Testing for the Cointegrating Rank of a VAR Process with Level Shift and Trend Break
Title: Testing for the Cointegrating Rank of a VAR Process with Level Shift and Trend Break
Publisher: European University Institute
Series/Number: EUI ECO; 2006/29
A test for the cointegrating rank of a vector autoregressive (VAR) process with a possible shift and broken linear trend is proposed. The break point is assumed to be known. The setup is a VAR process for cointegrated variables. The tests are not likelihood ratio tests but the deterministic terms including the broken trends are removed ¯rst by a GLS proce- dure and a likelihood ratio type test is applied to the adjusted series. The asymptotic null distribution of the test is derived and it is shown by a Monte Carlo experiment that the test has better small sample properties in many cases than a corresponding Gaussian likelihood ratio test for the cointegrating rank.
Subject: Cointegration; structural break; vector autoregressive process; error correction model
Type of Access: openAccess