|
on Forecasting |
| By: | Philip Hans Franses (Econometric Institute Erasmus School of Economics, Erasmus University Rotterdam); Michael McAleer (Econometric Institute, Erasmus School of Economics, Erasmus University Rotterdam and Tinbergen Institute, The Netherlands, Department of Quantitative Economics, Complutense University of Madrid, and Institute of Economic Research, Kyoto University.); Rianne Legerstee (Econometric Institute, Erasmus School of Economics, Erasmus University Rotterdam and Tinbergen Institute The Netherlands) |
| Abstract: | Macroeconomic forecasts are frequently produced, widely published, intensively discussed and comprehensively used. The formal evaluation of such forecasts has a long research history. Recently, a new angle to the evaluation of forecasts has been addressed, and in this review we analyse some recent developments from that perspective. The literature on forecast evaluation predominantly assumes that macroeconomic forecasts are generated from econometric models. In practice, however, most macroeconomic forecasts, such as those from the IMF, World Bank, OECD, Federal Reserve Board, Federal Open Market Committee (FOMC) and the ECB, are typically based on econometric model forecasts jointly with human intuition. This seemingly inevitable combination renders most of these forecasts biased and, as such, their evaluation becomes non-standard. In this review, we consider the evaluation of two forecasts in which: (i) the two forecasts are generated from two distinct econometric models; (ii) one forecast is generated from an econometric model and the other is obtained as a combination of a model and intuition; and (iii) the two forecasts are generated from two distinct (but unknown) combinations of different models and intuition. It is shown that alternative tools are needed to compare and evaluate the forecasts in each of these three situations. These alternative techniques are illustrated by comparing the forecasts from the (econometric) Staff of the Federal Reserve Board and the FOMC on inflation, unemployment and real GDP growth. It is shown that the FOMC does not forecast significantly better than the Staff, and that the intuition of the FOMC does not add significantly in forecasting the actual values of the economic fundamentals. This would seem to belie the purported expertise of the FOMC. |
| Keywords: | Macroeconomic forecasts, econometric models, human intuition, biased forecasts, forecast performance, forecast evaluation, forecast comparison. |
| JEL: | C22 C51 C52 C53 E27 E37 |
| Date: | 2012–06 |
| URL: | http://d.repec.org/n?u=RePEc:ucm:doicae:1214&r=for |
| By: | Ray C. Fair (Cowles Foundation, Yale University) |
| Abstract: | In January 2012 the Fed began reporting ranges of its economic forecasts. The ranges, however, measure differences of opinion, not variances of economic forecasts. This paper discusses what the Fed could report in a world in which it used a single macroeconometric model to make its forecasts and guide its policies. Suggestions are then made as to what might be feasible for the Fed to report given that it is unlikely to be willing to commit to a single model. |
| Keywords: | Forecasting uncertainty, Fed policy |
| JEL: | E58 |
| Date: | 2012–06 |
| URL: | http://d.repec.org/n?u=RePEc:cwl:cwldpp:1864&r=for |
| By: | Eichler Michael; Grothe Oliver; Tuerk Dennis; Manner Hans (METEOR) |
| Abstract: | Predicting the occurrence of extreme prices, so-called spikes, is one of the greatest challengeswhen modeling electricity spot prices. Despite the fact that recently new insights have beenachieved, the contemporaneous literature seems to be still at its beginning of understanding thedifferentmechanisms that drive spike probabilities. We therefore reconsider the problem offorecasting the occurrence of spikes, in the Australian electricity market. For this purpose, wefirst discuss properties of the price data with a focus on the occurrence of spikes. We thenpropose simple models for the probability of spikes which take these properties into account. Themodels compare favorably for in- and out-of-sample forecasts to a competing approach based on theautoregressive conditional hazard model. |
| Keywords: | econometrics; |
| Date: | 2012 |
| URL: | http://d.repec.org/n?u=RePEc:dgr:umamet:2012029&r=for |
| By: | George W. Evans; Seppo Honkapohja; Thomas Sargent; Noah Williams |
| Abstract: | Agents have two forecasting models, one consistent with the unique rational expectations equilibrium, another that assumes a time-varying parameter structure. When agents use Bayesian updating to choose between models in a self-referential system, we find that learning dynamics lead to selection of one of the two models. However, there are parameter regions for which the non-rational forecasting model is selected in the long-run. A key structural parameter governing outcomes measures the degree of expectations feedback in Muth's model of price determination. |
| Keywords: | Learning dynamics, Bayesian model averaging, grain of truth, self-referential systems. |
| JEL: | D83 D84 C52 C11 |
| Date: | 2012–01–25 |
| URL: | http://d.repec.org/n?u=RePEc:san:cdmawp:1203&r=for |
| By: | Rosalie Liccardo Pacula; Srikanth Kadiyala; Priscillia Hunt; Alessandro Malchiodi |
| Abstract: | This paper develops a new method for estimating trends in the size of counterfeit markets. The method draws on principles of microeconomic theory and uses aggregated product-level data to estimate counterfeiting activities in various geographic markets. Using confidential firm unit forecasts and actual sales information, a two stage approach is employed that first accounts for unexpected but observable factors that could lead to forecasting error and then, in the second stage, considers the influence of market susceptibility to IPR infringement. Data are analysed for 45 related products sold by a single firm operating in 16 countries during the period 2006-2011. Our models predict larger amounts of counterfeiting in countries with higher corruption norms, lower government control and effectiveness. Predictions of the level of counterfeiting obtained from the second stage are then compared to estimates of counterfeiting derived internally by the firm using shadow-shopping methods. While our two stage model generally under-predicts the level of counterfeiting in each year, it generates trends in counterfeiting that are broadly consistent with those obtained using more costly and intensive methods. |
| JEL: | H32 K42 |
| Date: | 2012–06 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:18171&r=for |
| By: | William Branch; George W. Evans; Bruce McGough |
| Abstract: | Incorporating adaptive learning into macroeconomics requires assumptions about how agents incorporate their forecasts into their decision-making. We develop a theory of bounded rationality that we call finite-horizon learning. This approach generalizes the two existing benchmarks in the literature: Euler-equation learning, which assumes that consumption decisions are made to satisfy the one-step-ahead perceived Euler equation, and infinite-horizon learning, in which consumption today is determined optimally from an infinite-horizon optimization problem with given beliefs. In our approach, agents hold a finite forecasting/planning horizon. We find for the Ramsey model that the unique rational expectations equilibrium is E-stable at all horizons. However, transitional dynamics can differ significantly depending upon the horizon. |
| Keywords: | Planning horizon, bounded rationality, dynamic optimization, adaptive learning, Ramsey model. |
| JEL: | D83 D84 D91 E32 |
| Date: | 2012–01–25 |
| URL: | http://d.repec.org/n?u=RePEc:san:cdmawp:1204&r=for |
| By: | John H. Cochrane |
| Abstract: | I translate familiar concepts of discrete-time time-series to contnuous-time equivalent. I cover lag operators, ARMA models, the relation between levels and differences, integration and cointegration, and the Hansen-Sargent prediction formulas. |
| JEL: | C01 C5 C58 E17 G17 |
| Date: | 2012–06 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:18181&r=for |