Estimation and Hypothesis Testing of Cointegration Vectors in Gaussian Vector Autoregressive Models
对允许协整的向量自回归模型进行似然分析，推导了协整秩的似然比检验及其渐近分布，并证明最大似然估计量的渐近分布为混合高斯分布，从而可用卡方分布对协整关系进行假设检验。
This paper contains the likelihood analysis of vector autoregressive models allowing for cointegration. The author derives the likelihood ratio test for cointegrating rank and finds it asymptotic distribution. He shows that the maximum likelihood estimator of the cointegrating relations can be found by reduced rank regression and derives the likelihood ratio test of structural hypotheses about these relations. The author shows that the asymptotic distribution of the maximum likelihood estimator is mixed Gaussian, allowing inference for hypotheses on the cointegrating relation to be conducted using the Chi( squared) distribution. Copyright 1991 by The Econometric Society.