0 + φ 1 w 1 + w y t = φ 1 y t 1 + w t = φ t+1 1 y 1 + φ t 1w 0 + φ t 1 1 w φ 1 w t 1 + w t (2) The procedure to express y t in term of the past values of w and the starting value y 1 is known as recursive substitution. 1

2 1.2 Dynamic multipliers 1. Computation of dynamic multipliers Assume that we start with y t 1 instead of y 1, i.e. we observe the value of y t 1 at period t 1. Can we say something about y t+j? y t = φ 1 y t 1 + w t y t+1 = φ 1 y t + w t+1 = φ 1 (φ 1 y t 1 + w t ) + w t+1 = φ 2 1y t 1 + φ 1 w t + w t y t+j = φ j+1 1 y t 1 + φ j 1 w t + φ j 1 1 w t φ 1 w t+j 1 + w t+j (3) The dynamic multiplier: y t+j = φ j 1 (4) Note that the multiplier does not depend on t. The dynamic multiplier y t the impact multiplier. 2. Impulse response function is called sometimes We can plot dynamic multipliers as a function of lag j, i.e plot { y t+j } J j=1. Because dynamic multipliers calculate the response of y to a single impulse in w, it is also referred to as the impulseresponse function. This function has many important applications in time-series analysis because it shows how the entire path of a variable is effected by a stochastic shock. Obviously, the dynamic of impulse response function depends on the value of φ 1 : (a) 0 < φ 1 < 1, the impulse response converges to zero; the system is stable (b) 1 < φ 1 < 0, the impulse response oscillates but converges to zero; the system is stable (c) φ 1 > 1, the impulse response is explosive; the system is unstable (d) φ 1 < 1, the impulse response is explosive; the system is unstable Impulse response functions for all possible cases are presented in Figure Permanent change in w In calculating dynamic multipliers in Figure 1, we were asking what would happen if w t were to increase by one unit with w t+1, w t+2,..., w t+j unaffected. We were finding the effect of a purely transitory change in w. 2

3 Impulse responses Impulse responses φ 1 = φ 1 = φ 1 = 0.5 φ 1 = φ 1 = Impulse responses Impulse responses φ 1 = φ 1 = Figure 1: Example of impulse response functions for first order difference equations. 3

4 Permanent change in w means that w t, w t+1,..., w t+j would all increase by one unit. The effect on y t+j of a permanent change in w beginning in period t is then given by y t+j + y t+j +1 + y t+j y t+j +j (5) 4

5 1.3 pth-order Di erence Equations 1. The model: A linear pth-order difference equation has the following form: y t = φ 1 y t 1 + φ 2 y t φ p y t p + w t (6) 2. Properties of the pth order di erence equation To illustrate the properties of pth order difference equation we consider the second order difference equation: so that p = 2. We write equation (7) as a first order vector difference equation. y t = φ 1 y t 1 + φ 2 y t 2 + w t (7) where ξ t = F ξ t 1 + v t (8) ξ = [ yt y t 1 ] [ ] φ1 φ 2, F =, v t = 1 0 [ wt 0 ] (9) If the starting value ξ t 1 is known we use the recursive substitution to obtain: ξ t = F t+1 ξ 1 + F t v 0 + F t 1 v 1 + F t 2 v F v t 1 + v t (10) Or if the starting value ξ t is known we use the recursive substitution to obtain: ξ t+j = F j+1 ξ t 1 + F j v t + F j 1 v t+1 + F j 2 v j F v t+j 1 + v t+j (11) 3. Computation of dynamic multipliers Recall the rules of vector and matrix differentiation: ξ t+j v t = F j v t v t = F j (12) This follows from the following rule. If x(β) = (x 1 (β),..., x m (β)) is an m 1 vector that depends on the n 1 vector β = (β 1,..., β n ), then 5

6 x β = In our the equation (12) x = F j v t and β = v t. x 1 β 1 x 1 β n... x m β 1 x m β n (13) Since the first element in ξ t+j is y t+j and the first element in v t is w t then the element (1,1) in the matrix F j is y t+j, i.e. the dynamic multiplier. For larger values of j, an easy way to obtain a numerical values for dynamic multiplier y t+j simulate the system. This is done as follows. Set y 1 = y 2 =... = y p = 0 and w 0 = 1, and set the values of w for all other dates to 0. Then use (6) to calculate the value for y t, t = 0, 1, 2,..., J. is to 4. Illustration of dynamic multipliers for the pth-order di erence equation. Example 1: Consider the second order difference equation. (a) Let the dynamic equation be as follows: so that F = Figure 2(a). y t = 0.6y t y t 2 + w t (14) [ ] The impulse-response function for this example is presented in 1 0 (b) Let the dynamic equation be as follows: so that F = Figure 2(b). y t = 0.8y t y t 2 + w t (15) [ ] The impulse-response function for this example is presented in 1 0 (c) Let the dynamic equation be as follows: so that F = Figure 2(c). y t = 0.9y t 1 0.5y t 2 + w t (16) [ ] The impulse-response function for this example is presented in 1 0 (d) Let the dynamic equation be as follows: y t = 0.5y t 1 1.5y t 2 + w t (17) 6

7 [ ] so that F =. The impulse-response function for this example is presented in 1 0 Figure 2(d). 5. The role of eigenvalue of the matrix F Similar to the first order difference equation, the impulse response function for the p-th order difference equation can be explosive or converge to zero. What determines the dynamics of impulse response function? The eigenvalues of matrix F determine whether the impulse response oscillates, converges or is explosive. The eigenvalues of a p p matrix F are those numbers λ for which F λi p = 0 (18) Proposition 1.1 The eigenvalues of the general matrix F defined in 9 are the values of λ that satisfy: λ p φ 1 λ p 1 φ 2 λ p 2... φ p λ φ p = 0 (19) If the eigenvalues are real but at least one eigenvalue is greater than unity in absolute value, the system is explosive. Example 1 cont. (a) Eigenvalues in the example 1(a): λ 2 0.6λ 0.2 = 0 (20) λ 1 = 0.838, λ 2 = 0.238, i.e. λ i < 1 and the system is stable. (b) Eigenvalues in the example 1(b) λ 2 0.8λ 0.4 = 0 (21) λ 1 = 1.148, λ 2 = 0.348, i.e. λ 1 > 1 and the system is unstable. (c) Eigenvalues in the example 1(c) λ λ = 0 (22) λ 1 = i, λ 2 = i, i.e. λ 1 = ( 0.45) = < 1 and the system is stable. Since eigenvalues are complex, the impulse response function oscillates. 7

8 (a) Impulse responses (b) Impulse responses φ 1 = 0.8, φ 2 = φ 1 = 0.6, φ 2 = (c) Impulse responses (d) Impulse responses φ 1 = -0.9, φ 2 = φ 1 = -0.5, φ 2 = Figure 2: Example of impulse response functions for second order difference equation. 8

9 (d) Eigenvalues in the example 1(d) λ λ = 0 (23) λ 1 = i, λ 2 = i, i.e. λ 1 = ( 0.25) = > 1 and the system is unstable. Since eigenvalues are complex, the impulse response function oscillates. 6. Why do eigenvalues determine the dynamics of dynamic multipliers? Recall that if the eigenvalues of p p matrix are distinct, there exists a nonsingular p p matrix T such that: F = T ΛT 1 (24) where Λ is a p p matrix with the eigenvalues of F on the principal diagonal and zeros elsewhere. Then, F j = T Λ j T 1 (25) and the value of eigenvalues in Λ determines whether the elements of F j explode or not. Recall from (12) that the dynamic multiplier is equal to ξ t+j v t determines whether the system is stable or not. = F j. Therefore, the size of eigenvalues 2 Lag operators Now we develop some of the results using time series operators, which are used in time-series econometrics very often. 1. Lag operator Generally, a time series operator transforms one times series or a group of time series into a new time series. A highly useful operator is the lag operator, represented by the symbol L. Faced with a time series defined in terms of compound operators, one may use the standard cummutative, associative and distributive laws for multiplication and addition. The main properties of the lag operator are as follows: Lx t = x t 1 9

10 L k x t = x t k L(βx t ) = β(lx t ) L(x t + w t ) = Lx t + Lw t Lc = c, c is a constant L i y t = y t+i (1 + φ 1 L + φ 2 1L )y t = y t 1 φ 1 L, a < First-order di erence equation The first-order difference equation has the form: y t = φ 1 y t 1 + w t y t = φ 1 (Ly t ) + w t (1 φ 1 L)y t = w t (26) Multiplying LHS and RHS of the equation 26 by (1 + φ 1 L + φ 2 L 2 + φ 3 L φ t L t ) we obtain: (1 φ t+1 1 L t+1 )y t = (1 + φ 1 L + φ 2 L 2 + φ 3 L φ t L t )w t y t = φ t+1 1 y 1 + w t + φ 1 w t 1 + φ 2 1w t φ t 1w 0 (27) Note that equation in (27) is the same as in equation (2). A sequence {y t } t= is said to be bounded if there exists a finite number ȳ such that y t < ȳ for all t. When φ 1 < 1, a sequence is bounded. 2.2 Second-order di erence equation A second-order difference equation is: (1 φ 1 L φ 2 L 2 )y t = w t y t = φ 1 y t 1 + φ 2 y t 2 + w t (1 λ 1 L)(1 λ 2 L)y t = w t (28) How do we find the values of λ 1 and λ 2? Step 1: Find the scalars z 1 and z 2 such that (1 φ 1 z φ 2 z 2 ) = 0 Step 2: Set λ 1 = z 1 1, λ 2 = z

11 Proposition 2.1 Factoring the polynomial (1 φ 1 L φ 2 L 2 ) as (1 φ 1 L φ 2 L) = (1 λ 1 L)(1 λ 2 L) (29) is the same calculation as finding eigenvalues of the matrix F in (9). The eigenvalues λ 1 and λ 2 of F are the same as the parameters λ 1 and λ 2 in (29). Given that the second-order difference equation is stable, with eigenvalues λ 1 and λ 2 distinct and both lie inside the unit circle the equation (28) can be written as (1 λ 1 L)(1 λ 2 L)y t = w t y t = (1 λ 1 L) 1 (1 λ 2 L) 1 w t (30) 2.3 pth-order Di erence Equations These techniques generalize in a straightforward way to a pth-order difference equation of the form: (1 φ 1 L φ 2 L 2... φ p L p )y t = w t y t = φ 1 y t 1 + φ 2 y t φ p y t p + w t (1 λ 1 L)(1 λ 2 L)...(1 λ p L)y t = w t (31) 11

Notes on Time Series Modeling

Notes on Time Series Modeling Notes on Time Series Modeling Garey Ramey University of California, San Diego January 17 1 Stationary processes De nition A stochastic process is any set of random variables y t indexed by t T : fy t g

More information

Problem Set 1 Solution Sketches Time Series Analysis Spring 2010

Problem Set 1 Solution Sketches Time Series Analysis Spring 2010 Problem Set 1 Solution Sketches Time Series Analysis Spring 2010 1. Construct a martingale difference process that is not weakly stationary. Simplest e.g.: Let Y t be a sequence of independent, non-identically

More information

Ch. 15 Forecasting. 1.1 Forecasts Based on Conditional Expectations

Ch. 15 Forecasting. 1.1 Forecasts Based on Conditional Expectations Ch 15 Forecasting Having considered in Chapter 14 some of the properties of ARMA models, we now show how they may be used to forecast future values of an observed time series For the present we proceed

More information

1 Linear Difference Equations

1 Linear Difference Equations ARMA Handout Jialin Yu 1 Linear Difference Equations First order systems Let {ε t } t=1 denote an input sequence and {y t} t=1 sequence generated by denote an output y t = φy t 1 + ε t t = 1, 2,... with

More information

TIME SERIES AND FORECASTING. Luca Gambetti UAB, Barcelona GSE Master in Macroeconomic Policy and Financial Markets

TIME SERIES AND FORECASTING. Luca Gambetti UAB, Barcelona GSE Master in Macroeconomic Policy and Financial Markets TIME SERIES AND FORECASTING Luca Gambetti UAB, Barcelona GSE 2014-2015 Master in Macroeconomic Policy and Financial Markets 1 Contacts Prof.: Luca Gambetti Office: B3-1130 Edifici B Office hours: email:

More information

Cointegrated VAR s. Eduardo Rossi University of Pavia. November Rossi Cointegrated VAR s Fin. Econometrics / 31

Cointegrated VAR s. Eduardo Rossi University of Pavia. November Rossi Cointegrated VAR s Fin. Econometrics / 31 Cointegrated VAR s Eduardo Rossi University of Pavia November 2014 Rossi Cointegrated VAR s Fin. Econometrics - 2014 1 / 31 B-N decomposition Give a scalar polynomial α(z) = α 0 + α 1 z +... + α p z p

More information

Solving Linear Rational Expectations Models

Solving Linear Rational Expectations Models Solving Linear Rational Expectations Models simplified from Christopher A. Sims, by Michael Reiter January 2010 1 General form of the models The models we are interested in can be cast in the form Γ 0

More information

Covariance Stationary Time Series. Example: Independent White Noise (IWN(0,σ 2 )) Y t = ε t, ε t iid N(0,σ 2 )

Covariance Stationary Time Series. Example: Independent White Noise (IWN(0,σ 2 )) Y t = ε t, ε t iid N(0,σ 2 ) Covariance Stationary Time Series Stochastic Process: sequence of rv s ordered by time {Y t } {...,Y 1,Y 0,Y 1,...} Defn: {Y t } is covariance stationary if E[Y t ]μ for all t cov(y t,y t j )E[(Y t μ)(y

More information

Multivariate ARMA Processes

Multivariate ARMA Processes LECTURE 8 Multivariate ARMA Processes A vector y(t) of n elements is said to follow an n-variate ARMA process of orders p and q if it satisfies the equation (1) A 0 y(t) + A 1 y(t 1) + + A p y(t p) = M

More information

Discrete time processes

Discrete time processes Discrete time processes Predictions are difficult. Especially about the future Mark Twain. Florian Herzog 2013 Modeling observed data When we model observed (realized) data, we encounter usually the following

More information

ECON 616: Lecture 1: Time Series Basics

ECON 616: Lecture 1: Time Series Basics ECON 616: Lecture 1: Time Series Basics ED HERBST August 30, 2017 References Overview: Chapters 1-3 from Hamilton (1994). Technical Details: Chapters 2-3 from Brockwell and Davis (1987). Intuition: Chapters

More information

SOME BASICS OF TIME-SERIES ANALYSIS

SOME BASICS OF TIME-SERIES ANALYSIS SOME BASICS OF TIME-SERIES ANALYSIS John E. Floyd University of Toronto December 8, 26 An excellent place to learn about time series analysis is from Walter Enders textbook. For a basic understanding of

More information

Ch. 14 Stationary ARMA Process

Ch. 14 Stationary ARMA Process Ch. 14 Stationary ARMA Process A general linear stochastic model is described that suppose a time series to be generated by a linear aggregation of random shock. For practical representation it is desirable

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

Multivariate Time Series

Multivariate Time Series Multivariate Time Series Fall 2008 Environmental Econometrics (GR03) TSII Fall 2008 1 / 16 More on AR(1) In AR(1) model (Y t = µ + ρy t 1 + u t ) with ρ = 1, the series is said to have a unit root or a

More information

Remark By definition, an eigenvector must be a nonzero vector, but eigenvalue could be zero.

Remark By definition, an eigenvector must be a nonzero vector, but eigenvalue could be zero. Sec 6 Eigenvalues and Eigenvectors Definition An eigenvector of an n n matrix A is a nonzero vector x such that A x λ x for some scalar λ A scalar λ is called an eigenvalue of A if there is a nontrivial

More information

5: MULTIVARATE STATIONARY PROCESSES

5: MULTIVARATE STATIONARY PROCESSES 5: MULTIVARATE STATIONARY PROCESSES 1 1 Some Preliminary Definitions and Concepts Random Vector: A vector X = (X 1,..., X n ) whose components are scalarvalued random variables on the same probability

More information

ARIMA Models. Richard G. Pierse

ARIMA Models. Richard G. Pierse ARIMA Models Richard G. Pierse 1 Introduction Time Series Analysis looks at the properties of time series from a purely statistical point of view. No attempt is made to relate variables using a priori

More information

Chapter 6. Maximum Likelihood Analysis of Dynamic Stochastic General Equilibrium (DSGE) Models

Chapter 6. Maximum Likelihood Analysis of Dynamic Stochastic General Equilibrium (DSGE) Models Chapter 6. Maximum Likelihood Analysis of Dynamic Stochastic General Equilibrium (DSGE) Models Fall 22 Contents Introduction 2. An illustrative example........................... 2.2 Discussion...................................

More information

UNIVERSITY OF CALIFORNIA, SAN DIEGO DEPARTMENT OF ECONOMICS

UNIVERSITY OF CALIFORNIA, SAN DIEGO DEPARTMENT OF ECONOMICS 2-7 UNIVERSITY OF LIFORNI, SN DIEGO DEPRTMENT OF EONOMIS THE JOHNSEN-GRNGER REPRESENTTION THEOREM: N EXPLIIT EXPRESSION FOR I() PROESSES Y PETER REINHRD HNSEN DISUSSION PPER 2-7 JULY 2 The Johansen-Granger

More information

7. MULTIVARATE STATIONARY PROCESSES

7. MULTIVARATE STATIONARY PROCESSES 7. MULTIVARATE STATIONARY PROCESSES 1 1 Some Preliminary Definitions and Concepts Random Vector: A vector X = (X 1,..., X n ) whose components are scalar-valued random variables on the same probability

More information

Advanced Econometrics

Advanced Econometrics Based on the textbook by Verbeek: A Guide to Modern Econometrics Robert M. Kunst robert.kunst@univie.ac.at University of Vienna and Institute for Advanced Studies Vienna May 2, 2013 Outline Univariate

More information

Remark 1 By definition, an eigenvector must be a nonzero vector, but eigenvalue could be zero.

Remark 1 By definition, an eigenvector must be a nonzero vector, but eigenvalue could be zero. Sec 5 Eigenvectors and Eigenvalues In this chapter, vector means column vector Definition An eigenvector of an n n matrix A is a nonzero vector x such that A x λ x for some scalar λ A scalar λ is called

More information

PY 351 Modern Physics Short assignment 4, Nov. 9, 2018, to be returned in class on Nov. 15.

PY 351 Modern Physics Short assignment 4, Nov. 9, 2018, to be returned in class on Nov. 15. PY 351 Modern Physics Short assignment 4, Nov. 9, 2018, to be returned in class on Nov. 15. You may write your answers on this sheet or on a separate paper. Remember to write your name on top. Please note:

More information

Class 1: Stationary Time Series Analysis

Class 1: Stationary Time Series Analysis Class 1: Stationary Time Series Analysis Macroeconometrics - Fall 2009 Jacek Suda, BdF and PSE February 28, 2011 Outline Outline: 1 Covariance-Stationary Processes 2 Wold Decomposition Theorem 3 ARMA Models

More information

We use the overhead arrow to denote a column vector, i.e., a number with a direction. For example, in three-space, we write

We use the overhead arrow to denote a column vector, i.e., a number with a direction. For example, in three-space, we write 1 MATH FACTS 11 Vectors 111 Definition We use the overhead arrow to denote a column vector, ie, a number with a direction For example, in three-space, we write The elements of a vector have a graphical

More information

Cointegrated VAR s. Eduardo Rossi University of Pavia. November Rossi Cointegrated VAR s Financial Econometrics / 56

Cointegrated VAR s. Eduardo Rossi University of Pavia. November Rossi Cointegrated VAR s Financial Econometrics / 56 Cointegrated VAR s Eduardo Rossi University of Pavia November 2013 Rossi Cointegrated VAR s Financial Econometrics - 2013 1 / 56 VAR y t = (y 1t,..., y nt ) is (n 1) vector. y t VAR(p): Φ(L)y t = ɛ t The

More information

Chapter 7. Canonical Forms. 7.1 Eigenvalues and Eigenvectors

Chapter 7. Canonical Forms. 7.1 Eigenvalues and Eigenvectors Chapter 7 Canonical Forms 7.1 Eigenvalues and Eigenvectors Definition 7.1.1. Let V be a vector space over the field F and let T be a linear operator on V. An eigenvalue of T is a scalar λ F such that there

More information

Vector error correction model, VECM Cointegrated VAR

Vector error correction model, VECM Cointegrated VAR 1 / 58 Vector error correction model, VECM Cointegrated VAR Chapter 4 Financial Econometrics Michael Hauser WS17/18 2 / 58 Content Motivation: plausible economic relations Model with I(1) variables: spurious

More information

slides chapter 3 an open economy with capital

slides chapter 3 an open economy with capital slides chapter 3 an open economy with capital Princeton University Press, 2017 Motivation In this chaper we introduce production and physical capital accumulation. Doing so will allow us to address two

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

Generalized Eigenvectors and Jordan Form

Generalized Eigenvectors and Jordan Form Generalized Eigenvectors and Jordan Form We have seen that an n n matrix A is diagonalizable precisely when the dimensions of its eigenspaces sum to n. So if A is not diagonalizable, there is at least

More information

Estimating and Identifying Vector Autoregressions Under Diagonality and Block Exogeneity Restrictions

Estimating and Identifying Vector Autoregressions Under Diagonality and Block Exogeneity Restrictions Estimating and Identifying Vector Autoregressions Under Diagonality and Block Exogeneity Restrictions William D. Lastrapes Department of Economics Terry College of Business University of Georgia Athens,

More information

AN ITERATION. In part as motivation, we consider an iteration method for solving a system of linear equations which has the form x Ax = b

AN ITERATION. In part as motivation, we consider an iteration method for solving a system of linear equations which has the form x Ax = b AN ITERATION In part as motivation, we consider an iteration method for solving a system of linear equations which has the form x Ax = b In this, A is an n n matrix and b R n.systemsof this form arise

More information

Macroeconomics Theory II

Macroeconomics Theory II Macroeconomics Theory II Economies as ynamic Systems Francesco Franco Nova SBE February 11, 2014 Francesco Franco Macroeconomics Theory II 1/18 First-order The variable z t follows a first-order di erence

More information

Automatic Control Systems theory overview (discrete time systems)

Automatic Control Systems theory overview (discrete time systems) Automatic Control Systems theory overview (discrete time systems) Prof. Luca Bascetta (luca.bascetta@polimi.it) Politecnico di Milano Dipartimento di Elettronica, Informazione e Bioingegneria Motivations

More information

Econometría 2: Análisis de series de Tiempo

Econometría 2: Análisis de series de Tiempo Econometría 2: Análisis de series de Tiempo Karoll GOMEZ kgomezp@unal.edu.co http://karollgomez.wordpress.com Segundo semestre 2016 IX. Vector Time Series Models VARMA Models A. 1. Motivation: The vector

More information

Graduate Macro Theory II: Notes on Solving Linearized Rational Expectations Models

Graduate Macro Theory II: Notes on Solving Linearized Rational Expectations Models Graduate Macro Theory II: Notes on Solving Linearized Rational Expectations Models Eric Sims University of Notre Dame Spring 2017 1 Introduction The solution of many discrete time dynamic economic models

More information

Solutions to Dynamical Systems 2010 exam. Each question is worth 25 marks.

Solutions to Dynamical Systems 2010 exam. Each question is worth 25 marks. Solutions to Dynamical Systems exam Each question is worth marks [Unseen] Consider the following st order differential equation: dy dt Xy yy 4 a Find and classify all the fixed points of Hence draw the

More information

Time Series Analysis. James D. Hamilton PRINCETON UNIVERSITY PRESS PRINCETON, NEW JERSEY

Time Series Analysis. James D. Hamilton PRINCETON UNIVERSITY PRESS PRINCETON, NEW JERSEY Time Series Analysis James D. Hamilton PRINCETON UNIVERSITY PRESS PRINCETON, NEW JERSEY PREFACE xiii 1 Difference Equations 1.1. First-Order Difference Equations 1 1.2. pth-order Difference Equations 7

More information

22.3. Repeated Eigenvalues and Symmetric Matrices. Introduction. Prerequisites. Learning Outcomes

22.3. Repeated Eigenvalues and Symmetric Matrices. Introduction. Prerequisites. Learning Outcomes Repeated Eigenvalues and Symmetric Matrices. Introduction In this Section we further develop the theory of eigenvalues and eigenvectors in two distinct directions. Firstly we look at matrices where one

More information

Solving Ax = b w/ different b s: LU-Factorization

Solving Ax = b w/ different b s: LU-Factorization Solving Ax = b w/ different b s: LU-Factorization Linear Algebra Josh Engwer TTU 14 September 2015 Josh Engwer (TTU) Solving Ax = b w/ different b s: LU-Factorization 14 September 2015 1 / 21 Elementary

More information

Autoregressive models with distributed lags (ADL)

Autoregressive models with distributed lags (ADL) Autoregressive models with distributed lags (ADL) It often happens than including the lagged dependent variable in the model results in model which is better fitted and needs less parameters. It can be

More information

Vector Autogregression and Impulse Response Functions

Vector Autogregression and Impulse Response Functions Chapter 8 Vector Autogregression and Impulse Response Functions 8.1 Vector Autogregressions Consider two sequences {y t } and {z t }, where the time path of {y t } is affected by current and past realizations

More information

CONTROL DESIGN FOR SET POINT TRACKING

CONTROL DESIGN FOR SET POINT TRACKING Chapter 5 CONTROL DESIGN FOR SET POINT TRACKING In this chapter, we extend the pole placement, observer-based output feedback design to solve tracking problems. By tracking we mean that the output is commanded

More information

Combining Macroeconomic Models for Prediction

Combining Macroeconomic Models for Prediction Combining Macroeconomic Models for Prediction John Geweke University of Technology Sydney 15th Australasian Macro Workshop April 8, 2010 Outline 1 Optimal prediction pools 2 Models and data 3 Optimal pools

More information

Eigenvalues. Matrices: Geometric Interpretation. Calculating Eigenvalues

Eigenvalues. Matrices: Geometric Interpretation. Calculating Eigenvalues Eigenvalues Matrices: Geometric Interpretation Start with a vector of length 2, for example, x =(1, 2). This among other things give the coordinates for a point on a plane. Take a 2 2 matrix, for example,

More information

Title. Description. var intro Introduction to vector autoregressive models

Title. Description. var intro Introduction to vector autoregressive models Title var intro Introduction to vector autoregressive models Description Stata has a suite of commands for fitting, forecasting, interpreting, and performing inference on vector autoregressive (VAR) models

More information

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

1 Outline. 1. Motivation. 2. SUR model. 3. Simultaneous equations. 4. Estimation 1 Outline. 1. Motivation 2. SUR model 3. Simultaneous equations 4. Estimation 2 Motivation. In this chapter, we will study simultaneous systems of econometric equations. Systems of simultaneous equations

More information

Definition: An n x n matrix, "A", is said to be diagonalizable if there exists a nonsingular matrix "X" and a diagonal matrix "D" such that X 1 A X

Definition: An n x n matrix, A, is said to be diagonalizable if there exists a nonsingular matrix X and a diagonal matrix D such that X 1 A X DIGONLIZTION Definition: n n x n matrix, "", is said to be diagonalizable if there exists a nonsingular matrix "X" and a diagonal matrix "D" such that X X D. Theorem: n n x n matrix, "", is diagonalizable

More information

Ch. 19 Models of Nonstationary Time Series

Ch. 19 Models of Nonstationary Time Series Ch. 19 Models of Nonstationary Time Series In time series analysis we do not confine ourselves to the analysis of stationary time series. In fact, most of the time series we encounter are non stationary.

More information

Non-Stationary Time Series and Unit Root Testing

Non-Stationary Time Series and Unit Root Testing Econometrics II Non-Stationary Time Series and Unit Root Testing Morten Nyboe Tabor Course Outline: Non-Stationary Time Series and Unit Root Testing 1 Stationarity and Deviation from Stationarity Trend-Stationarity

More information

Time Series Analysis. James D. Hamilton PRINCETON UNIVERSITY PRESS PRINCETON, NEW JERSEY

Time Series Analysis. James D. Hamilton PRINCETON UNIVERSITY PRESS PRINCETON, NEW JERSEY Time Series Analysis James D. Hamilton PRINCETON UNIVERSITY PRESS PRINCETON, NEW JERSEY & Contents PREFACE xiii 1 1.1. 1.2. Difference Equations First-Order Difference Equations 1 /?th-order Difference

More information

FACULTY OF MATHEMATICAL STUDIES MATHEMATICS FOR PART I ENGINEERING. Lectures

FACULTY OF MATHEMATICAL STUDIES MATHEMATICS FOR PART I ENGINEERING. Lectures FACULTY OF MATHEMATICAL STUDIES MATHEMATICS FOR PART I ENGINEERING Lectures MODULE 8 MATRICES III Rank of a matrix 2 General systems of linear equations 3 Eigenvalues and eigenvectors Rank of a matrix

More information

Chapter 3 Transformations

Chapter 3 Transformations Chapter 3 Transformations An Introduction to Optimization Spring, 2014 Wei-Ta Chu 1 Linear Transformations A function is called a linear transformation if 1. for every and 2. for every If we fix the bases

More information

Cointegration, Stationarity and Error Correction Models.

Cointegration, Stationarity and Error Correction Models. Cointegration, Stationarity and Error Correction Models. STATIONARITY Wold s decomposition theorem states that a stationary time series process with no deterministic components has an infinite moving average

More information

Citation Working Paper Series, F-39:

Citation Working Paper Series, F-39: Equilibrium Indeterminacy under F Title Interest Rate Rules Author(s) NAKAGAWA, Ryuichi Citation Working Paper Series, F-39: 1-14 Issue Date 2009-06 URL http://hdl.handle.net/10112/2641 Rights Type Technical

More information

Non-Stationary Time Series and Unit Root Testing

Non-Stationary Time Series and Unit Root Testing Econometrics II Non-Stationary Time Series and Unit Root Testing Morten Nyboe Tabor Course Outline: Non-Stationary Time Series and Unit Root Testing 1 Stationarity and Deviation from Stationarity Trend-Stationarity

More information

Univariate Time Series Analysis; ARIMA Models

Univariate Time Series Analysis; ARIMA Models Econometrics 2 Fall 24 Univariate Time Series Analysis; ARIMA Models Heino Bohn Nielsen of4 Outline of the Lecture () Introduction to univariate time series analysis. (2) Stationarity. (3) Characterizing

More information

New Notes on the Solow Growth Model

New Notes on the Solow Growth Model New Notes on the Solow Growth Model Roberto Chang September 2009 1 The Model The firstingredientofadynamicmodelisthedescriptionofthetimehorizon. In the original Solow model, time is continuous and the

More information

Linear Models with Rational Expectations

Linear Models with Rational Expectations Linear Models with Rational Expectations Vivaldo Mendes Dep. of Economics Instituto Universitário de Lisboa October 2017 (Vivaldo Mendes ISCTE-IUL ) Master in Economics October 2017 1 / 59 Summary 1 From

More information

Stock Prices, News, and Economic Fluctuations: Comment

Stock Prices, News, and Economic Fluctuations: Comment Stock Prices, News, and Economic Fluctuations: Comment André Kurmann Federal Reserve Board Elmar Mertens Federal Reserve Board Online Appendix November 7, 213 Abstract This web appendix provides some more

More information

and let s calculate the image of some vectors under the transformation T.

and let s calculate the image of some vectors under the transformation T. Chapter 5 Eigenvalues and Eigenvectors 5. Eigenvalues and Eigenvectors Let T : R n R n be a linear transformation. Then T can be represented by a matrix (the standard matrix), and we can write T ( v) =

More information

11. Further Issues in Using OLS with TS Data

11. Further Issues in Using OLS with TS Data 11. Further Issues in Using OLS with TS Data With TS, including lags of the dependent variable often allow us to fit much better the variation in y Exact distribution theory is rarely available in TS applications,

More information

E 4160 Autumn term Lecture 9: Deterministic trends vs integrated series; Spurious regression; Dickey-Fuller distribution and test

E 4160 Autumn term Lecture 9: Deterministic trends vs integrated series; Spurious regression; Dickey-Fuller distribution and test E 4160 Autumn term 2016. Lecture 9: Deterministic trends vs integrated series; Spurious regression; Dickey-Fuller distribution and test Ragnar Nymoen Department of Economics, University of Oslo 24 October

More information

Introduction to ARMA and GARCH processes

Introduction to ARMA and GARCH processes Introduction to ARMA and GARCH processes Fulvio Corsi SNS Pisa 3 March 2010 Fulvio Corsi Introduction to ARMA () and GARCH processes SNS Pisa 3 March 2010 1 / 24 Stationarity Strict stationarity: (X 1,

More information

Dynamical Systems. August 13, 2013

Dynamical Systems. August 13, 2013 Dynamical Systems Joshua Wilde, revised by Isabel Tecu, Takeshi Suzuki and María José Boccardi August 13, 2013 Dynamical Systems are systems, described by one or more equations, that evolve over time.

More information

Diagonalization of Matrices

Diagonalization of Matrices LECTURE 4 Diagonalization of Matrices Recall that a diagonal matrix is a square n n matrix with non-zero entries only along the diagonal from the upper left to the lower right (the main diagonal) Diagonal

More information

Properties of Zero-Free Spectral Matrices Brian D. O. Anderson, Life Fellow, IEEE, and Manfred Deistler, Fellow, IEEE

Properties of Zero-Free Spectral Matrices Brian D. O. Anderson, Life Fellow, IEEE, and Manfred Deistler, Fellow, IEEE IEEE TRANSACTIONS ON AUTOMATIC CONTROL, VOL 54, NO 10, OCTOBER 2009 2365 Properties of Zero-Free Spectral Matrices Brian D O Anderson, Life Fellow, IEEE, and Manfred Deistler, Fellow, IEEE Abstract In

More information

Math 3191 Applied Linear Algebra

Math 3191 Applied Linear Algebra Math 9 Applied Linear Algebra Lecture 9: Diagonalization Stephen Billups University of Colorado at Denver Math 9Applied Linear Algebra p./9 Section. Diagonalization The goal here is to develop a useful

More information

3 Time Series Regression

3 Time Series Regression 3 Time Series Regression 3.1 Modelling Trend Using Regression Random Walk 2 0 2 4 6 8 Random Walk 0 2 4 6 8 0 10 20 30 40 50 60 (a) Time 0 10 20 30 40 50 60 (b) Time Random Walk 8 6 4 2 0 Random Walk 0

More information

Measurement Errors and the Kalman Filter: A Unified Exposition

Measurement Errors and the Kalman Filter: A Unified Exposition Luiss Lab of European Economics LLEE Working Document no. 45 Measurement Errors and the Kalman Filter: A Unified Exposition Salvatore Nisticò February 2007 Outputs from LLEE research in progress, as well

More information

Forecasting with ARMA Models

Forecasting with ARMA Models LECTURE 4 Forecasting with ARMA Models Minumum Mean-Square Error Prediction Imagine that y(t) is a stationary stochastic process with E{y(t)} = 0. We may be interested in predicting values of this process

More information

A Modified Fractionally Co-integrated VAR for Predicting Returns

A Modified Fractionally Co-integrated VAR for Predicting Returns A Modified Fractionally Co-integrated VAR for Predicting Returns Xingzhi Yao Marwan Izzeldin Department of Economics, Lancaster University 13 December 215 Yao & Izzeldin (Lancaster University) CFE (215)

More information

International Macro Finance

International Macro Finance International Macro Finance Economies as Dynamic Systems Francesco Franco Nova SBE February 21, 2013 Francesco Franco International Macro Finance 1/39 Flashback Mundell-Fleming MF on the whiteboard Francesco

More information

Dynamic Factor Models, Factor Augmented VARs, and SVARs in Macroeconomics. -- Part 2: SVARs and SDFMs --

Dynamic Factor Models, Factor Augmented VARs, and SVARs in Macroeconomics. -- Part 2: SVARs and SDFMs -- Dynamic Factor Models, Factor Augmented VARs, and SVARs in Macroeconomics -- Part 2: SVARs and SDFMs -- Mark Watson Princeton University Central Bank of Chile October 22-24, 208 Reference: Stock, James

More information

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

the error term could vary over the observations, in ways that are related Heteroskedasticity We now consider the implications of relaxing the assumption that the conditional variance Var(u i x i ) = σ 2 is common to all observations i = 1,..., n In many applications, we may

More information

LECTURE 10 LINEAR PROCESSES II: SPECTRAL DENSITY, LAG OPERATOR, ARMA. In this lecture, we continue to discuss covariance stationary processes.

LECTURE 10 LINEAR PROCESSES II: SPECTRAL DENSITY, LAG OPERATOR, ARMA. In this lecture, we continue to discuss covariance stationary processes. MAY, 0 LECTURE 0 LINEAR PROCESSES II: SPECTRAL DENSITY, LAG OPERATOR, ARMA In this lecture, we continue to discuss covariance stationary processes. Spectral density Gourieroux and Monfort 990), Ch. 5;

More information

Slides to Lecture 3 of Introductory Dynamic Macroeconomics. Linear Dynamic Models (Ch 2 of IDM)

Slides to Lecture 3 of Introductory Dynamic Macroeconomics. Linear Dynamic Models (Ch 2 of IDM) Partial recap of lecture 2 1. We used the ADL model to make precise the concept of dynamic multiplier. Slides to Lecture 3 of Introductory Dynamic Macroeconomics. Linear Dynamic Models (Ch 2 of IDM) Ragnar

More information

Eco504, Part II Spring 2010 C. Sims PITFALLS OF LINEAR APPROXIMATION OF STOCHASTIC MODELS

Eco504, Part II Spring 2010 C. Sims PITFALLS OF LINEAR APPROXIMATION OF STOCHASTIC MODELS Eco504, Part II Spring 2010 C. Sims PITFALLS OF LINEAR APPROXIMATION OF STOCHASTIC MODELS 1. A LIST OF PITFALLS Linearized models are of course valid only locally. In stochastic economic models, this usually

More information

Permanent Income Hypothesis (PIH) Instructor: Dmytro Hryshko

Permanent Income Hypothesis (PIH) Instructor: Dmytro Hryshko Permanent Income Hypothesis (PIH) Instructor: Dmytro Hryshko 1 / 36 The PIH Utility function is quadratic, u(c t ) = 1 2 (c t c) 2 ; borrowing/saving is allowed using only the risk-free bond; β(1 + r)

More information

Estimating Moving Average Processes with an improved version of Durbin s Method

Estimating Moving Average Processes with an improved version of Durbin s Method Estimating Moving Average Processes with an improved version of Durbin s Method Maximilian Ludwig this version: June 7, 4, initial version: April, 3 arxiv:347956v [statme] 6 Jun 4 Abstract This paper provides

More information

Non-Stationary Time Series and Unit Root Testing

Non-Stationary Time Series and Unit Root Testing Econometrics II Non-Stationary Time Series and Unit Root Testing Morten Nyboe Tabor Course Outline: Non-Stationary Time Series and Unit Root Testing 1 Stationarity and Deviation from Stationarity Trend-Stationarity

More information

Recall : Eigenvalues and Eigenvectors

Recall : Eigenvalues and Eigenvectors Recall : Eigenvalues and Eigenvectors Let A be an n n matrix. If a nonzero vector x in R n satisfies Ax λx for a scalar λ, then : The scalar λ is called an eigenvalue of A. The vector x is called an eigenvector

More information

Animal Spirits, Fundamental Factors and Business Cycle Fluctuations

Animal Spirits, Fundamental Factors and Business Cycle Fluctuations Animal Spirits, Fundamental Factors and Business Cycle Fluctuations Stephane Dées Srečko Zimic Banque de France European Central Bank January 6, 218 Disclaimer Any views expressed represent those of the

More information

Difference equations. Definitions: A difference equation takes the general form. x t f x t 1,,x t m.

Difference equations. Definitions: A difference equation takes the general form. x t f x t 1,,x t m. Difference equations Definitions: A difference equation takes the general form x t fx t 1,x t 2, defining the current value of a variable x as a function of previously generated values. A finite order

More information

Non-Stationary Time Series, Cointegration, and Spurious Regression

Non-Stationary Time Series, Cointegration, and Spurious Regression Econometrics II Non-Stationary Time Series, Cointegration, and Spurious Regression Econometrics II Course Outline: Non-Stationary Time Series, Cointegration and Spurious Regression 1 Regression with Non-Stationarity

More information

Simultaneous (and Recursive) Equation Systems. Robert Dixon Department of Economics at the University of Melbourne

Simultaneous (and Recursive) Equation Systems. Robert Dixon Department of Economics at the University of Melbourne Simultaneous (and Recursive) Equation Systems Robert Dixon Department of Economics at the University of Melbourne In their History of Macroeconometric Model-Building, Bodkin, Klein and Marwah give "pride

More information

Chapter 3. Determinants and Eigenvalues

Chapter 3. Determinants and Eigenvalues Chapter 3. Determinants and Eigenvalues 3.1. Determinants With each square matrix we can associate a real number called the determinant of the matrix. Determinants have important applications to the theory

More information

Study Notes on Matrices & Determinants for GATE 2017

Study Notes on Matrices & Determinants for GATE 2017 Study Notes on Matrices & Determinants for GATE 2017 Matrices and Determinates are undoubtedly one of the most scoring and high yielding topics in GATE. At least 3-4 questions are always anticipated from

More information

Testing Error Correction in Panel data

Testing Error Correction in Panel data University of Vienna, Dept. of Economics Master in Economics Vienna 2010 The Model (1) Westerlund (2007) consider the following DGP: y it = φ 1i + φ 2i t + z it (1) x it = x it 1 + υ it (2) where the stochastic

More information

Perturbation and Projection Methods for Solving DSGE Models

Perturbation and Projection Methods for Solving DSGE Models Perturbation and Projection Methods for Solving DSGE Models Lawrence J. Christiano Discussion of projections taken from Christiano Fisher, Algorithms for Solving Dynamic Models with Occasionally Binding

More information

Chemical Process Dynamics and Control. Aisha Osman Mohamed Ahmed Department of Chemical Engineering Faculty of Engineering, Red Sea University

Chemical Process Dynamics and Control. Aisha Osman Mohamed Ahmed Department of Chemical Engineering Faculty of Engineering, Red Sea University Chemical Process Dynamics and Control Aisha Osman Mohamed Ahmed Department of Chemical Engineering Faculty of Engineering, Red Sea University 1 Chapter 4 System Stability 2 Chapter Objectives End of this

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

UNIT 1 DETERMINANTS 1.0 INTRODUCTION 1.1 OBJECTIVES. Structure

UNIT 1 DETERMINANTS 1.0 INTRODUCTION 1.1 OBJECTIVES. Structure UNIT 1 DETERMINANTS Determinants Structure 1.0 Introduction 1.1 Objectives 1.2 Determinants of Order 2 and 3 1.3 Determinants of Order 3 1.4 Properties of Determinants 1.5 Application of Determinants 1.6

More information

DIAGONALIZATION BY SIMILARITY TRANSFORMATIONS

DIAGONALIZATION BY SIMILARITY TRANSFORMATIONS DIAGONALIZATION BY SIMILARITY TRANSFORMATIONS The correct choice of a coordinate system (or basis) often can simplify the form of an equation or the analysis of a particular problem. For example, consider

More information

Master 2 Macro I. Lecture notes #12 : Solving Dynamic Rational Expectations Models

Master 2 Macro I. Lecture notes #12 : Solving Dynamic Rational Expectations Models 2012-2013 Master 2 Macro I Lecture notes #12 : Solving Dynamic Rational Expectations Models Franck Portier (based on Gilles Saint-Paul lecture notes) franck.portier@tse-fr.eu Toulouse School of Economics

More information

Matrices 2. Slide for MA1203 Business Mathematics II Week 4

Matrices 2. Slide for MA1203 Business Mathematics II Week 4 Matrices 2 Slide for MA1203 Business Mathematics II Week 4 2.7 Leontief Input Output Model Input Output Analysis One important applications of matrix theory to the field of economics is the study of the

More information

Trend-Cycle Decompositions

Trend-Cycle Decompositions Trend-Cycle Decompositions Eric Zivot April 22, 2005 1 Introduction A convenient way of representing an economic time series y t is through the so-called trend-cycle decomposition y t = TD t + Z t (1)

More information

Heteroskedasticity. We now consider the implications of relaxing the assumption that the conditional

Heteroskedasticity. We now consider the implications of relaxing the assumption that the conditional Heteroskedasticity We now consider the implications of relaxing the assumption that the conditional variance V (u i x i ) = σ 2 is common to all observations i = 1,..., In many applications, we may suspect

More information