A new strategy based on econometric models to improve the forecasts accuracy in Romania

• Author: Bratu (Simionescu), M.
• Position: Faculty of Cybernetics, Statistics and Economic Informatics, Academy of Economic Studies Bucharest
• Pages: 55-62

Bulletin of the Transilvania University of Braşov • Vol. 6 (55) •No. 1 - 2013

Series V: Economic Sciences

A NEW STRATEGY BASED ON

ECONOMETRIC MODELS

TO IMPROVE THE FORECASTS

ACCURACY IN ROMANIA

Mihaela BRATU (SIMIONESCU)

1

Abstract: An empirical stra tegy of improving the forecasts accur acy is

proposed in this article starting from econometric models with t he ra ndom

component determined using resampling techniques. New pred ictions were

built using those provided b y two institutions from Romania specialized in

forecasting: the Institute for Economic Forecasting (IEF) and the National

Commission of P rognosis (NCP). For the inflation and unemployment ra te

four different regr ession models were proposed to build other forecasts. Two

of the regression models improved both institutions forecasts for the inflation

and unemployment rate on the forecasting hor izon 2010-2012, while the

other two provided better pr edictions than the NCP ones. So, the models

based on resampled er rors is an origina l way of constructing new foreca sts

and a t the same time a good strategy of improving the predictions a ccuracy

for some macroeconomic forecasts in Romania.

Key words: accuracy, econometric models, forecasts, r esampling

techniques.

1 Faculty of Cybernetics, Statistics and Economic Informatics, Academy of Economic Studies Bucharest.

1 Introduction

In this study we are interested in building

new forecasts starting from the ones

provided by two specialized institutions in

Romania: the Institute for Economic

Forecasting (IEF) and the National

Commission of Prognosis (NCP). Actually,

our purpose is to test if the new predictions

based on econometric models using

resample techniques to generate the

random element are more accurate than the

initial ones.

After a short review in the literature

regarding the measures of forecasts

accuracy and the strategies to improve it,

we proposed some econometric models

used in constructing new prognosis for

inflation and unemployment rate on the

horizon 2010-2012. The accuracy of these

forecasts was assessed and the models that

improved the accuracy were identified.

2 Forecasts accuracy

To assess the forecasts accuracy, as well

as their ordering, statisticians have

developed several measures of accuracy.

For the comparison between the MSE

indicators of forecasts, Granger and

Newbold proposed a statistic. Another

statistic is presented by (Diebold and

Mariano, 1995) for the comparison of

other quantitative measures of errors.