A Practitioner's Guide to Lag Order Selection For VAR Impulse Response Analysis

It is common in empirical macroeconomics to fit vector autoregressive (VAR) models to construct estimates of impulse responses. An important preliminary step in impulse response analysis is the selection of the VAR lag order. In this paper, we compare the six lag-order selection criteria most commonly used in applied work. Our metric is the mean-squared error (MSE) of the implied pointwise impulse response estimates normalized relative to their MSE based on knowing the true lag order. Based on our simulation design we conclude that for monthly VAR models, the Akaike Information Criterion (AIC) tends to produce the most accurate structural and semi-structural impulse response estimates for realistic sample sizes. For quarterly VAR models, the Hannan-Quinn Criterion (HQC) appears to be the most accurate criterion with the exception of sample sizes smaller than 120, for which the Schwarz Information Criterion (SIC) is more accurate. For persistence profiles based on quarterly vector error correction models with known cointegrating vector, our results suggest that the SIC is the most accurate criterion for all realistic sample sizes.

[1]  Paul Kabaila,et al.  The Effect of Model Selection on Confidence Regions and Prediction Regions , 1995, Econometric Theory.

[2]  C. Sims.  MACROECONOMICS AND REALITY , 1977 .

[3]  B. M. Pötscher.  Comment on “The Effect of Model Selection on Confidence Regions and Prediction Regions” by P. Kabaila , 1995, Econometric Theory.

[4]  Steven Strongin,et al.  The identification of monetary policy disturbances: explaining the liquidity puzzle , 1995 .

[5]  B. G. Quinn.  A NOTE ON AIC ORDER DETERMINATION FOR MULTIVARIATE AUTOREGRESSIONS , 1988 .

[6]  Dag Tjøstheim,et al.  On the Estimation of Residual Variance and Order in Autoregressive Time Series , 1985 .

[7]  Barry G. Quinn,et al.  Order Determination for a Multivariate Autoregression , 1980 .

[8]  S. Johansen,et al.  MAXIMUM LIKELIHOOD ESTIMATION AND INFERENCE ON COINTEGRATION — WITH APPLICATIONS TO THE DEMAND FOR MONEY , 2009 .

[9]  M. Wickens,et al.  Interpreting cointegrating vectors and common stochastic trends , 1996 .

[10]  H. White,et al.  Information criteria for selecting possibly misspecified parametric models , 1996 .

[11]  L. Kilian.  IMPULSE RESPONSE ANALYSIS IN VECTOR AUTOREGRESSIONS WITH UNKNOWN LAG ORDER , 2001 .

[12]  Tiao Gc,et al.  An introduction to multiple time series analysis. , 1993 .

[13]  Eric M. Leeper,et al.  Narrative and VAR Approaches to Monetary Policy: Common Identification Problems , 1996 .

[14]  Peter C. B. Phillips,et al.  Posterior Odds Testing for a Unit Root with Data-Based Model Selection , 1994, Econometric Theory.

[15]  Lutz Kilian,et al.  Residual-Based Tests for Normality in Autoregressions: Asymptotic Theory and Simulation Evidence , 2000 .

[16]  Olivier J. Blanchard,et al.  The Dynamic Effects of Aggregate Demand and Supply Disturbances , 1988 .

[17]  J. R. M. Hosking,et al.  Lagrange‐Multiplier Tests of Multivariate Time‐Series Models , 1981 .

[18]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[19]  Lawrence J. Christiano,et al.  The Effects of Monetary Policy Shocks: Some Evidence from the Flow of Funds , 1996 .

[20]  C. Sims.  Are forecasting models usable for policy analysis , 1986 .

[21]  B. Bernanke,et al.  The Liquidity Effect and Long-Run Neutrality , 1998 .

[22]  J. Galí,et al.  Technology, Employment, and the Business Cycle: Do Technology Shocks Explain Aggregate Fluctuations , 1996 .

[23]  M. Watson.  Vector autoregressions and cointegration , 1986 .

[24]  Yongcheol Shin,et al.  Cointegration and speed of convergence to equilibrium , 1996 .

[25]  M. Watson,et al.  Systematic Monetary Policy and the Effects of Oil Price Shocks , 1997 .

[26]  Lutz Kilian,et al.  Exchange Rates and Monetary Fundamentals: What Do We Learn from Long-Horizon Regressions? , 1999 .

[27]  C. Sims,et al.  Bayesian methods for dynamic multivariate models , 1998 .

[28]  P. Söderlind,et al.  Applied Cointegration Analysis in the Mirror of Macroeconomic Theory , 1995 .

[29]  Martin Eichenbaum,et al.  Some Empirical Evidence on the Effects of Shocks to Monetary Policy on Exchange Rates , 1995 .

[30]  B. Bernanke,et al.  Inside the Black Box: The Credit Channel of Monetary Policy Transmission , 1995 .

[31]  M. Pesaran,et al.  Structural analysis of vector error correction models with exogenous I(1) variables , 2000 .

[32]  Helmut Lütkepohl,et al.  Asymptotic Distributions of Impulse Response Functions and Forecast Error Variance Decompositions of Vector Autoregressive Models , 1990 .

[33]  Ron Smith,et al.  Structural Analysis of Cointegrating Vars , 1998 .

[34]  O. Blanchard.  A Traditional Interpretation of Macroeconomic Fluctuations , 1989 .

[35]  James D. Hamilton,et al.  Oil Shocks and Aggregate Macroeconomic Behavior: The Role of Monetary Policy: A Comment , 2004 .

[36]  Jostein Paulsen,et al.  ORDER DETERMINATION OF MULTIVARIATE AUTOREGRESSIVE TIME SERIES WITH UNIT ROOTS , 1984 .

[37]  Lawrence J. Christiano,et al.  Monetary Policy Shocks: What Have We Learned and to What End? , 1998 .

[38]  B. Bernanke,et al.  Measuring Monetary Policy , 1995 .

[39]  Helmut Lütkepohl,et al.  Impulse response analysis of cointegrated systems , 1992 .

[40]  J. Galí,et al.  How Well Does The IS-LM Model Fit Postwar U. S. Data? , 1992 .

[41]  M. Watson,et al.  Sources of Business Cycle Fluctuations , 1988, NBER Macroeconomics Annual.

[42]  Clive W. J. Granger,et al.  Comments on testing economic theories and the use of model selection criteria , 1995 .

[43]  Gerald Nickelsburg,et al.  Small-sample properties of dimensionality statistics for fitting VAR models to aggregate economic data: A Monte Carlo study , 1985 .

[44]  Permanent and Transitory Shocks in Real Output: Estimates from Nineteenth Century and Postwar Economies , 1998 .

[45]  H. Lütkepohl.  COMPARISON OF CRITERIA FOR ESTIMATING THE ORDER OF A VECTOR AUTOREGRESSIVE PROCESS , 1985 .