The multiple time series and ridge regression techniques are proposed for modeling and analyzing a scaled real life (or a simulated) data as a SUR model with VAR(p) disturbances. The regression coefficients are estimated via the generalized least squares method if collinearity is weak and otherwise the regression coefficients are estimated by the generalized ridge regression method. Small sample likelihood ratio test statistic and model selection criteria are employed for selecting the smallest possible lag order for the VAR process. Moreover, Monte Carlo simulations (1000 replications) are conducted to examine the properties of some new and some of the existing ridge parameters in rectifying the collinearity problem in SUR models with VAR(2) disturbances via the trace(MSE) and condition number criteria. Two data sets are analyzed to illustrate the findings of the article.
