Residual autocorrelation testing for vector error correction models

Abstract

In applied time series analysis, checking for autocorrelation in a fitted model is a routine diagnostic tool. Therefore it is useful to know the asymptotic and small sample properties of the standard tests for the case when some of the variables are cointegrated. The properties of residual autocorrelations of vector error correction models (VECMs) and tests for residual autocorrelation are derived. In particular, the asymptotic distributions of Lagrange multiplier (LM) and portmanteau tests are given. Monte Carlo simulations show that the LM tests have satisfactory size properties only if autocorrelation of small order is tested in systems of small dimension. In contrast, portmanteau tests have roughly correct size in small samples only if higher order residual autocorrelation is tested. Their critical values have to be adjusted for the cointegration rank of the system, however. r 2005 Elsevier B.V. All rights reserved.JEL classification: C32

A Multivariate Approach for Identification of Optimal Locations with in Ethiopia's Wheat Market to Tackle Soaring Inflation on Food Price (Extended Version)

“…In this option you need to search for large number of permutation of markets. For number of prices equal to n and maximum number lags ( ) i L considered in i permutation of markets 4 the total number permutation of markets to be tested for each model is equal to ( )…”

“…And e is a white noise error vector or it is identically and independently distributed multivariate normal vector. And as shown by Brüggermann et al (2006) the different specification implemented in the error correction model will not make difference on the critical value of the limit distribution. So we can use the following LM statistics which is similar to the conventional LM statistics applied to VAR model.…”

Growth Trends and Cycles in the American Postwar Period, with Implications for Policy

“…Test for Gaussian residuals. Brüggeman, Lütkepohl, and Saikkonen (2006) recommend the use of the Breush-Godfrey LM test when investigating low-order autocorrelation in a small system with a large sample, as is the case here. Juselius (2006) suggests that absence of normality is not so much of a problem when it originates from excess kurtosis as it is from excess skewness (hence the importance of introducing relevant dummies).…”

Determinacy, indeterminacy and dynamic misspecification in linear rational expectations models

“…(22) and solve Eq. (23); finally, 14 ForΓ b := 0 2p×2p (purely forward-looking model), the unique stable solution is given by X t = Υu t unlessΓ f is invertible and the matrix (Γ f ) −1Γ 0 is stable.…”