Forecasting annual inflation in Suriname

For many countries, statistical information on macroeconomic variables is not abundant and, hence, creating forecasts for a key variable like inflation can be cumbersome. This paper addresses the creation of current year from MIDAS regression annual rates in Suriname where monthly are explanatory variables, and latter only available one half decade. The constructed model associates with hybrid New-Keynesian Philips curve (NKPC). Specific focus given to forecast accuracy high period 2016–2017. became very accurate when models included data May onwards. A particular parameter restriction was also useful improve accuracy.