Private Savings Behaviour in Lesotho: An Application of Autoregressive Distributed Lag (ARDL) Model

Abstract

The purpose of this paper is to investigate the private savings behaviour in Lesotho by employing an application of autoregressive distributed lag (ARDL) model. The empirical evidence on the determinants of private savings, the basic features of the Lesotho economy, the long-run and short-run determinants of private savings in Lesotho are modeled by using the dynamic Autoregressive Distributed Lag (ARDL) Modeling approach. The data used in this study were the secondary quarterly time series data that covered a 23-year period from 1980-I to 2003-IV. The overall performance of the long run model shows that about 97 % of the total variation was explained by the regressor which is an impressive performance of the best fitting model. The Durbin-Watson statistic also is around two which suggests that the model under consideration is not prone to serial correlation but more robust diagnostic test is employed. Similarly, F-statistics measuring the joint significance of all regressors in the model is statistically significant at 1 per cent level. On the other hand, the short run model of private saving rate also has a high value of the coefficient of determination of about 65 % showing that the overall fitness of the model is satisfactory.