| Abstract [eng] |
The aim of the study is to estimate the impact of fiscal policy for macroeconomics variables in Baltic countries. Quarterly Lithuanian, Latvian and Estionian datasets were used for that purpose. Usually VAR models are used to estimate the influence of fiscal policy. VAR models were used for this analysis aswell. The drawback of VAR models is that the number of parameters grow very fast and because of that we can not use big datasets. To solve this problem, the Lasso methods were used. Lasso methods perform both variable selection and regularization in order to enhance the accuracy of the statistical model it produces. The results show that, for the estimation the impact of fiscal policy, one of the Lasso methods is more accurate than the other and than the usual VAR model. |
