In this issue we have: Accuracy in forecasting macroeconomic variables in Iceland ; Combining Multivariate Density Forecasts Using Predictive Criteria ; Improving Forecasts of Inflation using the Term Structure of Interest Rates ; Option based forecasts of volatility and more.
Date: | 2008-05 |
By: | Ásgeir Daníelsson |
URL: | http://d.repec.org/n?u=RePEc:ice:wpaper:wp39&r=for |
This paper discusses accuracy in forecasting of macroeconomic time series in Iceland. Until recently only the National Economic Institute (NEI) did macroeconomic forecasting in Iceland. Extensive analysis of forecasting can therefore only be done for the forecasts made by this institution during 1974-2002. The paper analysis macroeconomic forecasts published by the Central Bank of Iceland (CBI). It also analysis the accuracy of the first realeases of data from Statistics Iceland as "forecasts" of final (or the most recent) data during recent years. Forecasts made by international institutions like OECD and IMF are not included. The paper finds that errors in forecasting of GDP and private consumption have declined and that the performance of the forecasting for these variables has improved on some measures. But the volatility in the series has also decreased so when the forecast errors are compared to measures! of the shocks that hit the economy the forecasting of changes in GDP do not seem to have improved. For some of the main components of GDP like export, imports and investments, the forecast errors have not decreased. |
Date: | 2008-05 |
By: | Hugo Gerard (Reserve Bank of Australia) Kristoffer Nimark (Reserve Bank of Australia) |
URL: | http://d.repec.org/n?u=RePEc:rba:rbardp:rdp2008-02&r=for |
This paper combines multivariate density forecasts of output growth, inflation and interest rates from a suite of models. An out-of-sample weighting scheme based on the predictive likelihood as proposed by Eklund and Karlsson (2007) and Andersson and Karlsson (2007) is used to combine the models. Three classes of models are considered: a Bayesian vector autoregression (BVAR), a factor-augmented vector autoregression (FAVAR) and a medium-scale dynamic stochastic general equilibrium (DSGE) model. Using Australian data over the inflation-targeting period, we find that, at short forecast horizons, the Bayesian VAR model is assigned the most weight, while at intermediate and longer horizons the factor model is preferred. The DSGE model is assigned little weight at all horizons, a result that can be attributed to the DSGE model producing density forecasts that are very wide when compared with the actual distribution of ! observations. While a density forecast evaluation exercise reveals little formal evidence that the optimally combined densities are superior to those from the best-performing individual model, or a simple equal-weighting scheme, this may be a result of the short sample available. | |
Keywords: | density forecasts; combining forecasts; predictive criteria |
JEL: | C52 C53 |
Date: | 2008-05-16 |
By: | Alonso Gomez John M Maheu Alex Maynard |
URL: | http://d.repec.org/n?u=RePEc:tor:tecipa:tecipa-319&r=for |
Many pricing models imply that nominal interest rates contain information on inflation expectations. This has lead to a large empirical literature that investigates the use of interest rates as predictors of future inflation. Most of these focus on the Fisher hypothesis in which the interest rate maturity matches the inflation horizon. In general forecast improvements have been modest and often fail to improve on autoregressive benchmarks. Rather than use only monthly interest rates that match the maturity of inflation, this paper advocates using the whole term structure of daily interest rates and their lagged values to forecast monthly inflation. Principle component methods are employed to combine information from interest rates across both the term structure and time series dimensions. We find robust forecasting improvements in general as compared to both an augmented Fisher equation and autoregressive benchmar! ks. | |
Keywords: | inflation, inflation forecast, Fisher equation, term structure, principal components |
JEL: | E31 E37 C53 C32 |
Date: | 2008-05 |
By: | Silvia Muzzioli |
URL: | http://d.repec.org/n?u=RePEc:mod:wcefin:08051&r=for |
Option based volatility forecasts can be divided into "model dependent" forecast, such as implied volatility, that is obtained by inverting the Black and Scholes formula, and "model free" forecasts, such as model free volatility, proposed by Britten-Jones and Neuberger (2000), that do not rely on a particular option pricing model. The aim of this paper is to investigate the unbiasedness and efficiency in predicting future realized volatility of the two option based volatility forecasts: implied volatility and model free volatility. The comparison is pursued by using intradaily data on the Dax-index options market. Our results suggest that Black-Scholes volatility subsumes all the information contained in historical volatility and is a better predictor than model free volatility. | |
Keywords: | Implied Volatility; Model free volatility; Volatility Forecasting |
JEL: | G13 G14 |
By: | Jesus Crespo Cuaresma Andreas Breitenfellner |
URL: | http://d.repec.org/n?u=RePEc:inn:wpaper:2008-08&r=for |
If oil exporters stabilize the purchasing power of their export revenues in terms of imports, exchange rate developments (and particularly, developments in the US dollar/euro exchange rate) may contain information about oil price changes. This hypothesis depends on three conditions: (a) OPEC has price setting capacity, (b) a high share of OPEC imports comes from the euro area and (c) alternatives to oil invoicing in US dollar are costly. We give evidence that using information on the US dollar/euro exchange rate (and its determinants) improves oil price forecasts significantly. We discuss possible implications that these results might suggest with regard to the stabilization of oil prices or the adjustment of global imbalances. | |
Keywords: | oil price, exchange rate, forecasting, multivariate time series models. |
JEL: | Q43 F31 C53 |
Date: | 2008-04-15 |
By: | Alvaro Sandroni (Department of Economics, University of Pennsylvania) Wojciech Olszewski (Department of Economics, Northwestern University) |
URL: | http://d.repec.org/n?u=RePEc:pen:papers:08-014&r=for |
The difficulties in properly anticipating key economic variables may encourage decision makers to rely on experts' forecasts. Professional forecasters, however, may not be reliable and so their forecasts must be empirically tested. This may induce experts to forecast strategically in order to pass the test. A test can be ignorantly passed if a false expert, with no knowledge of the data generating process, can pass the test. Many tests that are unlikely to reject correct forecasts can be ignorantly passed. Tests that cannot be ignorantly passed do exist, but these tests must make use of predictions contingent on data not yet observed at the time the forecasts are rejected. Such tests cannot be run if forecasters report only the probability of the next period's events on the basis of the actually observed data. This result shows that it is difficult to dismiss false, but strategic, experts who know how theories! are tested. This result also shows an important role that can be played by predictions contingent on data not yet observed. | |
Keywords: | Testing Strategic Experts |
JEL: | D81 C11 |
Taken from the NEP-FOR mailing list edited by Rob Hyndman.