New Forecasting Papers 2011-04-18

Date:

2011-04-11

By:

Kjetil Martinsen (Norges Bank (Central Bank of Norway))
Francesco Ravazzolo (Norges Bank (Central Bank of Norway))
Fredrik Wulfsberg (Norges Bank (Central Bank of Norway))

URL:

http://d.repec.org/n?u=RePEc:bno:worpap:2011_04&r=for

We assess the forecast ability of Norges Bank’s regional survey for inflation, GDP growth and the unemployment rate in Norway. We propose several factor models based on regional and sectoral information given by the survey. The analysis identifies which information extracted from the ten sectors and the seven regions performs particularly well at forecasting different variables and horizons. Results show that several factor models beat an autoregressive benchmark in forecasting inflation and unemployment rate. However, the factor models are most successful in forecasting GDP growth. Forecast combinations based on past performance give in most cases more accurate forecasts than the benchmark, but they never give the most accurate forecasts.

Keywords:

Keywords: Factor models; macroeconomic forecasting; qualitative survey data.

JEL:

C53

Date:

2011

By:

Michal Rubaszek (National Bank of Poland, Economic Institute)
Pawel Skrzypczynski (National Bank of Poland, Economic Institute)
Grzegorz Koloch (National Bank of Poland, Economic Institute)

URL:

http://d.repec.org/n?u=RePEc:nbp:nbpmis:81&r=for

The literature on exchange rate forecasting is vast. Many researchers have tested whether implications of theoretical economic models or the use of advanced econometric techniques can help explain future movements in exchange rates. The results of the empirical studies for major world currencies show that forecasts from a naive random walk tend to be comparable or even better than forecasts from more sophisticated models. In the case of the Polish zloty, the discussion in the literature on exchange rate forecasting is scarce. This article fills this gap by testing whether non-linear time series models are able to generate forecasts for the nominal exchange rate of the Polish zloty that are more accurate than forecasts from a random walk. Our results confirm the main findings from the literature, namely that it is difficult to outperform a naive random walk in exchange rate forecasting contest.

Keywords:

Exchange rate forecasting; Polish zloty; Markov-switching models; Artificial neural networks

JEL:

C22

Date:

2011

By:

Lee, Byoung-Hoon
Kenkel, Philip L.
Brorsen, B. Wade

URL:

http://d.repec.org/n?u=RePEc:ags:saea11:98829&r=for

Wheat regression models that account for the effect of weather are developed to forecast wheat yield and quality. Spatial lag effects are included. Wheat yield, protein, and test weight level are strongly influenced by weather variables. The forecasting power of the yield and protein models was enhanced by adding the spatial lag effect. Out of sample forecasting tests confirm the modelsâ usefulness in accounting for the variations in average wheat yield and qualities.

Keywords:

prediction, protein, spatial lag, test weight, weather, wheat yield, Agribusiness, Environmental Economics and Policy, Farm Management, Production Economics, Productivity Analysis, Risk and Uncertainty,

Date:

2011

By:

Isengildina-Massa, Olga
Tysinger, David
Gerard, Patrick
MacDonald, Stephen

URL:

http://d.repec.org/n?u=RePEc:ags:saea11:98811&r=for

This study investigated the magnitude of forecast improvements resulting from correction of inefficiencies in USDA cotton forecasts over 1999/00 to 2008/09 marketing years. The aspects of forecast performance included in this study were 1) bias and trends in bias, 2) correlation between forecast error and forecast level, 3) autocorrelation in forecast errors, 4) correlation in forecast revisions. Overall the results of this study demonstrated that some corrections of forecast inefficiencies, such as correction of correlation of error with forecast levels and correlation of error with previous yearâs error resulted in consistent improvement of USDA cotton forecasts, while correction for correlation in forecast revisions did not benefit the forecasts. Correction for bias yielded mixed results likely because USDA has already been applying those corrections to some of the categories and thus our analysis resulted in over-correcting. The framework developed in this study can be used by USDA and other agencies to monitor and improve the performance of their forecasts.

Keywords:

Commodity, Forecast evaluation, Fixed-event forecasts, Government forecasting, Forecast improvement, Agribusiness, Demand and Price Analysis, E37, E3, Q13,

Date:

2011-04-05

By:

Lo Duca, Marco (BOFIT)
Peltonen, Tuomas (BOFIT)

URL:

http://d.repec.org/n?u=RePEc:hhs:bofitp:2011_002&r=for

This paper develops a framework for assessing systemic risks and for predicting (out-of-sample) systemic events, i.e. periods of extreme financial instability with potential real costs. We test the ability of a wide range of “stand alone” and composite indicators in predicting systemic events and evaluate them by taking into account policy makers’ preferences between false alarms and missing signals. Our results highlight the importance of considering jointly various indicators in a multivariate framework. We find that taking into account jointly domestic and global macro-financial vulnerabilities greatly improves the performance of discrete choice models in forecasting systemic events. Our framework shows a good out-of-sample performance in predicting the last financial crisis. Finally, our model would have issued an early warning signal for the United States in 2006Q2, 5 quarters before the emergence of money markets tensions in August 2007.

Keywords:

early warning indicators; asset price booms and busts; financial stress; macro-prudential policies

JEL:

E44

Date:

2011

By:

Pierre-Noël Giraud (CERNA – Centre d'économie industrielle – Mines ParisTech)

URL:

http://d.repec.org/n?u=RePEc:hal:journl:hal-00582825&r=for

Many have attempted to forecast the date of the production peak and the volume of the ultimate reserves of a mineral commodity, using techniques derived from Hubbert's thesis. This note aims at exploring the scientific foundations and therefore the scope of validity of these forecasting techniques. Looking at the basic assumptions of Hubbert's thesis, it concludes that these techniques should not be used to forecast neither the peak (or plateau) of the annual production rate, nor the ultimate reserves of any mineral, unless given exceptional conditions.