The saving-investment relationship in periods of structural change The case of Greece

Purpose - To study the dynamic relationship between saving-investment in Greece during a period of structural changes with policy regime changes employing different methods of estimation. Design/methodology/approach - Different empirical methods are used to estimate the time varying savings retention coefficient. A recursive OLS, rolling OLS, Kalman filter estimator and Markov switching regime modeling (MS-R) are applied which have the advantage to capture the dependence structure of the series both in terms of constant and variance. Findings - The empirical evidence suggests that the degree of correlation between saving and investment weakens during financial liberalization periods. Practical implications -Conclusions drawn from this analysis could be useful for the analysis of other medium-sized economies. Originality/value - The paper employs four different estimation models to test the stability of the estimated coefficient. The MS-R is used, for the first time, to take into account the policy regime changes during the estimation period.