Short-run Forecasts Research Articles

Повышение качества прогнозирования простейшими методами комбинирования отдельных прогнозов

Combining forecasts is considered the easiest way to improve the forecast quality compared to individual models. In this paper, we test the capabilities of the simplest methods of combination, such as simple averages and estimates based on the standard error of previous forecasts, to improve the performance of short-run forecasts of five resource price indicators (oil and metals). The basis of the work is the Gaidar Institute forecasts database, which provides the database of primary forecasts and allows you to calculate their combinations in real time. Based on the obtained results we conclude that even the simplest methods of combination are a way to improve the accuracy of forecasts. In addition, in the case of resource prices, one can even single out a group of methods (namely, combining with weights inversely proportional to the squared errors of individual forecasts) that provide the maximum gain in quality for the most periods.

Do more stringent policies reduce daily COVID-19 case counts? Evidence from Canadian provinces

The enactment of COVID-19 policies in Canada falls under provincial jurisdiction. This study exploits time-series variation across four Canadian provinces to evaluate the effects of stricter COVID-19 policies on daily case counts. Employing data from this time-period allows an evaluation of the efficacy of policies independent of vaccine impacts. While both OLS and IV results offer evidence that more stringent Non-Pharmaceutical Interventions (NPIs) can reduce daily case counts within a short time-period, IV estimates are larger in magnitude. Hence, studies that fail to control for simultaneity bias might produce confounded estimates of the efficacy of NPIs. However, IV estimates should be treated as correlations given the possibility of other unobserved determinants of COVID-19 spread and mismeasurement of daily cases. With respect to specific policies, mandatory mask usage in indoor spaces and restrictions on business operations are significantly associated with lower daily cases. We also test the efficacy of different forecasting models. Our results suggest that Gradient Boosted Regression Trees (GBRT) and Seasonal Autoregressive-Integrated Moving Average (SARIMA) models produce more accurate short-run forecasts relative to Vector Auto Regressive (VAR), and Susceptible–Infected–Removed (SIR) epidemiology models. Forecasts from SIR models are also inferior to results from basic OLS regressions. However, predictions from models that are unable to correct for endogeneity bias should be treated with caution.

Short Run Forecast of Inflation Rate in India

Short Run Forecast of Inflation Rate in India

Beta autoregressive moving average model selection with application to modeling and forecasting stored hydroelectric energy

We evaluate the accuracy of model selection and associated short-run forecasts using beta autoregressive moving average (βARMA) models, which are tailored for modeling and forecasting time series that assume values in the standard unit interval, (0,1), such as rates, proportions, and concentration indices. Different model selection strategies are considered, including one that uses data resampling. Simulation evidence on the frequency of correct model selection favors the bootstrap-based approach. Model selection based on information criteria outperforms that based on forecasting accuracy measures. A forecasting analysis of the proportion of stored hydroelectric energy in South Brazil is presented and discussed. The empirical evidence shows that model selection based on data resampling typically leads to more accurate out-of-sample forecasts.

Short-run forecast and reduction mechanism of CO2 emissions: a Chinese province-level study.

Rational prediction of future CO2 at the regional level is essential to the carbon emission reduction targets in China. The primary aim of this study is to examine the applicability of an up-to-date forecast algorithm, namely dynamic mode decomposition (DMD), in provincial CO2 emission prediction. The testing results validate the accuracy and application value of the DMD short-run forecast, which may provide method reference for relevant policy formulation and research areas. Moreover, the 2020 provincial economic situation and CO2 emissions in China are projected via DMD. On this basis, the unqualified provinces regarding CO2 emission reduction are identified considering the relative standard and absolute standard, and the corresponding mitigation paths are proposed through decoupling analysis and shadow price calculation. The results indicate that the unqualified provinces include Heilongjiang, Gansu, Shanxi, Hebei, Liaoning, Jilin, Shaanxi, and Inner Mongolia. The open-emission-reduction mechanism should be adopted in the first five provinces; the conservative one should be applied in the other provinces. Graphical abstract.

Naive Forecast for COVID-19 in Utah Based on the South Korea and Italy Models-the Fluctuation between Two Extremes.

Differences in jurisdictional public health actions have played a significant role in the relative success of local communities in combating and containing the COVID-19 pandemic. We forecast the possible COVID-19 outbreak in one US state (Utah) by applying empirical data from South Korea and Italy, two countries that implemented disparate public health actions. Forecasts were created by aligning the start of the pandemic in Utah with that in South Korea and Italy, getting a short-run forecast based on actual daily rates of spread, and long-run forecast by employing a log-logistic model with four parameters. Applying the South Korea model, the epidemic peak in Utah is 169 cases/day, with epidemic resolution by the end of May. Applying the Italy model, new cases are forecast to exceed 200/day by mid-April, with the potential for 250 new cases a day at the epidemic peak, with the epidemic continuing through the end of August. We identify a 3-month variation in the likely length of the pandemic, a 1.5-fold difference in the number of daily infections at outbreak peak, and a 3-fold difference in the expected cumulative cases when applying the experience of two developed countries in handling this virus to the Utah context.

Using ARIMA Models to Forecasting of Economic Variables of Wheat Crop in Afghanistan

Wheat is considered the main food crops in Afghanistan, whether to use it for majority of the population consumption or to use it in some industries and others.
 Problem: Afghanistan suffers from a large gap between production and consumption, so the current research investigates the problem arising from a shortage of wheat production to meet self-sufficiency of the population.
 Methods: The time series analysis can provide short-run forecast for sufficiently large amount of data on the concerned variables very precisely. In univariate time series analysis, the ARIMA models are flexible and widely used. The ARIMA model is the combination of three processes: (i) Autoregressive (AR) process, (ii) Differencing process and (iii) Moving-Average (MA) process. These processes are known in statistical literature as main univariate time series models and are commonly used in many applications. Where, Estimation of future wheat requirement is one of the essential tools that may help decision-makers to determine wheat needs and then developing plans that help reduce the gap between production and consumption. A solid strategy that widely applying of improved seeds and fertilizers, an effective research and extension system for better crop management is necessary to eliminate this gap for self-sufficiency in wheat production, besides providing the necessary financial sums for that. Where most prediction methods are valid for one-year prediction. However, moving prediction methods have been found to measure and predict the future movement of the dependent variable.
 Aims: The current research aims to prediction for Area, Productivity, Production, Consumption and Population over the period (2002-2017), to estimate the values of these variables in the period of (2018-2030).
 Results: The results showed that through the drawing of the historical data for Planted area, Productivity, Production, Consumption and Population of wheat crop it was evident that the series data is not static due to an increasing or a decreasing of general trend, which means the instability of the average, by using Auto-correlation function (ACF) and Partial Correlation Function to detect the stability of the time series, The results showed also, the significance of Autocorrelation coefficient and partial correlation coefficient values, which indicates that the time series is not static.

Importance of Remittances Income in Mexico (1995 to 2017)

ABSTRACTThe hypothesis that Mexican remittances (1995 to 2017), one of the main sources of foreign income in Mexico, explain part of the country’s economic growth and that they are a good indicator of the welfare of the population measured through private consumption was not rejected. When applying an autoregressive vector model, there is a causal relationship between remittances and the service sector GDP, but not for industrial GDP. The Stolper–Samuelson theorem is also tested, the concentration of remittances is analyzed for each Mexican state, and the short-run forecast of remittances is presented.

Estimating the Equity Risk Premium Using Implied Cost of Capital

Research on the implied cost of capital (ICC) has found that the equity risk premium is approximately 3%, on average, much lower than estimates based on the mean of historical stock market returns. The validity of such ICC estimates, however, faces both theoretical and empirical challenges. The theoretical equivalence between ICC and expected return requires the stringent condition that the latter is a constant, which is inconsistent with theory and empirical evidence. The empirical estimation of ICC depends on short-run and long-run earnings forecasts, whose biases can severely limit the validity of the estimates. By employing a forecasting procedure that induces little bias in both short-run and long-run forecasts and taking into account the stochastic nature of expected returns, we show that the average market risk premium ranges between 3% and 6%. We also demonstrate that the results of prior research are affected by input errors that are partially self-canceling.

Understanding the Volatility of the Canadian Exchange Rate

In this Commentary, we document the nature of the Bank of Canada’s current monetary policy regime by focusing on the following questions: what are the historical determinants of the Canadian–US dollar nominal exchange rate, and can they be used in real-time forecasting applications? We find that the current real exchange rate is more useful than commodity prices for forecasting changes in the nominal exchange rate. In fact, short-run forecasts based on the real exchange rate are as good as random-walk forecasts according to which the future exchange rate is expected to be the same as today’s. Strikingly, medium- and long-run forecasts based on the real exchange rate are superior to random-walk forecasts. We argue that these findings reflect the fact Bank of Canada and the U.S. Federal Reserve System follow similar inflation-targeting regimes and neither actively manages exchange rates. A fundamental question is whether Canadian policymakers are satisfied with the current inflation targeting regime. A cost of the current regime is that it allows for very volatile nominal and real exchange rates. A benefit is that consumers and firms can avoid many of the changes in prices and wages that would be required if the nominal exchange rate did not adjust in a flexible manner. In this Commentary, we take no stand on the merits of the current regime. Instead, we highlight the tradeoffs that policymakers face. Evaluating the costs and benefits of those tradeoffs should play an important role in the process leading to the Bank of Canada’s next five-year agreement with the government.

Using Local Information to Improve Short-Run Corn Price Forecasts

Abstract We examine the short-run forecasting problem in a data set of daily prices from 134 corn buying locations from seven states – Iowa, Illinois, Indiana, Ohio, Minnesota, Nebraska, and Kansas. We ask the question: is there useful forecasting information in the cash bids from nearby markets? We use several criteria, including a Granger causality criterion, to specify forecast models that rely on the recent history of a market, the recent histories of nearby markets, and the recent histories of futures prices. For about 65% of the markets studied, the model consisting of futures prices, a market’s own history, and the history of nearby markets forecasts better than a model only incorporating futures prices and the market’s own history. That is, nearby markets have predictive content. But the magnitude varies with the forecast horizon. For short-run forecasts, the forecast accuracy improvement from including nearby markets is modest. As the forecast horizon increases, however, including nearby prices tends to significantly improve forecasts. We also examine the role played by physical market density in determining the value of incorporating nearby prices into a forecast model.

The effect of the European Markets in Financial Instruments Directive on affiliated analysts’ earnings forecast optimism

We investigate the effects of the European Markets in Financial Instruments Directive (MiFID) on optimism in financial analysts’ earnings forecasts for Euro Area firms. We find that before MiFID came into force affiliated analysts – that is, analysts with closer business ties to the firms they follow – issued more optimistic longer-term earnings forecasts than their more independent peers. At the same time their short-run forecasts were significantly less optimistic which is consistent with the notion of downward management of their earnings forecasts to avoid negative earnings surprises. Since the adoption of MiFID, these differences in short-term and longer-term forecasts by affiliated and non-affiliated analysts have been eliminated indicating that with respect to affiliated financial analysts’ earnings estimates MiFID has been successful in mitigating conflicts of interest.

Short-Run Forecasting of Argentine Gross Domestic Product Growth

We propose a small-scale dynamic factor model for monitoring Argentine gross domestic product (GDP) in real time using economic data at mixed frequencies (monthly and quarterly), which are published with different time lags. Our model not only produces a coincident index of the Argentine business cycle in striking accordance with professional consensus and the history of the Argentine business cycle, but also generates accurate short-run forecasts of the highly volatile Argentine GDP growth. By using a pseudo real-time empirical evaluation, we show that our model produces reliable backcasts, nowcasts, and forecasts well before the official data are released.

The Term Structure of Exchange Rate Predictability: Commonality, Scapegoat, and Disageement

In this paper we study the exchange rate predictability across a range of investment horizons by return decomposition into forward premium component and carry trade risk premium component, for which we propose a term structure model to capture exchange rate dynamics with a broad set of predictors meanwhile handle both parameter and model uncertainties. We demonstrate the time-varying term-structural and model disagreement effects of exchange rate determinants as well as the projections of predictive information over the term structure. We also utilize the time-variation in the probability weighting from dynamic model averaging to identify the scapegoat drivers of customer order flows, which are also informative about the term structure of carry trade risk premia. Our findings reveal that heterogeneous agents learn to forecast exchange rates and switch trading rules over time, resulting in the dynamic country-specific and global exposures of exchange rates to short-run non-fundamental risk and long-run business cycle risk. Hedging pressure and liquidity are identified to contain predictive information that is common to a range of forecasting horizons. Policy-related predictors are important for short-run forecasts up to 3 months while crash risk indicators matter for long-run forecasts from 9 months to 12 months. We further comprehensively evaluate both statistical and economic significance of the model allowing for a full spectrum of currency investment management, and find that the model generates substantial performance fees of 6.5% per annum.

Wage Net Discount Rates: 1981–2012

Abstract The study explores time series properties of three wage net discount rate series derived using interest rates based on (alternatively) 1-year, 6-month and 3-month Treasury securities coupled with wage growth rates, initially for the period from 1981:01 to 2012:06, then subsequently through 2012:12. Stationarity tests are run on the full series and various sub-series to identify any portion of the series on which reliable forecasting can be based. Initially no support is found for the total offset hypothesis based on the full-time series (but support is subsequently found for total offset when exploring various data sub-series). Positive findings include that the three trended wage net growth rate series for the entire period under study are stationary, implying that reliable short-term forecasting of wage net discount rates is possible based on each of the trended series. Short-run forecasts based on the trended series are presented for 2012:07–2012:12 and compared to actual data in the period. Finally, the three trended wage net discount rate series are re-examined for 1981:01–2012:12, with short-term forecasting equations presented. Various sub-series of WNDRs are then explored in hopes of finding one or more that may be stationary about a constant term. Additional testing identifies three sub-series all ending 2012:12 with varying start dates that have desirable stationarity properties. The sub-series starting 2007:11 is highly stationary, but peculiar, with an associated constant WNDR that is negative and statistically different from zero; and the two sub-series beginning 1990:12 and 1994:05 have stationary attributes, yet possess constant terms that are slightly positive but not statistically different from zero, thus providing modest support for the total offset method.

Errors in Short Run Forecasts Next-day Volatility of Equity Risk Premium in the UK and U.S. Market: Empirical Research before and after the Global Financial Crisis

The current article has focused on the comparison of the equity risk premiums’ development in the two largest equity markets in the world, the U.K. and U.S. markets. The investigation has been made through estimating short run forecasts and calculating their errors. Therefore the aim of the study is to estimate errors in short run forecasts next-day volatility of the equity risk premium in the UK and U.S. markets. As the estimation method it used GARCH (1,2). It is obtained daily data for the period from 1999 to March 2014. The results have clearly proved that errors of forecasts are still at a higher level nowadays, than before the global financial crisis. Finally, it created a motivation for a future research in that area due to differences between types of financial systems.

The Accuracy Assessment of Macroeconomic Forecasts based on Econometric Models for Romania

The forecasts accuracy evaluation became a constant preoccupation of specialists in forecasting, because of the failure of predictions that caused the actual economic crisis. The objective of this research is to model and predict some economic variables corresponding too few macroeconomic blocks for Romanian economy. The forecast method is represented by econometric models. Moreover, the accuracy of these predictions is assessed, VARMA models generating more accurate short-run forecasts for inflation, real GDP and interest rate in Romania (horizon: 2012-2013) compared to VAR and AR models. The econometric models proposed for unemployment rate, exchange rate and rate of monetary supply determined better forecasts than random walk.

Predicting Hotel Demand Using Destination Marketing Organization’s Web Traffic Data

This study uses the web traffic volume data of a destination marketing organization (DMO) to predict hotel demand for the destination. The results show a significant improvement in the error reduction of ARMAX models, compared with their ARMA counterparts, for short-run forecasts of room nights sold by incorporating web traffic data as an explanatory variable.These empirical results demonstrate the significant value of website traffic data in predicting demand for hotel rooms at a destination, and potentially even local businesses’ future revenue and performance. The implications for future research on using big data for forecasting hotel demand is also discussed.

Short Run and Alternative Macroeconomic Forecasts for Romania and Strategies to Improve their Accuracy

For the same macroeconomic variables more predictions can be made, using dif- ferent forecasting forecasting. Th e most important step is the choice of the prediction with the highest degree of accuracy, this being used in establishing the governmental policies or the monetary policy by the central bank. We made short run forecasts (January 2012-March 2012) for variables as infl ation rate, unemployment rate and interest rate for Romania using techniques like: econometric modeling, exponential smoothing technique and moving average method. In order to improve the forecasts accuracy, we used two empirical strategies: making combined prognosis and building the forecasts based on historical accuracy indicators. Th e predictions based on expo- nential smoothing technique have the highest degree of acuracy, being superior to those got applying the strategies of improving the accuracy.

Predicting Macroeconomic Indicators in the Czech Republic Using Econometric Models and Exponential Smoothing Techniques

Abstract Econometric modeling and exponential smoothing techniques are two quantitative forecasting methods with good results in practice, but the objective of the research was to find out which of the two techniques are better for short run predictions. Therefore, for inflation, unemployment and interest rate in the Czech Republic various accuracy indicators were calculated for the predictions based on these methods. Short run forecasts on a horizon of 3 months were made for December 2011-February 2012, the econometric models being updated. For the Czech Republic, the exponential smoothing techniques provided more accurate forecasts than the econometric models (VAR(2) models, ARMA procedure and models with lagged variables). One explication for the better performance of smoothing techniques would be that in the chosen countries the short run predictions were more influenced by the recent evolution of the indicators.