where Lˆ = L(θˆ) is the log-likelihood of the model in Eq. (1) andLˆ0 = L(θˆ0) is the log-likelihood of the alternative constant modelsetting B equal to a matrix of zeros, and θˆ and θˆ0 are the maximum-likelihood estimates for the two models.The moment persistence measure LR∗VAR(1) might be interpretedsimilarly to the R2 in a simple linear regression: the more variationa model can explain, relative to a simple mean model benchmark,the better the predictability. In the case of Eq. (2) a better predictability implies higher LR∗VAR(1) and, hence, higher persistence.