Threshold models: Basic concepts and new results
|
|
- Noah Kennedy
- 5 years ago
- Views:
Transcription
1 Threshold models: Basic concepts and new results 1 1 Department of Economics National Taipei University PCCU, Taipei, 2009
2 Outline
3 1 Structural Change Model (Chow 1960; Bai 1995)
4 1 Structural Change Model (Chow 1960; Bai 1995) { β1 x y t = t + u t if t T 1 β 2 x t + u t if t > T 1
5 1 Structural Change Model (Chow 1960; Bai 1995) { β1 x y t = t + u t if t T 1 β 2 x t + u t if t > T 1 2 Markov Switching Model (Hamilton 1989)
6 1 Structural Change Model (Chow 1960; Bai 1995) { β1 x y t = t + u t if t T 1 β 2 x t + u t if t > T 1 2 Markov Switching Model (Hamilton 1989) 3 Threshold Model (Tong 1978, 1983, 1990)
7 1 Structural Change Model (Chow 1960; Bai 1995) { β1 x y t = t + u t if t T 1 β 2 x t + u t if t > T 1 2 Markov Switching Model (Hamilton 1989) 3 Threshold Model (Tong 1978, 1983, 1990) { β1 y y t = t 1 + u t if y t 1 c β 2 y t 1 + u t if y t 1 > c
8 Threshold Autoregressive models Basic Threshold Autoregressive model is as following: { β1 x y t = t + u t if z t c β 2 x t + u t if z t > c If the threshold variable z t is equal to lagged dependent variable y t 1, it is called Self-exciting autoregressive model { β1 y y t = t 1 + u t if y t 1 c β 2 y t 1 + u t if y t 1 > c
9 Basic Assumptions 1 u t is i.i.d. mean-zero sequence with a bound density function, and E u t 2γ < for some γ > 2. 2 β 1 1 and β 2 < 1 or β 1 < 1 and β 2 1 Under these assumptions satisfied, SETAR model will be stationary.
10 Smooth transition SETAR models Consider the threshold models as below: y t = β 1 y t 1 + β 2 y t 1 G(y t 1, θ) + u t We use a smooth function to make sure threshold models continuous at threshold value θ. Generally the transition functions considered in literature are 1 Logistic distribution (LSTAR model) G(y t 1, θ) = [1 + exp(κ(y t 1 c))] 1 2 Exponential distribution (ESTAR model) G(y t 1, θ) = 1 exp( κ(y t 1 c) 2 )
11 Threshold models under different types of data Cross section data { β1 x y t = t + u t if z t c β 2 x t + u t if z t > c Time series data { β1 y y t = t 1 + u t if y t 1 c β 2 y t 1 + u t if y t 1 > c Panel data { β1 y y it = it 1 + u it if y it 1 c β 2 y it 1 + u it if y it 1 > c
12 Specification tests for threshold autoregressive model Test for nonlinearity If we have accurate threshold value c, 1 Chow (1960) test 2 Ramsey (1969) RESET test 3 CUSUM test If we need to estimate threshold value c in advance, 1 Ramsey (1969) RESET test 2 CUSUM test
13 SETAR model vs. linear model (Davies 1977, 1987, Andrews and Ploberger 1991) Estimate unrestricted equation y t = β 1 y t 1 I(y t 1 c) + β 2 y t 1 I(y t 1 > c) + u t and restricted equation y t = β 1 y t 1 + u 1t. Calculate regression variance ˆσ 2 and σ 2 for two equations. The F-test can be obtain as below: ( σ(c) 2 ˆσ(c) 2 ) F n (c) = n ˆσ(c) 2
14 LSTAR model vs. ESTAR model (Luukkonen, Saikkonen and Teräsvirta 1988; Granger and Teräsvirta 1993) Auxiliary regression y t = θ 0 + θ 1 y t 1 + θ 2 y 2 t 1 + θ 3y 3 t 1 + θ 4y 4 t 1 + ɛ t (1) We use sequential method to test LSTAR and ESTAR models. 1 If We reject H LSTAR4 : θ 4 = 0, LSTAR model will be choose. 2 If We accept H LSTAR4 : θ 4 = 0 and reject H ESTAR3 : θ 3 = 0 θ 4 = 0, ESTAR model will be choose. 3 If We accept H LSTAR4 : θ 4 = 0 and H ESTAR3 : θ 3 = 0 θ 4 = 0 and reject H ESTAR3 : θ 2 = 0 θ 3 = θ 4 = 0, ESTAR model will be choose.
15 Estimation for threshold model How to obtain consistent estimator for threshold value c? Concentrated least square method (Bai 1996) Estimate the threshold value ĉ by minimizing a concentrated two stage least square criterion S n (γ) = n (y i β 1 (c)x i I(q i c) β 2 (c)x i I(q i > c)) 2 i=1
16 After c obtained, the consistent coefficients can be estimated by Cross section case 1 Nonlinear least square methods 2 Instrument variable methods (Caner and Hansen 2004) 3 LAD methods (Caner and Hansen 2002) Time series case 1 Nonlinear least square method
17 Basic Concepts Consider the SETAR model u t if c 1 y t 1 c 2 y t = ϕ 1 (y t 1 c 1 ) + u t if y t 1 < c 1 (2) ϕ 2 (y t 1 c 2 ) + u t if y t 1 > c 2 If we want to detect whether the true data generation process is I(1), we need test H 0 : ϕ 1 = ϕ 2 = 0. Pippenger and Goering (1993) find ADF test with low power for nonlinear alternative.
18 Basic Concepts Under null hypothesis satisfied, Equation (2) is equal to I(1) process. The threshold value c cannot be identified (Davies 1977, 1987). The method to solve Davies problem is to find all possible threshold values. Calculate all ADF statistic critical values under different threshold values and find a smallest one.
19 When we consider possible threshold value, there are two possible setting in threshold value space. 1 fixed space (González and Gonzalo 1997; Berben and van Dijk 1999, Caner and Hansen 2001, Seo 2004): c C, C is fixed. 2 Adaptive space (Bec, Ben Salem and Carrasco 2004, Bec, Guay and Guerre 2004, Park and Shintani 2005, de Jong, Wang and Bae 2007): c C, the upper and lower bounds of C grow at rate T 1/2.
20 From the different consideration about residual structure. 1 u t is martingale difference sequence: infimum Dickey-Fuller test (González and Gonzalo 1997; Berben and van Dijk 1999, Caner and Hansen 2001, Seo 2004) 2 u t is weakly stationary sequence: infimum ADF test (Park and Shintani 2005) or infimum Phillips-Perron test (de Jong, Wang and Bae 2007)
21 Threshold unit root tests for smooth transition models Consider the smooth transition model y t = ρy t 1 G(y t 1, θ) + u t Nonlinear least square methods (Park and Shintani 2005) to estimate coefficients and test whether H 0 : ρ = 0. Use Taylor expansion to expend G(y t 1, θ) 1 Exponential STAR model (G(y t 1, θ) = 1 exp( κy 2 t 1 )) y t = φy 3 t 1 + ɛ t Detect H 0 : φ = 0. 2 Logistic STAR model (G(y t 1, θ) = [1 + exp(κ(y t 1 c))] 1 )
22 Use Taylor expansion Test H 0 : θ 1 = θ 2 = 0 y t = θ 1 y t 1 + θ 2 y 2 t 1 + u t
23 Panel threshold model Hansen (1999) propose panel threshold model for a balanced panel. y it = β 1 x it I(q it c) + β 2 x it I(q it > c) + µ i + u it (3) He uses concentrate least square to search c. After c obtained, fixed effect transformation is used. The estimated coefficients are consistent with fixed T as n.
24 Panel smooth transition threshold unit root tests If the panel smooth threshold model with continuous transition function, Exponential distribution function 1 Chiang, Kuan and Lo 2006 y it = ρ i y it 1 [1 exp( c i y 2 it 1)] + u it Using Taylor expansion and ADF statistic to test H 0 : φ i = 0 i ki y it = φ i yit π ij y it j + ɛ it j=1 2 Cerrato, de Peretti and Sarantis 2007 y it = ρ i y it 1 [1 exp( c i y 2 it 1)] + u it u it = λ i f t + e it
25 Use Pesaran (2007) panel unit root test for cross section dependence k i y it = φ i yit hiȳ3 it 1 + g ij ȳ it j + π ij y it j + ɛ it j=0 k i j=1 Logistic distribution function He and Sandberg (2006) consider LSTAR model. They use Taylor expansion to rewrite original LSTAR model y it = α i + δ i y it 1 + ρ(y it 1 )y it 1 + ũ it Test H 0 : δ i = 0 i and ρ(y it ) = 1.
26 Estimation for panel threshold model 1 Hansen (1999) Fixed effect transformation methods 2 Shin (2006), Gørgens, Skeel and Würtz (2008) GMM approach.
27 1 Multivariate Error Correction Approach (Balke and Fomby 1997, Hansen and Seo 2002, Seo 2006)
28 1 Multivariate Error Correction Approach (Balke and Fomby 1997, Hansen and Seo 2002, Seo 2006) y 1t = βy 2t + z t y 2t = ɛ 2t z t = ρ 1 z t 1 I(q t 1 γ) + ρ 2 z t 1 I(q t 1 > γ) + ɛ 1t
29 1 Multivariate Error Correction Approach (Balke and Fomby 1997, Hansen and Seo 2002, Seo 2006) y 1t = βy 2t + z t y 2t = ɛ 2t z t = ρ 1 z t 1 I(q t 1 γ) + ρ 2 z t 1 I(q t 1 > γ) + ɛ 1t Y t = Π 1 Y t 1 I(q t 1 γ) + Π 2 Y t 1 I(q t 1 > γ) + ɛ t
30 1 Multivariate Error Correction Approach (Balke and Fomby 1997, Hansen and Seo 2002, Seo 2006) y 1t = βy 2t + z t y 2t = ɛ 2t z t = ρ 1 z t 1 I(q t 1 γ) + ρ 2 z t 1 I(q t 1 > γ) + ɛ 1t 2 Single equation Approach (Arai 2004, Gonzalo and Pitarakis , Saikkonen 2008, Saikkonen and Choi 2004)
31 1 Multivariate Error Correction Approach (Balke and Fomby 1997, Hansen and Seo 2002, Seo 2006) y 1t = βy 2t + z t y 2t = ɛ 2t z t = ρ 1 z t 1 I(q t 1 γ) + ρ 2 z t 1 I(q t 1 > γ) + ɛ 1t 2 Single equation Approach (Arai 2004, Gonzalo and Pitarakis , Saikkonen 2008, Saikkonen and Choi 2004) { y1t = βy 2t + γy 2t g(y 2t ; θ) + ɛ 1t y 2t = ɛ 2t
32 Estimation of threshold cointegration In threshold cointegration model, We use concentrate least square to estimate Π 1, Π 2 and γ 1 Given γ, the least squares estimators are ˆΠ 1 (γ) = Y t Z 1 (Z 1 Z 1 ) 1 and ˆΠ 1 (γ) = Y t Z 2 (Z 2 Z 2 ) 1, where Z 1 = Y t 1 I(q t 1 γ) and Z 2 = Y t 1 I(q t 1 > γ). 2 Calculate γ with arg min γ U U, where U = Y ˆΠ 1 (γ)z 1 ˆΠ 2 (γ)z 2. 3 Substitute ˆγ into threshold error correction model to get ˆΠ 1 and ˆΠ 2.
33 Testing for threshold cointegration models 1 Threshold cointegration against linear cointegration (Hansen and Seo 2002) Y t = Π 1 Y t 1 I(q t 1 γ) + Π 2 Y t 1 I(q t 1 > γ) + ɛ t The null hypothesis is H 0 : Π 1 = Π 2 (linear cointegration). This test is a LM-type test. 2 Threshold cointegration against no cointegration (Seo 2007) Y t = Π 1 Y t 1 I(q t 1 γ) + Π 2 Y t 1 I(q t 1 > γ) + ɛ t The null hypothesis is H 0 : Π 1 = Π 2 = 0 (no cointegration).
34 Threshold model with endogenous threshold variable Consider the threshold model { β1 x y i = i + u i if q i γ β 2 x i + u i if q i > γ (4) If we want to obtain consistent estimators of β 1 and β 2, q t cannot be correlated with u t. If q t is correlated with u t, we need new method to estimate β 1 and β 2.
35 Bias-Correction Estimator for endogenous threshold models Kourtellos, Stengos and Tan (2007) consider a threshold model with endogenous threshold variables like Equation(4). { xi β y i = 1 + u i if q i γ x i β 2 + u i if q i > γ (5) y i, x i, z i are exogenous variables. q i is an endogenous variable. The selection equation is q i = z i π + υ i. (6)
36 Define the indicator variable { 1 iff υi γ z I i = i π 0 iff υ i > γ z i π The joint distribution between u i and υ i is defined as ( ) ( ( ) ) ui σ 2 x i, z i N 0 u σ uɛ σ uɛ 1 υ i Use the relationship between u i and ɛ i. ( ) ( ) ( ɛi 1 σuυ ui = 0 1 υ i υ i )
37 Let κ 1 = σ uυ = ρ 1 σ u, and define u i = κ 1 υ i + ɛ i = κ 1 λ 1i (γ z i π) + e i where λ 1i (γ z i π) = φ(γ z i π) Φ(γ z i π) (Inverse Mills bias correction item). We may get conditional expectations for each of the regimes. E(y x 1, z 1, υ i γ z i π) = x i β 1 + κ 1 λ 1i (γ z i π) E(y x 2, z 2, υ i > γ z i π) = x i β 2 + κ 1 λ 2i (γ z i π)
38 When two regimes have the same error structure, THRET model can be estimate by y i = x i β 2 + x i (γ)ϕ + κλ i (γ z i π) + e i, (7) where x i (γ) = x i I(q i γ) and ϕ = β 2 β 1. This estimation method looks like sample-selection model. The main difference about these two model is THRET model using all data.
39 Estimation of Threshold model with endogenous threshold variable Kourtellos, Stengos and Tan (2007) use three steps to obtain consistent estimator. 1 Estimate the parameter vector π in Equation (6) by least square. 2 Estimate the threshold value ˆγ by minimizing a concentrated two stage least square criterion using ˆπ from first stage. n S n (γ) = (y i x i β 1 x i (γ)ϕ κλ i (γ z i ˆπ)) 2. i=1 3 Estimate the lease square estimates of the slop parameters based on the split samples implied by ˆγ.
40 Threshold regression with endogenous threshold and slop models When threshold model with endogenous threshold value and regressors, we need to use instrumental variables. Consider THRET model { xi β y i = 1 + u i if q i γ x i β 2 + u i if q i > γ (8) q i = z i Γ + υ i. (9) where x i = (x 1i x 2i ). x 1i is endogenous variable. We need z i = (z 1i x 2i ).
41 1 Estimate the parameter vector π in Equation (9) by least square. 2 Estimate the threshold value ˆγ by minimizing a concentrated two stage least square criterion using ˆπ from first stage. S n (γ) = n (y i ˆx i β 1 ˆx i (γ)ϕ κλ i (γ z i ˆπ)) 2. i=1 3 Estimate the lease square estimates of the slop parameters based on the split samples implied by ˆγ.
42 panel threshold model with endogenous threshold variable Consider a panel threshold model with endogenous threshold value: y it = x it I(q it γ)β 1 + x it I(q it > γ)β 2 + η i + e it (10) q it = z it π + u it. (11) Under n and T fixed, we may derive consistent estimators for β 1 and β 2.
43 Basic Assumptions 1 Assumption 1: {y it, x it, q it, e it } is strictly stationary, ergodic. 2 Assumption 2: {y it, x it, q it, e it : 1 i n, 1 t T } are from balanced panel data 3 Assumption 3: u it z it N (0, 1) 4 Assumption 4 : The joint distribution between e it and u it is defined as: [ eit u it ] ( x it, z it N 0, [ σ 2 e γ j γ j 1 ] ), where γ j is covariance between e it and u it, γ j = γ 1 when q it θ and γ j = γ 2 when q it > θ. 5 Assumption 5: n and T is fixed.
44 Estimation of panel threshold model with endogenous threshold variable Using first difference transformation to eliminate fixed effect η i in Equation (10). Estimate the parameter vector π in Equation (11) by least square. Estimate the threshold value ˆγ by minimizing a concentrated two stage least square criterion using ˆπ from first stage. n S n (γ) = ( y i (x it I(q it γ) x it 1 I(q it 1 γ))β 1 i=1 (x it I(q it > γ) x it 1 I(q it 1 > γ))β 2 κλ i (γ z i ˆπ)) 2.
45 Estimate the lease square estimates of the slop parameters based on the split samples implied by ˆγ. Why not use fixed effect transformation? Because fixed effect transformation will generate heteroskedasticity under T small. E(u it ū i )(u is ū i ) = σ2 u T. We plan to expend this panel threshold model to dynamic panel data model.
46 Future study and possible problems Panel threshold unit root case. Panel smooth transition threshold model
Regime switching models
Regime switching models Structural change and nonlinearities Matthieu Stigler Matthieu.Stigler at gmail.com April 30, 2009 Version 1.1 This document is released under the Creative Commons Attribution-Noncommercial
More informationEstimation of Threshold Cointegration
Estimation of Myung Hwan London School of Economics December 2006 Outline Model Asymptotics Inference Conclusion 1 Model Estimation Methods Literature 2 Asymptotics Consistency Convergence Rates Asymptotic
More informationPanel Threshold Regression Models with Endogenous Threshold Variables
Panel Threshold Regression Models with Endogenous Threshold Variables Chien-Ho Wang National Taipei University Eric S. Lin National Tsing Hua University This Version: June 29, 2010 Abstract This paper
More informationThreshold Effects in Multivariate Error Correction Models
hreshold Effects in Multivariate Error Correction Models Jesùs Gonzalo Universidad Carlos III de Madrid Department of Economics jgonzalo@elrond.uc3m.es and Jean-Yves Pitarakis University of Southampton
More informationThreshold Effects in Multivariate Error Correction Models
hreshold Effects in Multivariate Error Correction Models Jesùs Gonzalo Universidad Carlos III de Madrid Jean-Yves Pitarakis University of Southampton Abstract In this paper we propose a testing procedure
More informationEconometric Methods for Panel Data
Based on the books by Baltagi: Econometric Analysis of Panel Data and by Hsiao: Analysis of Panel Data Robert M. Kunst robert.kunst@univie.ac.at University of Vienna and Institute for Advanced Studies
More informationTime 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 informationTechnical Appendix-3-Regime asymmetric STAR modeling and exchange rate reversion
Technical Appendix-3-Regime asymmetric STAR modeling and exchange rate reversion Mario Cerrato*, Hyunsok Kim* and Ronald MacDonald** 1 University of Glasgow, Department of Economics, Adam Smith building.
More informationMEI Exam Review. June 7, 2002
MEI Exam Review June 7, 2002 1 Final Exam Revision Notes 1.1 Random Rules and Formulas Linear transformations of random variables. f y (Y ) = f x (X) dx. dg Inverse Proof. (AB)(AB) 1 = I. (B 1 A 1 )(AB)(AB)
More informationEconometric modeling of the relationship among macroeconomic variables of Thailand: Smooth transition autoregressive regression model
The Empirical Econometrics and Quantitative Economics Letters ISSN 2286 7147 EEQEL all rights reserved Volume 1, Number 4 (December 2012), pp. 21 38. Econometric modeling of the relationship among macroeconomic
More informationIs the Basis of the Stock Index Futures Markets Nonlinear?
University of Wollongong Research Online Applied Statistics Education and Research Collaboration (ASEARC) - Conference Papers Faculty of Engineering and Information Sciences 2011 Is the Basis of the Stock
More informationTime 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 informationMoreover, the second term is derived from: 1 T ) 2 1
170 Moreover, the second term is derived from: 1 T T ɛt 2 σ 2 ɛ. Therefore, 1 σ 2 ɛt T y t 1 ɛ t = 1 2 ( yt σ T ) 2 1 2σ 2 ɛ 1 T T ɛt 2 1 2 (χ2 (1) 1). (b) Next, consider y 2 t 1. T E y 2 t 1 T T = E(y
More informationEconometrics of Panel Data
Econometrics of Panel Data Jakub Mućk Meeting # 9 Jakub Mućk Econometrics of Panel Data Meeting # 9 1 / 22 Outline 1 Time series analysis Stationarity Unit Root Tests for Nonstationarity 2 Panel Unit Root
More informationAdaptive Consistent Unit Root Tests Based on Autoregressive Threshold Model
Adaptive Consistent Unit Root ests Based on Autoregressive hreshold Model Frédérique Bec Alain Guay Emmanuel Guerre January 2004 first version: February 2002) Abstract his paper aims to understand how
More informationUniversity of Kent Department of Economics Discussion Papers
University of Kent Department of Economics Discussion Papers Testing for Granger (non-) Causality in a Time Varying Coefficient VAR Model Dimitris K. Christopoulos and Miguel León-Ledesma January 28 KDPE
More informationTesting for a Unit Root in the Asymmetric Nonlinear Smooth Transition Framework
Testing for a Unit Root in the Asymmetric Nonlinear Smooth Transition Framework Razvan Pascalau Department of Economics, Finance and Legal Studies University of Alabama November 8, 7 Abstract This paper
More informationSaskia Rinke and Philipp Sibbertsen* Information criteria for nonlinear time series models
Stud. Nonlinear Dyn. E. 16; (3): 35 341 Saskia Rinke and Philipp Sibbertsen* Information criteria for nonlinear time series models DOI 1.1515/snde-15-6 Abstract: In this paper the performance of different
More informationUnit root tests for ESTAR models
University of Wollongong Research Online Centre for Statistical & Survey Methodology Working Paper Series Faculty of Engineering and Information Sciences 20 Unit root tests for ESAR models Heni Puspaningrum
More informationTesting 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 informationLM-Tests for Linearity Against Smooth Transition Alternatives: A Bootstrap Simulation Study
LM-Tests for Linearity Against Smooth Transition Alternatives: A Bootstrap Simulation Study Jonathan B. Hill Dept. of Economics Florida International University July 5, 2004 Abstract The universal method
More informationFORECASTING PERFORMANCE OF LOGISTIC STAR MODEL - AN ALTERNATIVE VERSION TO THE ORIGINAL LSTAR MODELS. Olukayode, A. Adebile and D ahud, K, Shangodoyin
FORECASTING PERFORMANCE OF LOGISTIC STAR MODEL - AN ALTERNATIVE VERSION TO THE ORIGINAL LSTAR MODELS Olukayode, A. Adebile and D ahud, K, Shangodoyin Abstract This paper proposes an alternative representation
More informationVector Auto-Regressive Models
Vector Auto-Regressive Models Laurent Ferrara 1 1 University of Paris Nanterre M2 Oct. 2018 Overview of the presentation 1. Vector Auto-Regressions Definition Estimation Testing 2. Impulse responses functions
More informationFinal Exam November 24, Problem-1: Consider random walk with drift plus a linear time trend: ( t
Problem-1: Consider random walk with drift plus a linear time trend: y t = c + y t 1 + δ t + ϵ t, (1) where {ϵ t } is white noise with E[ϵ 2 t ] = σ 2 >, and y is a non-stochastic initial value. (a) Show
More informationVAR Models and Applications
VAR Models and Applications Laurent Ferrara 1 1 University of Paris West M2 EIPMC Oct. 2016 Overview of the presentation 1. Vector Auto-Regressions Definition Estimation Testing 2. Impulse responses functions
More informationECON 4160, Spring term Lecture 12
ECON 4160, Spring term 2013. Lecture 12 Non-stationarity and co-integration 2/2 Ragnar Nymoen Department of Economics 13 Nov 2013 1 / 53 Introduction I So far we have considered: Stationary VAR, with deterministic
More informationNonstationary Panels
Nonstationary Panels Based on chapters 12.4, 12.5, and 12.6 of Baltagi, B. (2005): Econometric Analysis of Panel Data, 3rd edition. Chichester, John Wiley & Sons. June 3, 2009 Agenda 1 Spurious Regressions
More informationThis chapter reviews properties of regression estimators and test statistics based on
Chapter 12 COINTEGRATING AND SPURIOUS REGRESSIONS This chapter reviews properties of regression estimators and test statistics based on the estimators when the regressors and regressant are difference
More informationEconometrics. Week 11. Fall Institute of Economic Studies Faculty of Social Sciences Charles University in Prague
Econometrics Week 11 Institute of Economic Studies Faculty of Social Sciences Charles University in Prague Fall 2012 1 / 30 Recommended Reading For the today Advanced Time Series Topics Selected topics
More informationNon-linear unit root testing with arctangent trend: Simulation and applications in finance
STATISTICS RESEARCH ARTICLE Non-linear unit root testing with arctangent trend: Simulation and applications in finance Deniz Ilalan 1 * and Özgür Özel 2 Received: 24 October 2017 Accepted: 18 March 2018
More informationNonlinear Error Correction Model and Multiple-Threshold Cointegration May 23, / 31
Nonlinear Error Correction Model and Multiple-Threshold Cointegration Man Wang Dong Hua University, China Joint work with N.H.Chan May 23, 2014 Nonlinear Error Correction Model and Multiple-Threshold Cointegration
More informationFinancial Econometrics
Financial Econometrics Nonlinear time series analysis Gerald P. Dwyer Trinity College, Dublin January 2016 Outline 1 Nonlinearity Does nonlinearity matter? Nonlinear models Tests for nonlinearity Forecasting
More informationQuestions and Answers on Unit Roots, Cointegration, VARs and VECMs
Questions and Answers on Unit Roots, Cointegration, VARs and VECMs L. Magee Winter, 2012 1. Let ɛ t, t = 1,..., T be a series of independent draws from a N[0,1] distribution. Let w t, t = 1,..., T, be
More informationNon-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 informationTesting Common Nonlinear Features in Vector Nonlinear Autoregressive Models
Working papers in transport, tourism, information technology and microdata analysis Testing Common Nonlinear Features in Vector Nonlinear Autoregressive Models Dao Li Changli He Editor: Hasan Fleyeh Nr:
More informationStudies in Nonlinear Dynamics and Econometrics
Studies in Nonlinear Dynamics and Econometrics Quarterly Journal April 1997, Volume, Number 1 The MIT Press Studies in Nonlinear Dynamics and Econometrics (ISSN 1081-186) is a quarterly journal published
More informationProf. 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 informationSystem-Equation ADL Tests for Threshold Cointegration
System-Equation ADL Tests for Threshold Cointegration Jing Li Department of Economics South Dakota State University. Abstract In this paper we develop new system-equation tests for threshold cointegration
More informationEcon 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 informationCentral Bank of Chile October 29-31, 2013 Bruce Hansen (University of Wisconsin) Structural Breaks October 29-31, / 91. Bruce E.
Forecasting Lecture 3 Structural Breaks Central Bank of Chile October 29-31, 2013 Bruce Hansen (University of Wisconsin) Structural Breaks October 29-31, 2013 1 / 91 Bruce E. Hansen Organization Detection
More informationThe ENSO Effect on World Wheat Market Dynamics: Smooth Transitions in Asymmetric Price Transmission
The ENSO Effect on World Wheat Market Dynamics: Smooth Transitions in Asymmetric Price Transmission David Ubilava Lecturer in the School of Economics at the University of Sydney david.ubilava@sydney.edu.au
More informationUnit Root Tests in Three-Regime SETAR Models
Unit Root ests in hree-regime SEAR Models George Kapetanios Department of Economics, Queen Mary, University of London Yongcheol Shin School of Economics, University of Edinburgh his Version, November 23
More informationPurchasing power parity: A nonlinear multivariate perspective. Abstract
Purchasing power parity: A nonlinear multivariate perspective Frédérique Bec THEMA, University of Cergy-Pontoise and CREST, France Mélika Ben Salem OEP, Paris-Est University and LEA-INRA (PSE), France
More informationEC821: Time Series Econometrics, Spring 2003 Notes Section 9 Panel Unit Root Tests Avariety of procedures for the analysis of unit roots in a panel
EC821: Time Series Econometrics, Spring 2003 Notes Section 9 Panel Unit Root Tests Avariety of procedures for the analysis of unit roots in a panel context have been developed. The emphasis in this development
More informationEconometrics. Week 4. Fall Institute of Economic Studies Faculty of Social Sciences Charles University in Prague
Econometrics Week 4 Institute of Economic Studies Faculty of Social Sciences Charles University in Prague Fall 2012 1 / 23 Recommended Reading For the today Serial correlation and heteroskedasticity in
More informationECON 4160, Lecture 11 and 12
ECON 4160, 2016. Lecture 11 and 12 Co-integration Ragnar Nymoen Department of Economics 9 November 2017 1 / 43 Introduction I So far we have considered: Stationary VAR ( no unit roots ) Standard inference
More informationApplication of Smooth Transition autoregressive (STAR) models for. Exchange Rate
Application of Smooth Transition autoregressive (STAR) models for Exchange Rate Muhammad Tayyab 1, Ayesha Tarar 2 and Madiha Riaz 3* 1. Assistant Executive Engineer,Resignalling Project, Pakistan 2. Lecturer
More informationThe Power of Unit Root Tests Against Nonlinear Local Alternatives
The Power of Unit Root Tests Against Nonlinear Local Alternatives Matei Demetrescu a and Robinson Kruse b a University of Bonn b CREATES, Aarhus University May 23, 2 Abstract This article extends the analysis
More informationGoodness-of-Fit Tests for Time Series Models: A Score-Marked Empirical Process Approach
Goodness-of-Fit Tests for Time Series Models: A Score-Marked Empirical Process Approach By Shiqing Ling Department of Mathematics Hong Kong University of Science and Technology Let {y t : t = 0, ±1, ±2,
More informationPanel unit root and cointegration methods
University of Vienna, Dept. of Economics Master in Economics Vienna 2010 Outline of the talk (1) Unit root, cointegration and estimation in time series. 1a) Unit Root tests (Dickey-Fuller Test, 1979);
More informationChristopher Dougherty London School of Economics and Political Science
Introduction to Econometrics FIFTH EDITION Christopher Dougherty London School of Economics and Political Science OXFORD UNIVERSITY PRESS Contents INTRODU CTION 1 Why study econometrics? 1 Aim of this
More informationA radial basis function artificial neural network test for neglected nonlinearity
Econometrics Journal (2003), volume 6, pp. 357 373. A radial basis function artificial neural network test for neglected nonlinearity ANDREW P. BLAKE AND GEORGE KAPETANIOS Centre for Central Banking Studies,
More informationEmpirical Market Microstructure Analysis (EMMA)
Empirical Market Microstructure Analysis (EMMA) Lecture 3: Statistical Building Blocks and Econometric Basics Prof. Dr. Michael Stein michael.stein@vwl.uni-freiburg.de Albert-Ludwigs-University of Freiburg
More informationEvaluating the carbon-macroeconomy relationship
Evaluating the carbon-macroeconomy relationship Julien Chevallier Université Paris Dauphine (CGEMP/LEDa) This presentation: February 2011 The Usual Suspects 115 EU 27 Seasonally Adjusted Industrial Production
More informationAdvanced 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 informationEfficient Estimation of Non-Linear Dynamic Panel Data Models with Application to Smooth Transition Models
Efficient Estimation of Non-Linear Dynamic Panel Data Models with Application to Smooth Transition Models Tue Gørgens Christopher L. Skeels Allan H. Würtz February 16, 2008 Preliminary and incomplete.
More informationAdvanced 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 16, 2013 Outline Univariate
More informationNon-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 informationThe Role of "Leads" in the Dynamic Title of Cointegrating Regression Models. Author(s) Hayakawa, Kazuhiko; Kurozumi, Eiji
he Role of "Leads" in the Dynamic itle of Cointegrating Regression Models Author(s) Hayakawa, Kazuhiko; Kurozumi, Eiji Citation Issue 2006-12 Date ype echnical Report ext Version publisher URL http://hdl.handle.net/10086/13599
More informationEconomics 536 Lecture 7. Introduction to Specification Testing in Dynamic Econometric Models
University of Illinois Fall 2016 Department of Economics Roger Koenker Economics 536 Lecture 7 Introduction to Specification Testing in Dynamic Econometric Models In this lecture I want to briefly describe
More informationNon-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 informationEconomic modelling and forecasting. 2-6 February 2015
Economic modelling and forecasting 2-6 February 2015 Bank of England 2015 Ole Rummel Adviser, CCBS at the Bank of England ole.rummel@bankofengland.co.uk Philosophy of my presentations Everything should
More informationDarmstadt Discussion Papers in Economics
Darmstadt Discussion Papers in Economics The Effect of Linear Time Trends on Cointegration Testing in Single Equations Uwe Hassler Nr. 111 Arbeitspapiere des Instituts für Volkswirtschaftslehre Technische
More informationA PANIC Attack on Unit Roots and Cointegration. July 31, Preliminary and Incomplete
A PANIC Attack on Unit Roots and Cointegration Jushan Bai Serena Ng July 3, 200 Preliminary and Incomplete Abstract his paper presents a toolkit for Panel Analysis of Non-stationarity in Idiosyncratic
More informationBayesian Inference for a Threshold Autoregression with a Unit Root
Bayesian Inference for a Threshold Autoregression with a Unit Root Penelope Smith Melbourne Institute The University of Melbourne Parkville, VIC 3010 September 1, 2005 Abstract A Bayesian approach to distinguishing
More informationEstimation and Inference in Threshold Type Regime Switching Models
Estimation and Inference in Threshold Type Regime Switching Models Jesús Gonzalo Universidad Carlos III de Madrid Department of Economics Calle Madrid 126 28903 Getafe (Madrid) - Spain Jean-Yves Pitarakis
More informationRegression 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 informationNews Shocks: Different Effects in Boom and Recession?
News Shocks: Different Effects in Boom and Recession? Maria Bolboaca, Sarah Fischer University of Bern Study Center Gerzensee June 7, 5 / Introduction News are defined in the literature as exogenous changes
More informationModelling of Economic Time Series and the Method of Cointegration
AUSTRIAN JOURNAL OF STATISTICS Volume 35 (2006), Number 2&3, 307 313 Modelling of Economic Time Series and the Method of Cointegration Jiri Neubauer University of Defence, Brno, Czech Republic Abstract:
More informationThema Working Paper n Université de Cergy Pontoise, France
Thema Working Paper n 2012-25 Université de Cergy Pontoise, France Are Southeast Asian Real Exchange Rates Mean Reverting? Frédérique Bec Songlin zeng February, 2012 Are Southeast Asian Real Exchange Rates
More informationFinancial Time Series Analysis: Part II
Department of Mathematics and Statistics, University of Vaasa, Finland Spring 2017 1 Unit root Deterministic trend Stochastic trend Testing for unit root ADF-test (Augmented Dickey-Fuller test) Testing
More informationTitle. Description. Quick start. Menu. stata.com. xtcointtest Panel-data cointegration tests
Title stata.com xtcointtest Panel-data cointegration tests Description Quick start Menu Syntax Options Remarks and examples Stored results Methods and formulas References Also see Description xtcointtest
More informationEC408 Topics in Applied Econometrics. B Fingleton, Dept of Economics, Strathclyde University
EC48 Topics in Applied Econometrics B Fingleton, Dept of Economics, Strathclyde University Applied Econometrics What is spurious regression? How do we check for stochastic trends? Cointegration and Error
More informationUnit Roots in Time Series with Changepoints
International Journal of Statistics and Probability; Vol. 6, No. 6; November 2017 ISSN 1927-7032 E-ISSN 1927-7040 Published by Canadian Center of Science and Education Unit Roots in Time Series with Changepoints
More informationSteven Cook University of Wales Swansea. Abstract
On the finite sample power of modified Dickey Fuller tests: The role of the initial condition Steven Cook University of Wales Swansea Abstract The relationship between the initial condition of time series
More informationDetecting Mean Reversion in Real Exchange Rates from a Multiple Regime star Model
ANNALS OF ECONOMICS AND SAISICS NUMBER 99/, october/december DOI.// Detecting Mean Reversion in Real Exchange Rates Frédérique Bec thema-university of Cergy-Pontoise and crest Mélika Ben Salem cee and
More informationEconometrics of Panel Data
Econometrics of Panel Data Jakub Mućk Meeting # 6 Jakub Mućk Econometrics of Panel Data Meeting # 6 1 / 36 Outline 1 The First-Difference (FD) estimator 2 Dynamic panel data models 3 The Anderson and Hsiao
More informationØkonomisk Kandidateksamen 2004 (I) Econometrics 2. Rettevejledning
Økonomisk Kandidateksamen 2004 (I) Econometrics 2 Rettevejledning This is a closed-book exam (uden hjælpemidler). Answer all questions! The group of questions 1 to 4 have equal weight. Within each group,
More informationReview of Econometrics
Review of Econometrics Zheng Tian June 5th, 2017 1 The Essence of the OLS Estimation Multiple regression model involves the models as follows Y i = β 0 + β 1 X 1i + β 2 X 2i + + β k X ki + u i, i = 1,...,
More informationSMOOTH TRANSITION AUTOREGRESSIVE MODELS
SMOOTH TRANSITION AUTOREGRESSIVE MODELS A STUDY OF THE INDUSTRIAL PRODUCTION INDEX OF SWEDEN A Thesis By Jia Zhou Supervisor: Anders Ågren Department of Statistics Submitted in partial fulfillment of the
More informationUnit Root and Cointegration
Unit Root and Cointegration Carlos Hurtado Department of Economics University of Illinois at Urbana-Champaign hrtdmrt@illinois.edu Oct 7th, 016 C. Hurtado (UIUC - Economics) Applied Econometrics On the
More informationStationary and nonstationary variables
Stationary and nonstationary variables Stationary variable: 1. Finite and constant in time expected value: E (y t ) = µ < 2. Finite and constant in time variance: Var (y t ) = σ 2 < 3. Covariance dependent
More informationUnit Root Tests for Panels in the Presence of Short-run and Long-run Dependencies: Nonlinear IV Approach with Fixed N and Large T 1
Unit Root Tests for Panels in the Presence of Short-run and Long-run Dependencies: Nonlinear IV Approach with Fixed N and Large T 1 Yoosoon Chang Department of Economics Rice University Wonho Song Korea
More informationBagging and Forecasting in Nonlinear Dynamic Models
DBJ Discussion Paper Series, No.0905 Bagging and Forecasting in Nonlinear Dynamic Models Mari Sakudo (Research Institute of Capital Formation, Development Bank of Japan, and Department of Economics, Sophia
More informationHomogenous vs. Heterogenous Transition Functions in Smooth Transition Regressions A LM-Type Test
Homogenous vs. Heterogenous Transition Functions in Smooth Transition Regressions A LM-Type Test Matei Demetrescu Julian S. Leppin Stefan Reitz This version: August 2017 Abstract Panel Smooth Transition
More informationUnit roots in vector time series. Scalar autoregression True model: y t 1 y t1 2 y t2 p y tp t Estimated model: y t c y t1 1 y t1 2 y t2
Unit roots in vector time series A. Vector autoregressions with unit roots Scalar autoregression True model: y t y t y t p y tp t Estimated model: y t c y t y t y t p y tp t Results: T j j is asymptotically
More informationResponse surface models for the Elliott, Rothenberg, Stock DF-GLS unit-root test
Response surface models for the Elliott, Rothenberg, Stock DF-GLS unit-root test Christopher F Baum Jesús Otero Stata Conference, Baltimore, July 2017 Baum, Otero (BC, U. del Rosario) DF-GLS response surfaces
More informationTrending Models in the Data
April 13, 2009 Spurious regression I Before we proceed to test for unit root and trend-stationary models, we will examine the phenomena of spurious regression. The material in this lecture can be found
More information1 Estimation of Persistent Dynamic Panel Data. Motivation
1 Estimation of Persistent Dynamic Panel Data. Motivation Consider the following Dynamic Panel Data (DPD) model y it = y it 1 ρ + x it β + µ i + v it (1.1) with i = {1, 2,..., N} denoting the individual
More informationRecent Advances in Cointegration Analysis
EUROPEAN UNIVERSITY INSTITUTE DEPARTMENT OF ECONOMICS EUI Working Paper ECO No. 2004 /12 Recent Advances in Cointegration Analysis HELMUT LÜTKEPOHL BADIA FIESOLANA, SAN DOMENICO (FI) All rights reserved.
More informationSzilárd MADARAS, 1 Lehel GYÖRFY 2 1. Introduction. DOI: /auseb
Acta Univ. Sapientiae, Economics and Business, 4 (2016) 33 41 DOI: 10.1515/auseb-2016-0002 Non-Linearity and Non-Stationarity of Exchange Rate Time Series in Three Central-Eastern European Countries Regarding
More informationResidual-Based Tests for Cointegration and Multiple Deterministic Structural Breaks: A Monte Carlo Study
Residual-Based Tests for Cointegration and Multiple Deterministic Structural Breaks: A Monte Carlo Study Matteo Mogliani Paris School of Economics, France VERY PRELIMINARY VERSION, DO NOT CIRCULATE November
More informationContents. Part I Statistical Background and Basic Data Handling 5. List of Figures List of Tables xix
Contents List of Figures List of Tables xix Preface Acknowledgements 1 Introduction 1 What is econometrics? 2 The stages of applied econometric work 2 Part I Statistical Background and Basic Data Handling
More informationEconometrics I KS. Module 2: Multivariate Linear Regression. Alexander Ahammer. This version: April 16, 2018
Econometrics I KS Module 2: Multivariate Linear Regression Alexander Ahammer Department of Economics Johannes Kepler University of Linz This version: April 16, 2018 Alexander Ahammer (JKU) Module 2: Multivariate
More informationA note on nonlinear dynamics in the Spanish term structure of interest rates B
International Review of Economics and Finance 15 (2006) 316 323 www.elsevier.com/locate/iref A note on nonlinear dynamics in the Spanish term structure of interest rates B Vicente EsteveT Departamento
More informationNONLINEAR DYNAMICS UNDER UNCOVERED INTEREST RATE PARITY: CASES OF THE CZECH REPUBLIC, HUNGARY AND SLOVAKIA 1
Vít Pošta NONLINEAR DYNAMICS UNDER UNCOVERED INTEREST RATE PARITY: CASES OF THE CZECH REPUBLIC, HUNGARY AND SLOVAKIA 1 Abstract: There has been an increasing amount of research giving mixed evidence of
More informationSheffield Economic Research Paper Series. SERP Number:
Sheffield Economic Research Paper Series SERP Number: 2004013 Jamie Gascoigne Estimating threshold vector error-correction models with multiple cointegrating relationships. November 2004 * Corresponding
More informationThe Influence of Additive Outliers on the Performance of Information Criteria to Detect Nonlinearity
The Influence of Additive Outliers on the Performance of Information Criteria to Detect Nonlinearity Saskia Rinke 1 Leibniz University Hannover Abstract In this paper the performance of information criteria
More informationARDL Cointegration Tests for Beginner
ARDL Cointegration Tests for Beginner Tuck Cheong TANG Department of Economics, Faculty of Economics & Administration University of Malaya Email: tangtuckcheong@um.edu.my DURATION: 3 HOURS On completing
More informationCointegration, 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