Econometrics, represented by regression analysis, has been utilized more and more for estimation of damages in Korean civil litigations. The leading case of such litigation is the case of military oil supply contracts. In the U.S. and EU, utilization ...
Econometrics, represented by regression analysis, has been utilized more and more for estimation of damages in Korean civil litigations. The leading case of such litigation is the case of military oil supply contracts. In the U.S. and EU, utilization of econometrics seems to be already established in the area of damage assessment. Regression analysis is a statistical process for estimating the relationships between a dependent variable and one or more independent variables, and it helps one understand how the typical value of the dependent variable changes when any one of the independent variables is varied, while the other independent variables are held fixed. It also helps one review the validity of a hypothesis. In contrast to U.S. procedure where regression analysis report is made and presented by each party`s own econometric expert, such report is made and presented by court-appointed econometric expert in Korean litigation procedure. In order for a regression analysis to produce a feasible and suitable result, the data sets should be enough and not-contrived, and the regression model should be proper. For that purpose, it is also needed that spurious correlation be excluded, endogeneity not occur, necessary variables not be omitted, and inappropriate variables not be included. Substantial bias may arise in the result of the regression, when such principles are not complied with. If courts want to prevent misuse of regression analysis and to render judgments based on persuading result of regression analysis, i.e., if courts want to have confidence in the result of the analysis, whether the above-mentioned factors are obeyed in the course of the regression analysis should be examined by the courts.