Abstract:
An accurate forecast for inflation is mandatory in the conduct of monetary policy in every monetary framework. This research puts a first effort to accurately model and consequently forecast monthly inflation for the economy of Suriname. This paper employs various econometric techniques such as Autoregressive Integrated Moving Average models, Vector Autoregressive models, Factor Augmented Vector Autoregressive models, Bayesian Vector Autoregressive models and Vector Error Correction models to model monthly inflation for Suriname over the period 2004 to 2018. Consequently, the in-sample forecast performance of the models is evaluated by comparison of the Root Mean Square Error and the Mean Average Errors. Since Suriname encountered a high-inflation period, we split up the sample in two periods, i.e. including and excluding this high-inflation episode. In this evaluation, not surprisingly, the Root Mean Square Errors of the models was considerably lower in the sample excluding the high inflation episode. Consequently, we also conducted an out-of-sample forecasting exercise. The VECM yields the best results forecasting up to three months ahead, while thereafter, the FAVAR, which includes more economic information, outperforms the VECM, based on the assessment of the out-of-sample forecast performance of the models.
Additional Information:
The authors are staff members of the Research Department of the Central Bank of Suriname. The views expressed in this paper are those of the authors and do not necessarily reflect those of the Bank. Research papers constitute work in progress and are published to elicit comments and to further debate