In this issue we have: On economic evaluation of directional forecasts, Predicting unemployment in short samples with internet job search query data, Does Accounting for Spatial Effects Help Forecasting the Growth of Chinese Provinces? Nonlinearity, Nonstationarity, and Spurious Forecasts, Forecasting Inflation Using Dynamic Model Averaging, and more.

200910 
By:  Oliver Blaskowitz Helmut Herwartz 
URL:  http://d.repec.org/n?u=RePEc:hum:wpaper:sfb649dp2009052&r=for 
It is commonly accepted that information is helpful if it can be exploited to improve a decision mak ing process. In economics, decisions are often based on forecasts of up{ or downward movements of the variable of interest. We point out that directional forecasts can provide a useful framework to assess the economic forecast value when loss functions (or success measures) are properly formu lated to account for realized signs and realized magnitudes of directional movements. We discuss a general approach to evaluate (directional) forecasts which is simple to implement, robust to outlying or unreasonable forecasts and which provides an economically interpretable loss/success functional framework. As such, the measure of directional forecast value is a readily available alternative to the commonly used squared error loss criterion.  
Keywords:  Directional forecasts, directional forecast value, forecast evaluation, economic forecast value, mean squared forecast error, mean absolute forecast error 
JEL:  C52 

20091030 
By:  Francesco, D'Amuri 
URL:  http://d.repec.org/n?u=RePEc:pra:mprapa:18403&r=for 
This article tests the power of a novel indicator based on job search related web queries in predicting quarterly unemployment rates in short samples. Augmenting standard time series specifications with this indicator definitely improves outofsample forecasting performance at nearly all insample interval lengths and forecast horizons, both when compared with models estimated on the same or on a much longer time series interval.  
Keywords:  Google econometrics; Forecast comparison; Keyword search; Unemployment; Time series models. 
JEL:  C53 

2009 
By:  Eric Girardin Konstantin A. Kholodilin 
URL:  http://d.repec.org/n?u=RePEc:diw:diwwpp:dp938&r=for 
In this paper, we make multistep forecasts of the annual growth rates of the real GRP for each of the 31 Chinese provinces simultaneously. Beside the usual panel data models, we use panel models that explicitly account for spatial dependence between the GRP growth rates. In addition, the possibility of spatial effects being different for different groups of provinces (Interior and Coast) is allowed. We find that both pooling and accounting for spatial effects helps substantially improve the forecast performance compared to the benchmark models estimated for each of the provinces separately. It was also shown that effect of accounting for spatial dependence is even more pronounced at longer forecasting horizons (the forecast accuracy gain as measured by the root mean squared forecast error is about 8% at 1year horizon and exceeds 25% at 13 and 14year horizon).  
Keywords:  Chinese provinces, forecasting, dynamic panel model, spatial autocorrelation, groupspecific spatial dependence 
JEL:  C21 

20091103 
By:  Marmer, Vadim 
URL:  http://d.repec.org/n?u=RePEc:ubc:pmicro:vadim_marmer200960&r=for 
Implications of nonlinearity, nonstationarity and misspecification are considered from a forecasting perspective. Our model allows for small departures from the martingale difference sequence hypothesis by including a nonlinear component, formulated as a general, integrable transformation of the I(1) predictor. We assume that the true generating mechanism is unknown to the econometrician and he is therefore forced to use some approximating functions. It is shown that in this framework the linear regression techniques lead to spurious forecasts. Improvements of the forecast accuracy are possible with properly chosen nonlinear transformations of the predictor. The paper derives the limiting distribution of the forecasts' MSE. In the case of square integrable approximants, it depends on the Lâ‚‚distance between the nonlinear component and approximating function. Optimal forecasts are available for a given class of app! roximants.  
Keywords:  Forecasting; integrated time series; misspecified models; nonlinear transformations; stock returns 

200901 
By:  Gary Koop (Department of Economics, University of Strathclyde and RCEA) Dimitris Korobilis (Department of Economics, University of Strathclyde and RCEA) 
URL:  http://d.repec.org/n?u=RePEc:rim:rimwps:34_09&r=for 
There is a large literature on forecasting inflation using the generalized Phillips curve (i.e. using forecasting models where inflation depends on past inflation, the unemployment rate and other predictors). The present paper extends this literature through the use of econometric methods which incorporate dynamic model averaging. These not only allow for coefficients to change over time (i.e. the marginal effect of a predictor for inflation can change), but also allows for the entire forecasting model to change over time (i.e. different sets of predictors can be relevant at different points in time). In an empirical exercise involving quarterly US inflation, we fi…nd that dynamic model averaging leads to substantial forecasting improvements over simple benchmark approaches (e.g. random walk or recursive OLS forecasts) and more sophisticated approaches such as those using time varying coefficient models.  
Keywords:  Option Pricing; Modular Neural Networks; Nonparametric Methods 
JEL:  E31 

200904 
By:  ChulYong Lee Jongsu LEE (Technology Management, Economics and Policy Program(TEMEP), Seoul National University) 
URL:  http://d.repec.org/n?u=RePEc:snv:dp2009:200903&r=for 
Forecasting demand for new technology for which few historical data observations are available is difficult but essential to successful marketing. The current study suggests an alternative forecasting methodology based on a hazard rate model using stated and revealed preferences. In estimating the hazard rate, information is derived initially through conjoint analysis based on a consumer survey and then updated using Bayes¡¯ theorem with available market data. Based on the results of the empirical analysis, the model described here can significantly improve demand forecasting for newly introduced technologies.  
Keywords:  demand forecasting, conjoint analysis, Bayesian update, telematics service 

20091106 
By:  Domenico Giannone (ECARES, Université Libre de Bruxelles and CEPR) Lucrezia Reichlin (London Business School and CEPR) Saverio Simonelli (Università di Napoli Federico II, EUI and CSEF) 
URL:  http://d.repec.org/n?u=RePEc:sef:csefwp:240&r=for 
This paper assesses the role of surveys for the early estimates of GDP in the euro area in a modelbased automated procedures which exploits the timeliness of their release. The analysis is conducted using both an historical evaluation and a real time case study on the current conjuncture.  
Keywords:  Forecasting; factor model; real time data; large data sets; survey 
JEL:  E52 

200904 
By:  Jongsu Lee ChulYong (Technology Management, Economics and Policy Program(TEMEP), Seoul National University) 
URL:  http://d.repec.org/n?u=RePEc:snv:dp2009:200904&r=for 
The paper introduces a replacement forecasting model that operates at the brand level and overcomes limitations of existing models. The model (1) consists of a diffusion model and a time series model; (2) separately identifies the diffusion of firsttime purchases and that of replacement purchases; (3) reflects brands¡¯ competitive factors affecting product diffusion; and (4) characterizes consumers¡¯ different replacement cycles.The model is applied to South Korea¡¯s mobile handset market. The model performs well in terms of its fit and forecasting when compared with other forecasting models incorporating replacement and repeat purchases. The usefulness of the model stems from its ability to describe complicated environments and its flexibility in including multiple factors that drive diffusion in the regression analysis.  
Keywords:  Replacement, Diffusion model, Mobile handset market 

2009 
By:  Andres Fernandez Norman R. Swanson 
URL:  http://d.repec.org/n?u=RePEc:fip:fedpwp:0928&r=for 
In this paper, the authors empirically assess the extent to which early release inefficiency and definitional change affect prediction precision. In particular, they carry out a series of exante prediction experiments in order to examine: the marginal predictive content of the revision process, the tradeoffs associated with predicting different releases of a variable, the importance of particular forms of definitional change, which the authors call "definitional breaks," and the rationality of early releases of economic variables. An important feature of our rationality tests is that they are based solely on the examination of exante predictions, rather than being based on insample regression analysis, as are many tests in the extant literature. Their findings point to the importance of making realtime datasets available to forecasters, as the revision process has marginal predictive content, and because predictive ! accuracy increases when multiple releases of data are used when specifying and estimating prediction models. The authors also present new evidence that early releases of money are rational, whereas prices and output are irrational. Moreover, they find that regardless of which release of our price variable one specifies as the "target" variable to be predicted, using only "first release" data in model estimation and prediction construction yields mean square forecast error (MSFE) "best" predictions. On the other hand, models estimated and implemented using "latest available release" data are MSFEbest for predicting all releases of money. The authors argue that these contradictory findings are due to the relevance of definitional breaks in the data generating processes of the variables that they examine. In an empirical analysis, they examine the realtime predictive content of money for income, and they find that vector autoregressions with money do not perform significantl! y worse than autoregressions, when predicting output during the last 2 0 years.  
Keywords:  Economic forecasting ; Econometrics 

2009 
By:  Öller, LE Stockhammar, P 
URL:  http://d.repec.org/n?u=RePEc:pra:mprapa:18582&r=for 
The distribution of differences in logarithms of the Dow Jones share index is compared to the normal (N), normal mixture (NM) and a weighted sum of a normal and an Assymetric Laplace distribution (NAL). It is found that the NAL fits best. We came to this result by studying samples with high, medium and low volatility, thus circumventing strong heteroscedasticity in the entire series. The NAL distribution also fitted economic growth, thus revealing a new analogy between financial data and real growth.  
Keywords:  Density forecasting; heteroscedasticity; mixed Normal Asymmetric Laplace distribution; Method of Moments estimation; connection with economic growth. 
JEL:  C20 

2009 
By:  Sébastien Laurent Jeroen V.K. Rombouts Francesco Violante 
URL:  http://d.repec.org/n?u=RePEc:lvl:lacicr:0948&r=for 
A large number of parameterizations have been proposed to model conditional variance dynamics in a multivariate framework. However, little is known about the ranking of multivariate volatility models in terms of their forecasting ability. The ranking of multivariate volatility models is inherently problematic because it requires the use of a proxy for the unobservable volatility matrix and this substitution may severely affect the ranking. We address this issue by investigating the properties of the ranking with respect to alternative statistical loss functions used to evaluate model performances. We provide conditions on the functional form of the loss function that ensure the proxybased ranking to be consistent for the true one – i.e., the ranking that would be obtained if the true variance matrix was observable. We identify a large set of loss functions that yield a consistent ranking. In a simulation study, we sam! ple data from a continuous time multivariate diffusion process and compare the ordering delivered by both consistent and inconsistent loss functions. We further discuss the sensitivity of the ranking to the quality of the proxy and the degree of similarity between models. An application to three foreign exchange rates, where we compare the forecasting performance of 16 multivariate GARCH specifications, is provided.  
Keywords:  Volatility, multivariate GARCH, Matrix norm, Loss function, Model confidence set 
JEL:  C10 

20091030 
By:  O'Brien, Meghan 
URL:  http://d.repec.org/n?u=RePEc:isu:genres:13119&r=for 
Despite pronouncements that the recession ended in the third quarter of 2009, the prospects for the holiday retail season remain bleak. This report describes the factors that will continue to suppress retail sales for the holiday season and beyond and forecasts how different retail categories will fare this holiday season. 

200910 
By:  Jamie Hall (Reserve Bank of Australia) Jarkko Jääskelä (Reserve Bank of Australia) 
URL:  http://d.repec.org/n?u=RePEc:rba:rbardp:rdp200906&r=for 
This paper examines the statistical properties of inflation in a sample of inflationtargeting and noninflationtargeting countries. First, it analyses the timevarying volatility of a measure of the persistent component of inflation. Based on this measure, inflationtargeting countries (Australia, Canada, New Zealand, Sweden and the United Kingdom) have experienced a relatively more pronounced fall in the volatility of inflation than noninflationtargeting countries (Austria, France, Germany, Japan and the United States). But it is hard to say whether inflation is more volatile in inflationtargeting or noninflationtargeting countries. Second, it analyses whether inflation became easier to forecast after the introduction of inflation targeting. It finds that inflation became easier to forecast in both inflationtargeting and noninflationtargeting countries; the improvement was greater for the former group but fore! cast errors remain smaller for the latter group.  
Keywords:  inflation; time series econometrics 
JEL:  C53 

2009 
By:  Valentina Corradi Norman R. Swanson 
URL:  http://d.repec.org/n?u=RePEc:fip:fedpwp:0929&r=for 
This paper develops tests for comparing the accuracy of predictive densities derived from (possibly misspecified) diffusion models. In particular, the authors first outline a simple simulationbased framework for constructing predictive densities for onefactor and stochastic volatility models. Then, they construct accuracy assessment tests that are in the spirit of Diebold and Mariano (1995) and White (2000). In order to establish the asymptotic properties of their tests, the authors also develop a recursive variant of the nonparametric simulated maximum likelihood estimator of Fermanian and Salanié (2004). In an empirical illustration, the predictive densities from several models of the onemonth federal funds rates are compared.  
Keywords:  Econometric models – Evaluation ; Stochastic analysis 

20091110 
By:  Xin Jin John M Maheu 
URL:  http://d.repec.org/n?u=RePEc:tor:tecipa:tecipa382&r=for 
This paper proposes a new dynamic model of realized covariance (RCOV) matrices based on recent work in timevarying Wishart distributions. The specifications can be linked to returns for a joint multivariate model of returns and covariance dynamics that is both easy to estimate and forecast. Realized covariance matrices are constructed for 5 stocks using highfrequency intraday prices based on positive semidefinite realized kernel estimates. We extend the model to capture the strong persistence properties in RCOV. Outofsample performance based on statistical and economic metrics show the importance of this. We discuss which features of the model are necessary to provide improvements over a traditional multivariate GARCH model that only uses daily returns.  
Keywords:  eigenvalues, dynamic conditional correlation, predictive likelihoods, MCMC 
JEL:  C11 
Taken from the NEPFOR mailing list edited by Rob Hyndman.