|
on Forecasting |
By: | Alessi, Luci (Federal Reserve Bank of New York); Ghysels, Eric (Federal Reserve Bank of New York); Onorante, Luca (Federal Reserve Bank of New York); Peach, Richard (Federal Reserve Bank of New York); Potter, Simon M. (Federal Reserve Bank of New York) |
Abstract: | This paper documents macroeconomic forecasting during the global financial crisis by two key central banks: the European Central Bank and the Federal Reserve Bank of New York. The paper is the result of a collaborative effort between the two institutions, allowing us to study the time-stamped forecasts as they were made throughout the crisis. The analysis does not focus exclusively on point forecast performance. It also examines density forecasts, as well as methodological contributions, including how financial market data could have been incorporated into the forecasting process. |
Keywords: | macro forecasting; financial crisis |
JEL: | B41 E32 G01 N20 |
Date: | 2014–07–01 |
URL: | http://d.repec.org/n?u=RePEc:fip:fednsr:680&r=for |
By: | Francisco Javier Eransus (Departamento de Economía Cuantitativa (Department of Quantitative Economics), Facultad de Ciencias Económicas y Empresariales (Faculty of Economics and Business), Universidad Complutense de Madrid); Alfonso Novales Cinca (Departamento de Economía Cuantitativa (Department of Quantitative Economics), Facultad de Ciencias Económicas y Empresariales (Faculty of Economics and Business), Universidad Complutense de Madrid) |
Abstract: | We propose a new approach to evaluating the usefulness of a set of forecasts, based on the use of a discrete loss function de…ned on the space of data and forecasts. Existing procedures for such an evaluation either do not allow for formal testing, or use tests statistics based just on the frequency distribution of (data , forecasts)-pairs. They can easily lead to misleading conclusions in some reasonable situations, because of the way they formalize the underlying null hypothesis that ‘the set of forecasts is not useful.’ Even though the ambiguity of the underlying null hypothesis precludes us from performing a standard analysis of the size and power of the tests, we get results suggesting that the proposed DISC test performs better than its competitors. |
Keywords: | Forecasting Evaluation, Loss Function. |
JEL: | C53 C52 C12 |
Date: | 2014 |
URL: | http://d.repec.org/n?u=RePEc:ucm:doicae:1424&r=for |
By: | Rocío Elizondo |
Abstract: | The purpose of this paper is to show that an affine model which incorporates the condition of no arbitrage enables improvements in forecasting the term structure of interest rates in Mexico. The three factors of the yield curve (level, slope and curvature) used in the model are estimated by the method of principal components. The forecasting model is specified as a linear relationship between each of the interest rates and these factors, for maturities of 1 to 60 months. Affine model predictions are compared with four benchmark models: a forward rate, an AR(1), a VAR(1), and a random walk model. The main finding is that the affine model has a performance comparable to benchmark models for horizons of 12 and 18 months, except for the random walk model. However, improving its forecasting performance for the 24-month horizon, and especially for 60-month maturities. |
Keywords: | Affine Model, Forecasts, Yield Curve, Principal Components, Condition of no Arbitrage |
JEL: | G12 E43 C12 C53 |
Date: | 2013–04 |
URL: | http://d.repec.org/n?u=RePEc:bdm:wpaper:2013-03&r=for |
By: | Wilmer Osvaldo Martínez-Rivera; Manuel Dario Hernández-Bejarano; Juan Manuel Julio-Román |
Abstract: | We propose to assess the performance of k forecast procedures by exploring the distributions of forecast errors and error losses. We argue that non systematic forecast errors minimize when their distributions are symmetric and unimodal, and that forecast accuracy should be assessed through stochastic loss order rather than expected loss order, which is the way it is customarily performed in previous work. Moreover, since forecast performance evaluation can be understood as a one way analysis of variance, we propose to explore loss distributions under two circumstances; when a strict (but unknown) joint stochastic order exists among the losses of all forecast alternatives, and when such order happens among subsets of alternative procedures. In spite of the fact that loss stochastic order is stronger than loss moment order, our proposals are at least as powerful as competing tests, and are robust to the correlation, autocorrelation and heteroskedasticity settings they consider. In addition, since our proposals do not require samples of the same size, their scope is also wider, and provided that they test the whole loss distribution instead of just loss moments, they can also be used to study forecast distributions as well. We illustrate the usefulness of our proposals by evaluating a set of real world forecasts. Classification JEL: C53, C12, C14. |
Date: | 2014–06 |
URL: | http://d.repec.org/n?u=RePEc:bdr:borrec:825&r=for |
By: | Francisco Javier Eransus (Departamento de Economía Cuantitativa (Department of Quantitative Economics), Facultad de Ciencias Económicas y Empresariales (Faculty of Economics and Business), Universidad Complutense de Madrid); Alfonso Novales Cinca (Departamento de Economía Cuantitativa (Department of Quantitative Economics), Facultad de Ciencias Económicas y Empresariales (Faculty of Economics and Business), Universidad Complutense de Madrid) |
Abstract: | We analyze the effect of parameter estimation error on the size of unconditional population level tests of predictive ability when they are implemented under a class of loss functions we refer to as ‘discrete functions’. The analysis is restricted to linear models in stationary variables. We obtain analytical results for no nested models guaranteeing asymptotic irrelevance of parameter estimation error under a plausible predictive environment and three subsets of discrete loss functions that seem quite appropriate for many economic applications. For nested models, we provide some Monte Carlo evidence suggesting that the asymptotic distribution of the Diebold and Mariano (1995) test is relatively robust to parameter estimation error in many cases if it is implemented under discrete loss functions, unlike what happens under the squared forecast error or the absolute value error loss functions. |
Keywords: | Parameter uncertainty; Forecast accuracy; Discrete loss function. |
JEL: | C53 C52 C12 |
Date: | 2014 |
URL: | http://d.repec.org/n?u=RePEc:ucm:doicae:1422&r=for |
By: | Zhang, Guangfeng; Zhang, Qiong; Majeed, Muhammad Tariq |
Abstract: | Using two measures of private information and high-frequency transaction data from the leading interdealer electronic broking system Reuters D2000-2, we examine the association between exchange rate return and contemporaneous order flow and the predictability power of lagged order flow on the future exchange rate return. Our empirical analysis demonstrates that at high frequency (5, 10, 15, 20, 25, and 30 min) there exists strong positive association between exchange rate returns and contemporaneous order flow. However, the results indicate weak predictability of order flow on the future exchange rate return. |
Keywords: | Exchange Rate, Forecasting, Microstructure Approach |
JEL: | F31 G17 |
Date: | 2013 |
URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:57673&r=for |
By: | Philippe De Peretti (CES - Centre d'économie de la Sorbonne - CNRS : UMR8174 - Université Paris I - Panthéon-Sorbonne); Oren Tapiero (CES - Centre d'économie de la Sorbonne - CNRS : UMR8174 - Université Paris I - Panthéon-Sorbonne) |
Abstract: | The ability to trade in dark-pools without publicly announcing trading orders, concerns regulators and market participants alike. This paper analyzes the information contribution of dark trades to the intraday volatility process. The analysis is conducted by performing a GARCH estimation framework where errors follow the generalized error distribution (GED) and two different proxies for dark trading activity are separately included in the volatility equation. Results indicate that dark trades convey important information on the intraday volatility process. Furthermore, the results highlight the superiority of the proportion of dark trades relative to the proportion of dark volume in affecting the one-step-ahead density forecast |
Keywords: | Dark Pools; Density Forecast; Dark Volume; Dark trade |
Date: | 2014–02–20 |
URL: | http://d.repec.org/n?u=RePEc:hal:cesptp:hal-00984834&r=for |
By: | Denis M. Filatov; Maksim A. Vanyarkho |
Abstract: | We suggest an original physical approach to describe the mechanism of market pricing. The core of our approach is to consider pricing at different time scales separately, using independent equations of motion. Such an approach leads to a pricing model that not only allows estimating the volatility of future market prices, but also permits forecasting the direction of the price move. Alongside with that, it is crucial that our model implies no calibration on historical market data. And last but not least, properties of the model's solution are consistent with those of real markets: it has fat tails, possesses scaling and evinces nonlinear market memory. As our model has been derived with the tip of the pen, it may be not a yet another confirmation of the known empirical facts, but a theoretical justification thereto. Tests on real financial instruments prove the competence of our approach. |
Date: | 2014–06 |
URL: | http://d.repec.org/n?u=RePEc:arx:papers:1406.5718&r=for |
By: | Wim Verhoeven; Arjan Ruis; Tommy Span |
Abstract: | FAMOS, which stands for Financial Analysis Model of Small and Medium Enterprises (SMEs), forecasts assets and capital as expressed on the balance sheet of size classes and sectors. In addition, the model generates a number of financial indicators, from which the financial situation of firms can be derived instantly (e.g. liquidity, solvency). FAMOS distinguishes between 17 sectors and 5 size classes. The modelling of the size-class structure is the surplus value of the model. FAMOS comprises both corporations and non-corporations. Corporations are further divided into micro-sized, small, medium-sized and large enterprises. The model can be used for various purposes. Firstly, model estimates can be used to describe the actual financial situation of firms, and to forecast the balance structure for the coming years, differentiated by size class and sector. Secondly, the impact of changes in turnover, investments, profits and financial costs on the composition of assets and capital can be analyzed. For instance, an increase of the interest rate of 2 percentage points affects the liquidity and solvency of firms. With FAMOS, it is possible to address the effects of such changes across size classes. � |
Date: | 2013–10–21 |
URL: | http://d.repec.org/n?u=RePEc:eim:papers:h201312&r=for |