Back to the future. Counterfactual Scenarios Challenges, Methodology and an Empirical Test

Forecasting has become an important part for policy planning. Economic forecasts offer guidance under conditions. They are used and/or produced by politicians, researchers, companies, associations or unions. They enter decision making processes and have an impact on state budget, consumption decision, personnel strategies – just to name a few. Ex-ante (policy) impact assessment (IA) is a forward-looking concept that has to deal with a lot of unknowns (e.g. natural disasters). The predicted impact is only valid within a certain framework or set of assumptions. However, it allows to pass judgements on the effectiveness and efficiency of planned measures. In many countries, impact assessments “has become an important tool for assisting policy makers in their decision-making process” (Großmann et al. 2016: 13). Due to its importance of (ex-ante) impact assessment, the questions arises regularly whether the forecasted results are robust. Or put differently: How good is the forecast? One method to answer this is to apply counterfactual forecasts. Such counterfactual scenarios or ex-post scenarios are, however, challenging to model. There can be two reasons for going “back to the future” and for facing this challenge: First, to test the accuracy of a forecasting model, or, second, to study the efficiency of an already implemented policy. While the first reasons produces a “first order” ex-post simulation, the second reason is a “second order” ex-post simulation where first order results are used as a baseline. Only first-order simulations can be compared to the already known real world. With some diagnostic checks – such as mean, relative or squared error tests – the model forecasting performance can be evaluated. However, the question is not if there are error terms to be observed but how big they are. Second-order scenarios can only be compared to first-order scenarios, not to actual data. In this paper, we introduce how to perform ex-post forecast with a macroeconometric input-output model. We take the example of COFORCE which has been developed to fore-cast the Chilean economy until 2035 (Mönnig & Bieritz 2019). The remainder of the paper is structured as follows: First, an overview about the challeng-es concerned with ex-post simulations is given. Then, the methodological approach is described. Next, an ex-post simulation is performed on the model COFORCE. The paper concludes with the main findings.