Was the Recent Downturn in US GDP Predictable?

In this issue we have: Was the Recent Downturn in US GDP Predictable, Forecasting Binary Outcomes, Managing Sales Forecasters, Forecasting Inflation and the Inflation Risk Premiums Using Nominal Yields, and many more.




  1. Was the Recent Downturn in US GDP Predictable?

    Date: 2012-11
    By: Mehmet Balcilar (Eastern Mediterranean University)
    Rangan Gupta (University of Pretoria)
    Anandamayee Majumdar (University of North Texas Health Science Center)
    Stephen M. Miller (University of Nevada, Las Vegas and University of Connecticut)
    URL: http://d.repec.org/n?u=RePEc:uct:uconnp:2012-38&r=for
    This paper uses small set of variables– real GDP, the inflation rate, and the short-term interest rate — and a rich set of models — athoeretical and theoretical, linear and nonlinear, as well as classical and Bayesian models — to consider whether we could have predicted the recent downturn of the US real GDP. Comparing the performance by root mean squared errors of the models to the benchmark random-walk model, the two theoretical models, especially the nonlinear model, perform well on the average across all forecast horizons in out-of-sample forecasts, although at specific forecast horizons certain nonlinear athoeretical models perform the best. The nonlinear theoretical model also dominates in our ex ante forecast of the Great Recession, suggesting that developing forward-looking, microfounded, nonlinear, dynamic-stochastic-general-equilibrium models of the economy, may prove crucial in forecasting turning points. JEL Classification: C32, E37 Key words: Forecasting, Linear and non-linear models, Great Recession
  2. Forecasting Binary Outcomes

    Date: 2012
    By: Kajal Lahiri
    Liu Yang
    URL: http://d.repec.org/n?u=RePEc:nya:albaec:12-09&r=for
    Binary events are involved in many economic decision problems. In recent years, considerable progress has been made in diverse disciplines in developing models for forecasting binary outcomes. We distinguish between two types of forecasts for binary events that are generally obtained as the output of regression models: probability forecasts and point forecasts. We summarize specification, estimation, and evaluation of binary response models for the purpose of forecasting in a unified framework which is characterized by the joint distribution of forecasts and actuals, and a general loss function. Analysis of both the skill and the value of probability and point forecasts can be carried out within this framework. Parametric, semiparametric, nonparametric, and Bayesian approaches are covered. The emphasis is on the basic intuitions underlying each methodology, abstracting away from the mathematical details.
  3. Managing Sales Forecasters

    Date: 2012-12-03
    By: Bert de Bruijn (Erasmus University Rotterdam)
    Philip Hans Franses (Erasmus University Rotterdam)
    URL: http://d.repec.org/n?u=RePEc:dgr:uvatin:20120131&r=for
    A Forecast Support System (FSS), which generates sales forecasts, is a sophisticated business analytical tool that can help to improve targeted business decisions. Many companies use such a tool, although at the same time they may allow managers to quote their own forecasts. These sales forecasters (managers) can take the FSS output as their input, but they can also fully ignore the FSS out- comes. We propose a methodology that allows to evaluate the forecast accuracy of these managers, relative to the FSS, while taking aboard latent variation across managers’ behavior. We show that the results, here for a large Germany-based pharmaceutical company, can in fact be used to manage the sales forecasters by giving clear-cut recommendations for improvement.
    Keywords: Forecast Support System; Sales forecasters; Forecast accuracy
    JEL: M11
  4. Forecasting Inflation and the Inflation Risk Premiums Using Nominal Yields

    Date: 2012
    By: Bruno Feunou
    Jean-Sébastien Fontaine
    URL: http://d.repec.org/n?u=RePEc:bca:bocawp:12-37&r=for
    We provide a decomposition of nominal yields into real yields, expectations of future inflation and inflation risk premiums when real bonds or inflation swaps are unavailable or unreliable due to their relative illiquidity. We combine nominal yields with surveys of inflation forecasts within a no-arbitrage model where conditional expectations are latent but spanned by the history of the observed data, analog to a GARCH model for the conditional variance. The filtering problem is numerically trivial and we conduct a battery of out-of-sample comparisons. Our favored model matches the quarterly inflation forecasts from surveys and uses the information in yields to produce the best monthly forecasts. Moreover, we restrict the distribution of the inflation Sharpe ratios to achieve economically reasonable estimates of the inflation risk premium and of the real rates. We find that the inflation risk premium (i) is positive on average, (ii) rises when the unemployment rate increases and (iii) when the level of interest rates decreases. Hence, real yields are more pro-cyclical than nominal yields due to variations of the inflation risk premiums.
    Keywords: Asset Pricing; Econometric and statistical methods; Inflation and prices; Interest rates
    JEL: E43
  5. Real-time nowcasting with a Bayesian mixed frequency model with stochastic volatility

    Date: 2012
    By: Andrea Carriero
    Todd E. Clark
    Massimiliano Marcellino
    URL: http://d.repec.org/n?u=RePEc:fip:fedcwp:1227&r=for
    This paper develops a method for producing current-quarter forecasts of GDP growth with a (possibly large) range of available within-the-quarter monthly observations of economic indicators, such as employment and industrial production, and financial indicators, such as stock prices and interest rates. In light of existing evidence of time variation in the variances of shocks to GDP, we consider versions of the model with both constant variances and stochastic volatility. We also evaluate models with either constant or time-varying regression coefficients. We use Bayesian methods to estimate the model, in order to facilitate providing shrinkage on the (possibly large) set of model parameters and conveniently generate predictive densities. We provide results on the accuracy of nowcasts of real-time GDP growth in the U.S. from 1985 through 2011. In terms of point forecasts, our proposal is comparable to alternative econometric methods and survey forecasts. In addition, it provides reliable density forecasts, for which the stochastic volatility specification is quite useful, while parameter time-variation does not seem to matter.
    Keywords: Bayesian statistical decision theory
  6. An Error Correction Analysis of Visitor Arrivals to the Bahamas

    Date: 2012-02-11
    By: Charles, Jacky S.
    Fullerton, Thomas M., Jr.
    URL: http://d.repec.org/n?u=RePEc:pra:mprapa:43064&r=for
    Tourism is the major domestic export for many countries in the Caribbean region. Given this, the variables which influence tourism demand in this region, as well as accurate forecasts, can assist policy makers in their planning efforts and growth strategies. This study utilizes error correction models (ECMs) to analyze tourism demand in the Bahamas. Findings suggest that income and habit persistence/word of mouth advertising are the primary determinants of tourism demand in the Bahamas, while the cost of travel is generally insignificant. To further assess model reliability, forecasts of the ECMs are compared to random walk and random walk with drift benchmarks. The study finds that while the ECMs provide fairly reliable forecasts, their performances are not superior to those provided by random walk benchmarks.
    Keywords: Tourism; Error Correction Analysis; Forecasts; Bahamas
    JEL: O54
  7. Can consumer confidence data predict real variables? Evidence from Croatia

    Date: 2012-10
    By: Marija Kuzmanovic (EBRD)
    Peter Sanfey (EBRD)
    URL: http://d.repec.org/n?u=RePEc:ebd:wpaper:151&r=for
    This paper uses monthly data to examine the links between consumer confidence and real economic variables in Croatia, and it tests whether movements in the former contain predictive power for the latter. The results suggest that changes in consumer confidence help to explain retail turnover and imports, while expectations about forthcoming major purchases have particularly strong predictive power for retail turnover. We also find that the inclusion of confidence on the right-hand side improves the fit of simple models of retail turnover, a variable that is highly correlated with quarterly GDP. The results therefore highlight the usefulness of these survey data in helping to explain and forecast the real economy.
    Keywords: consumer confidence; Croatia
    JEL: E2
  8. Policy Interest-Rate Expectations in Sweden: A Forecast Evaluation

    Date: 2012-11-30
    By: Österholm, Pär (National Institute of Economic Research)
    Beechey, Meredith (Sveriges Riksbank)
    URL: http://d.repec.org/n?u=RePEc:hhs:nierwp:0127&r=for
    In this paper, we evaluate two types of Swedish policy interest-rate ex-pectations: survey expectations and expectations inferred from market pricing. The data are drawn from the most prominent survey of finan-cial-market economists and from Swedish financial markets and the data are carefully matched by date to ensure comparability. Results show that both kinds of expectations suffer from bias and inefficiency and in terms of forecast precision there is no clear winner. We do find, though, evi-dence that the forecast accuracy of both kinds of policy-rate expectations has improved since the Riksbank started publishing its own policy-rate forecast, suggesting that this communication strategy has been beneficial from a policy perspective.
    Keywords: Survey data; Monetary policy; Sveriges Riksbank
    JEL: E47
  9. Time Horizons And Smoothing In the Bank of England’s Reaction Function: The Contrast Between The Standard GMM And Ex Ante Forecast Approaches

    Date: 2012
    By: David Cobham
    Yue Kang
    URL: http://d.repec.org/n?u=RePEc:hwe:hwuedp:1208&r=for
    The monetary policy reaction function of the Bank of England is estimated by the standard GMM approach and the ex-ante forecast method developed by Goodhart (2005), with particular attention to the horizons for inflation and output at which each approach gives the best fit. The horizons for the ex-ante approach are much closer to what is implied by the Bank’s view of the transmission mechanism, while the GMM approach produces an implausibly slow adjustment of the interest rate, and suffers from a weak instruments problem. These findings suggest a strong preference for the ex-ante approach.
  10. The Role of Credit in International Business Cycles

    Date: 2012
    By: TengTeng Xu
    URL: http://d.repec.org/n?u=RePEc:bca:bocawp:12-36&r=for
    This paper examines the role of bank credit in modeling and forecasting business cycle fluctuations, and investigates the international transmission of US credit shocks, using a global vector autoregressive (GVAR) framework and associated country-specific error correction models. The paper constructs and compiles a dataset on bank credit for 33 advanced and emerging market economies from 1979Q1 to 2009Q4. The empirical results suggest that the incorporation of credit provides significant improvement in modeling and forecasting output growth, changes in inflation and long run interest rates, for countries with developed banking sector. Impulse response analysis provide strong evidence of the international spillover of US credit shocks to the UK, the Euro area, Japan and other industrialized economies, and the propagation to the real economy.
    Keywords: Business fluctuations and cycles; Credit and credit aggregates; Econometric and statistical methods; International financial markets
    JEL: C32
  11. Dynamic Factor Models with Infinite-Dimensional Factor Space: One-Sided Representations

    Date: 2012-12
    By: Mario Forni
    Marc Hallin
    Marco Lippi
    Paolo Zaffaroni
    URL: http://d.repec.org/n?u=RePEc:eca:wpaper:2013/134458&r=for
    Abstract. Factor model methods recently have become extremely popular in the theory andpractice of large panels of time series data. Those methods rely on various factor models whichall are particular cases of the Generalized Dynamic Factor Model (GDFM) introduced inForni, Hallin, Lippi and Reichlin (2000). That paper, however, relies on Brillinger’s dynamicprincipal components. The corresponding estimators are two-sided filters whose performanceat the end of the observation period or for forecasting purposes is rather poor. No such problem arises with estimators based on standard principal components, which have beendominant in this literature. On the other hand, those estimators require the assumptionthat the space spanned by the factors has finite dimension. In the present paper, we arguethat such an assumption is extremely restrictive and potentially quite harmful. Elaboratingupon recent results by Anderson and Deistler (2008a, b) on singular stationary processes withrational spectrum, we obtain one-sided representations for the GDFM without assuming finitedimension of the factor space. Construction of the corresponding estimators is also brieflyoutlined. In a companion paper, we establish consistency and rates for such estimators, andprovide Monte Carlo results further motivating our approach.
    Keywords: generalized dynamic factor models; vector processes with singular spectral density; one-sided representations for dynamic models
    JEL: C00
  12. Gasoline Prices, Fuel Economy, and the Energy Paradox

    Date: 2012-11
    By: Hunt Allcott
    Nathan Wozny
    URL: http://d.repec.org/n?u=RePEc:nbr:nberwo:18583&r=for
    It is often asserted that consumers undervalue future gasoline costs relative to purchase prices when they choose between automobiles, or equivalently that they have high “implied discount rates” for these future energy costs. We show how this can be tested by measuring whether relative prices of vehicles with different fuel economy ratings fully adjust to time series variation in gasoline price forecasts. We then test the model using a detailed dataset based on 86 million transactions at auto dealerships and wholesale auctions between 1999 and 2008. Over our base sample, vehicle prices move as if consumers are indifferent between one dollar in discounted future gas costs and only 76 cents in vehicle purchase price. We document how endogenous market shares and utilization, measurement error, and different gasoline price forecasts can affect the results, and we show how to address these issues empirically. We also provide unique empirical evidence of sticky information: vehicle markets respond to changes in gasoline prices with up to a six month delay.
    JEL: D03
  13. Did local lenders forecast the bust? Evidence from the real estate market

    Date: 2012
    By: Kristle Romero Cortés
    URL: http://d.repec.org/n?u=RePEc:fip:fedcwp:1226&r=for
    This paper shows that mortgage lenders with a physical branch near the property being financed have better information about home-price fundamentals than nonlocal lenders. During the real estate run-up from 2002-06, home price growth negatively correlates with the share of loans made by local lenders, namely lenders with a branch in the respective county. Moreover, home prices fell less from 2006-09 in areas where more of the loans were made by local lenders. California foreclosure rates during the crisis are negatively correlated with local lending during the run-up. A 1 standard deviation increase in local loans is associated with 5 fewer foreclosures for every 1,000 houses. When local lenders retain loans for their portfolio rather than securitizing, the results for both home price growth and foreclosures are even stronger.
    Keywords: Mortgage loans ; Foreclosure ; Housing
  14. Stochastic PDEs and Quantitative Finance: The Black-Scholes-Merton Model of Options Pricing and Riskless Trading

    Date: 2012-12
    By: Brandon Kaplowitz
    Siddharth G. Reddy
    URL: http://d.repec.org/n?u=RePEc:arx:papers:1212.1919&r=for
    Differential equations can be used to construct predictive models of a diverse set of real-world phenomena like heat transfer, predator-prey interactions, and missile tracking. In our work, we explore one particular application of stochastic differential equations, the Black-Scholes-Merton model, which can be used to predict the prices of financial derivatives and maintain a riskless, hedged position in the stock market. This paper is intended to provide the reader with a history, derivation, and implementation of the canonical model as well as an improved trading strategy that better handles arbitrage opportunities in high-volatility markets. Our attempted improvements may be broken into two components: an implementation of 24-hour, worldwide trading designed to create a continuous trading scenario and the use of the Student’s t-distribution (with two degrees of freedom) in evaluating the Black-Scholes equations.


Taken from the NEP-FOR mailing list edited by Rob Hyndman.