In this Working Paper, we describe how we used stochastic simulation to evaluate the risks surrounding the January 2006 nime Economic Outlook (neo) for the world economy. We summarise the main results by showing confidence intervals around the baseline projection as well as probabilities that certain events will occur. The results presented in this Working Paper are of an illustrative nature and do not constitute an update of the January 2006 nime Economic Outlook.
This exercise is motivated by the fact that the public discussion of point projections very often treats these as accurate statements on future effective outcomes, notwithstanding that projections made on the basis of macroeconomic models are exposed to several risks. Indeed, macroeconometric models are no more than the best possible representations of complex interactions in the economy, making their use subject to risks related for instance to the behavioural equations’ error terms and to the model’s exogenous variables.
The Working Paper is structured as follows. The first chapter gives a brief introduction and summarises the main results. The second chapter describes how the stochastic simulation of the nime model is implemented. The third chapter discusses the main results. There we present confidence intervals for the major macroeconomic variables of the euro area, the United States and Japan. We also estimate the probabilities of occurrence of specific events.
The stochastic simulation results show for instance that there is a 95 per cent probability that gdp growth in the euro area will come out between 1.5 per cent and 3 per cent in 2006. Similarly, there is a 95 per cent probability that real gdp growth will come out between 0.3 and 2.8 per cent in 2012. For the United States, the 95 per cent confidence interval places real gdp growth between 2.5 and 4.2 per cent in 2006 and between 1.3 and 3.3 per cent in 2012. For Japan, there is a 95 per cent probability that real gdp growth will come out between 0.8 and 2.8 per cent in 2006 and between 0.1 and 2.4 per cent in 2012.
Stochastic simulation also allows us to estimate the probability of the occurrence of a specific event. For instance, the simulation results indicate that there is a limited 1 per cent probability, that under current policies, gdp growth in the euro area will be smaller in 2006 than in 2005. Furthermore, the probability that gdp growth in the euro area will come out above 3 per cent over the entire 2010-2012 period, as targeted under the Lisbon Agenda, is also negligible. There is only a 13.3 per cent probability that euro area inflation will effectively stay below the ecb’s 2 per cent upper limit over the entire 2006-2012 period. The probability that the euro area’s nominal short-term interest rate will come out 25 basis points higher in 2006 than in 2005, when it averaged 2.2 per cent, is estimated at 23.7 per cent; the probability that monetary policy will tighten more strongly, raising the short-term interest rate by 50 basis points in 2006, is estimated at only 1.7 per cent. This compares with a 83.8 per cent probability that the us short-term interest rate will come out 50 basis points higher in 2006 than in 2005. Finally, although the latest neo baseline projection shows that the rise in Japan’s deflator of private consumption should come out at 0.3 per cent in 2006, Table 2 shows there is still a 31.7 per cent probability of deflation in 2006. However, the probability of deflation occurring consecutively in 2006 and in 2007 is just 4.9 per cent.