Forecasting system energy demand

This paper presents the results of the Electric Power Research Institute Short Range Forecasting Project (EPRI-SRF) performed by the Load Forecasts Department, Economics and Forecasts Division of Ontario Hydro, Ontario, Canada. In this study a variety of short-range forecasting techniques are applied to Ontario Hydro monthly data on total system energy demand. These techniques are available in a software package (FORECAST MASTER) developed for EPRI by two consultants—Scientific Systems, Inc. (SSI) and Quantitativ Economic Research, Inc. (QUERI). The methods used for this study were the univariate Box-Jenkins method, the multivariate state-space method, Bayesian vector autoregression and autoregress ve econometric regression. A comparison of the models developed show that the econometric models perform the best overall. The state-space models are more suitable for very short-term (one-step ahead) forecasts. Although the Box-Jenkins method has the advantage of simplicity in terms of estimation and data requirement, its performance was not as good as that of the others. Bayesian vector autoregresson results indicate that this program needs some modification for monthly data.     

Is it possible to find an econometric law that works well in explanation and prediction? The case of Australian money demand

Pratt and Schlaifer's (1984, 1988) research employed in efforts to produce laws in economics are considered and their use in predicting future data is described. Data for Australia are used to illustrate the approaches.     

Forecasting demand in international markets: The case of correlated time series

In this paper a data analysis tool for analyzing highly correlated time series data is suggested. The main objective is to unify multiple time series into a single series and then apply a univariate method for the purpose of prediction. This method is essentially efficient for analyzing multiple time series with sparse data. Several time series data of relative demand for black and white television receivers in various countries are analyzed and quite accurate predictions are obtained.     

Simultaneous equation estimates of electricity demand for the rural south: Revenue projection when prices are administered

Presented are estimates of demand equations and producer revenue projections for rural farm electricity consumers in the USA. Statistical tests include a Box-Cox comparison of functional form, a Koyck-distributed lag, and a contrast of average versus marginal prices. Producer revenue projections take account of the estimated demand equation and non-continuous rate schedules for each of the electricity distributors. Multiple price equilibria result from differences in administered price schedules between sellers. The ‘effective’ price elasticity based upon forecasts which take account of the market circumstances is lower than the simple demand point elasticity but higher than found in some previous studies.     

Forecasting Government Bond Yields with Neural Networks Considering Cointegration

This paper discusses techniques that might be helpful in predicting interest rates and tries to evaluate a new hybrid forecasting approach. Results of examining government bond yields in Germany and France reported in this study indicate that a hybrid forecasting approach which combines techniques of cointegration analysis with neural network (NN) forecasting models can produce superior results to the use of NN forecasting models alone. The findings documented in this paper could be a consequence of the fact that examining differenced data under certain conditions will lead to a loss of information and that the inclusion of the error correction term from the cointegration model can help to cope with this problem. The paper also discusses some possibly interesting directions for further research. Copyright © 2015 John Wiley & Sons, Ltd.     

Forecasting contemporaneous aggregates and the combination of forecasts: The case of the U.K. monetary aggregates

A number of papers in recent years have investigated the problems of forecasting contemporaneously aggregated time series and of combining alternative forecasts of a time series. This paper considers the integration of both approaches within the example of assessing the forecasting performance of models for two of the U.K. monetary aggregates, £M3 and MO. It is found that forecasts from a time series model for aggregate £M3 are superior to aggregated forecasts from individual models fitted to either the components or counterparts of £M3 and that an even better forecast is obtained by forming a linear combination of the three alternatives. For MO, however, aggregated forecasts from its components prove superior to either the forecast from the aggregate itself or from a linear combination of the two.     

Forecasting vehicle holdings and usage with a disaggregate choice model

A case study in which a three-stage choice model of Canadian household vehicle holdings and usage is used to generate short-run forecasts of changes in household vehicle usage and gasoline consumption in response to a range of energy-related policies. The objectives of this case study are to (1) demonstrate the application of disaggregate choice modelling methods to the generation of policy-relevant forecasts of travel behaviour; (2) draw implications from this forecasting exercise concerning the likely impacts of various energy-related policies; and (3) assess some of the strengths and weaknesses of the current state-of-the-art of forecasting with disaggregate choice models, using the presented study as a case in point.     

Forecasting with growth curves: the effect of error structure

"The main theme of this paper is an investigation into the importance of error structure as a determinant of the forecasting accuracy of the logistic model. The relationship between the variance of the disturbance term and forecasting accuracy is examined empirically. A general local logistic model is developed as a vehicle to be used in this investigation. Some brief comments are made on the assumptions about error structure, implicit or explicit, in the literature." The results suggest that "the variance of the disturbance term, when using the logistic to forecast human populations, is proportional to at least the square of population size."     

Forecasting Austrian IPOs: An application of linear and neural network error-correction models

In this paper we apply cointegration and Granger-causality analyses to construct linear and neural network error-correction models for an Austrian Initial Public Offerings IndeX (IPOX_ATX). We use the significant relationship between the IPOX_ATX and the Austrian Stock Market Index ATX to forecast the IPOX_ATX. For prediction purposes we apply augmented feedforward neural networks whose architecture is determined by Sequential Network Construction with the Schwartz Information Criterion as an estimator for the prediction risk. Trading based on the forecasts yields results superior to Buy and Hold or Moving Average trading strategies in terms of mean-variance considerations.     

Forecasting the federal budget with time-series models

The stochastic properties of conventionally denned federal expenditures and revenues are examined, and cointegration is found. Alternative time-series models-univariate ARIMA models, vector autoregressions in levels and differences, and an error correction model-are specified and estimated using quarterly data from 1955:1 through 1979:4. Updated forecasts for up to three years beyond the sample period are evaluated against actual expenditures, revenues and the deficit. The vector autoregression in levels shows evidence of nonstationarity, which leads to strong biases in the forecasts. The remaining models produce forecasts that are satisfactory by the mean squared error criterion, and the magnitudes of biases at the longer horizons are significantly smaller than those of the official forecasts.     

Forecasting ski demand: comparing learning curve and varying parameter coefficient approaches

Demand for skiing expanded rapidly in the 1980s, fell quite dramatically at the start of the 1990s as the economy declined but has not subsequently recovered. Two possible explanations are explored. The first is based on perceiving skiing as a new product to most consumers, which reached maximum growth in 1989. Current levels now largely represent ‘repeat buyers’. The alternative approach sees the growth as the result of economic factors, particularly credit conditions. The importance of these factors was not, however, constant, and grew with the changes in the financial system. Thus the recovery had a muted effect. These two approaches are modelled, estimated and the results compared by both residual and ex post forecasting analysis. The paper concludes that the varying coefficient econometric model probably produces the most reliable forecasts. Copyright © 1999 John Wiley & Sons, Ltd.     

Forecasting future canadian residential heating demand: An illustration of forecasting with aggregated and disaggregated data

This paper examines the sensitivity of forecasts to the level of aggregation of the data. A relative shares regression model and a multinominal logit model are tested with both aggregate and disaggregate survey data from 2109 respondents. The results indicate the appropriate model to use depends on whether the data are disaggregate or aggregate in form. Forecasts of solar heating of dwelling unit demand and market shares are also reported for Canada in terms of the solar price relative to the natural gas price and solar reliability relative to natural gas reliability.     

Forecasting inflation using economic indicators: the case of France

In order to provide short‐run forecasts of headline and core HICP inflation for France, we assess the forecasting performance of a large set of economic indicators, individually and jointly, as well as using dynamic factor models. We run out‐of‐sample forecasts implementing the Stock and Watson (1999) methodology. We find that, according to usual statistical criteria, the combination of several indicators—in particular those derived from surveys—provides better results than factor models, even after pre‐selection of the variables included in the panel. However, factors included in VAR models exhibit more stable forecasting performance over time. Results for the HICP excluding unprocessed food and energy are very encouraging. Moreover, we show that the aggregation of forecasts on subcomponents exhibits the best performance for projecting total inflation and that it is robust to data snooping. Copyright © 2007 John Wiley & Sons, Ltd.     

Energy demand forecasts with investment constraints

The energy sector in India claims 30% of the available investments. Moreover, oil import bills have the largest share among the total import bills. Thus, macro economic development and energy sector are highly interdependent. Where energy demand is forecasted without these linkages one cannot be sure if investments and imports required for energy sector will be available. The SImulation of MAcroeconomic scenarios (SIMA) model generates macroeconomically consistent energy scenarios from two interlinked submodels i.e. economic and energy submodels. The energy sector is a part of the non-agricultural sector but it is linked to both the agricultural and the non-agricultural sectors. These three sectors compete with each other for the available capital. In a two-step procedure, various energy economy relations are econometrically estimated and then these are solved simultaneously by feeding in the exogenous parameters (population, oil prices, etc.). The scenarios created correspond to 1991–2010. They are the Dynamics As Usual and the High Oil Price scenarios with capital required for phasing in the electricity sector. Energy-related emission levels for pollutants such as CO₂, NO_x and SO₂ emissions are also calculated for each scenario.     

Forecasting the Antwerp maritime steel traffic flow: A case study

This paper uses multivariate time series models to specify the maritime steel traffic flow in the port of Antwerp. The time series considered are the total outgoing and total incoming maritime steel traffic and the total steel production in the EEC. The obtained time series models provide useful insight into the general behaviour of the maritime steel traffic flow during the period 1971–82. In particular, they provide a quantitative interpretation of important changes which took place in the European steel industry during that period. The multivariate time series models produce forecasts which are a substantial improvement over those obtained by univariate time series models. This is especially the case for the series of total incoming maritime steel traffic in the port of Antwerp, when differencing and transformation of the original data are applied.     

Univariate Forecasting Comparisons: The Case of the Spanish Automobile Industry

This paper investigates the forecasting ability of unobserved component models, when compared with the standard ARIMA univariate approach. A forecasting exercise is carried out with each method, using monthly time series of automobile sales in Spain. The accuracy of the different methods is assessed by comparing several measures of forecasting performance based on the out-of-sample predictions for various horizons, as well as different assumptions on the models’ parameters. Overall there seems little to choose between the methods in forecasting performance terms but the recursive unobserved component models provide greater flexibility for adaptive applications. © 1997 by John Wiley & Sons, Ltd.     

Practitioners'Forum. Forecasting and Planning the Jeddah Air Traffic with a Mini Model

A simple model of particular socio-economic and technical environment proves useful in forecasting and planning. The specific application forecasts air traffic at King Abdulaziz International Airport (KAIA) in Jeddah, Saudi Arabia, through a number of explanatory variables The purpose of the model is to explain and forecast the change in growth rates of passenger flow through the airport. The dynamics of passenger flow are linked to the dynamics of the oil-based economy of Saudi Arabia and the global economic and business environment.     

Forecasting for business planning: A case study of IBM product sales

This is a case study of a closely managed product. Its purpose is to determine whether time-series methods can be appropriate for business planning. By appropriate, we mean two things: whether these methods can model and estimate the special events or features that are often present in sales data; and whether they can forecast accurately enough one, two and four quarters ahead to be useful for business planning. We use two time-series methods, Box-Jenkins modeling and Holt-Winters adaptive forecasting, to obtain forecasts of shipments of a closely managed product. We show how Box-Jenkins transfer-function models can account for the special events in the data. We develop criteria for choosing a final model which differ from the usual methods and are specifically directed towards maximizing the accuracy of next-quarter, next-half-year and next-full-year forecasts. We find that the best Box-Jenkins models give forecasts which are clearly better than those obtained from Holt-Winters forecast functions, and are also better than the judgmental forecasts of IBM's own planners. In conclusion, we judge that Box-Jenkins models can be appropriate for business planning, in particular for determining at the end of the year baseline business-as-usual annual and monthly forecasts for the next year, and in mid-year for resetting the remaining monthly forecasts.     

Assessing the Macroeconomic Forecasting Performance of Boosting: Evidence for the United States,the Euro Area and Germany

The use of large datasets for macroeconomic forecasting has received a great deal of interest recently. Boosting is one possible method of using high‐dimensional data for this purpose. It is a stage‐wise additive modelling procedure, which, in a linear specification, becomes a variable selection device that iteratively adds the predictors with the largest contribution to the fit. Using data for the United States, the euro area and Germany, we assess the performance of boosting when forecasting a wide range of macroeconomic variables. Moreover, we analyse to what extent its forecasting accuracy depends on the method used for determining its key regularization parameter: the number of iterations. We find that boosting mostly outperforms the autoregressive benchmark, and that K‐fold cross‐validation works much better as stopping criterion than the commonly used information criteria. Copyright © 2014 John Wiley & Sons, Ltd.     

Forecasting with an econometric model: The issue of judgemental adjustment

The paper outlines the current state of forecasting with an econometric model. After briefly distinguishing econometric techniques from other statistical approaches and arguing the advantages of this approach the paper concentrates on the issue of judgemental adjustments to models for forecasting purposes. Two types of adjustment are distinguished and the conditions under which each is justified are stated. Guidance in the use of adjustment is offered through a review of considerations in an actual forecasting situation.