Time Series Model Prediction Research Articles

Spatial and Temporal Characteristics of High-Temperature Heat Wave Disasters in Chongqing

In the background of global warming, heat wave disasters have become more frequent globally, and mountainous cities are more seriously affected by heat wave disasters due to the special features of topography and urban morphology. This paper analyzes the temporal and spatial distribution characteristics of heat wave disasters in Chongqing, a mountainous city. The results shows that heat wave disasters in Chongqing tend to increase overall and decrease locally before increasing. Significant growth in heat waves since 2010 and time series model prediction analysis shows that Chongqing will face more severe heat waves in the future. The spatial distribution of heat wave disasters varies significantly, high in the middle and low at the ends. There is a tendency for the center of heat wave disasters to shift from the south-central part of Chongqing to the northeast. In addition to the influence of atmospheric circulation and mountain topography, the causes are also positively related to urban development intensity and urbanization trends. It is necessary to develop specific control and management measures for heat waves depending on the characteristics of them. The take-home message of the study is the spatial and temporal trends of heat waves in Chongqing to provide a theoretical basis for high-temperature mitigation.

Model averaging prediction for time series models with a diverging number of parameters

An important problem with the model averaging approach is the choice of weights. In this paper, a generalized Mallows model averaging (GMMA) criterion for choosing weights is developed in the context of an infinite order autoregressive (AR(∞)) process. The GMMA method adapts to the circumstances in which the dimensions of candidate models can be large and increase with the sample size. The GMMA method is shown to be asymptotically optimal in the sense of achieving the lowest out-of-sample mean squared prediction error (MSPE) for both the independent-realization and the same-realization predictions, which, as a byproduct, solves a conjecture put forward by Hansen (2008) that the well-known Mallows model averaging criterion from Hansen (2007) is asymptotically optimal for predicting the future of a time series. The rate of the GMMA-based weight estimator tending to the optimal weight vector minimizing the independent-realization MSPE is derived as well. Both simulation experiment and real data analysis illustrate the merits of the GMMA method in the prediction of an AR(∞) process.

A note on simultaneous calibrated prediction intervals for time series

This paper deals with simultaneous prediction for time series models. In particular, it presents a simple procedure which gives well-calibrated simultaneous prediction intervals with coverage probability close to the target nominal value. Although the exact computation of the proposed intervals is usually not feasible, an approximation can be easily attained by means of a suitable bootstrap simulation procedure. This new predictive solution is much simpler to compute than those ones already proposed in the literature, based on asymptotic calculations. Applications of the bootstrap calibrated procedure to AR, MA and ARCH models are presented.

Resources and Future Availability of Agricultural Biomass for Energy Use in Beijing

The increasing importance of lignocellulosic biomass based energy production has led to an urgent need to conduct a reliable resource supply assessment. This study analyses and estimates the availability of agricultural residue biomass in Beijing, where biomass energy resources are relatively rich and is mainly distributed in the suburbs. The major types of crops considered across Beijing include food crops (e.g., maize, winter wheat, soybean, tubers and rice), cotton crops and oil-bearing crops (e.g., peanuts). The estimates of crop yields are based on historical data between 1996 and 2017 collected from the Beijing Municipal Bureau of Statistics. The theoretical and collectable amount of agricultural residues was calculated on the basis of the agricultural production for each crop, multiplied by specific parameters collected from the literature. The assessment of current and near future agricultural residues from crop harvesting and processing resources in Beijing was performed by employing three advanced modeling methods: the Time Series Analysis Autoregressive moving average (ARMA) model, Least Squares Linear Regression and Gray System Gray Model (GM) (1,1). The results show that the time series model prediction is suitable for short-term prediction evaluation; the least squares fitting result is more accurate but the factors affecting agricultural waste production need to be considered; the gray system prediction is suitable for trend prediction but the prediction accuracy is low.

Time series model prediction and trend variability of aerosol optical depth over coal mines in India

A study of the assessment and management of air quality was carried out at 11 coal mines in India. Long-term observations (about 13 years, March 2000-December 2012) and modeling of aerosol loading over coal mines in India are analyzed in the present study. In this respect, the Box-Jenkins popular autoregressive integrated moving average (ARIMA) model was applied to simulate the monthly mean Terra Moderate Resolution Imaging Spectroradiometer (MODIS) aerosol optical depth (AOD550 nm) over 11 sites in the coal mines region. The ARIMA model was found as the most suitable model with least normalized Bayesian information criterion (BIC) and root mean square error and high value of R (2). Estimation was done with the Ljung-Box test. Finally, a forecast for a 3-year period from January 2013 to December 2015 was calculated which showed that the model forecasted values are following the observed trend quite well over all mining areas in India. The average values of AOD for the next 3 years (2013-2015) at all sites are found to be 0.575 ± 0.13 (Raniganj), 0.452 ± 0.12 (Jharia), 0.339 ± 0.13 (Bokaro), 0.280 ± 0.09 (Bishrampur), 0.353 ± 0.13 (Korba), 0.308 ± 0.08 (Talcher), 0.370 ± 0.11 (Wardha), 0.35 ± 0.10 (Adilabad), 0.325 ± 0.09 (Warangal), 0.467 ± 0.09 (Godavari Valley), and 0.236 ± 0.07 (Cuddapah), respectively. In addition, long-term lowest monthly mean AOD550 values are observed over Bishrampur followed by Cuddapah, Talcher, Warangal, Adilabad, Korba, Wardha, Godavari Valley, Jharia, and Raniganj. Raniganj and Jharia exhibit the highest AOD values due to opencast mines and extensive mining activities as well as a large number of coal fires. Similarly, the highest AOD values are observed during the monsoon season among all four seasons over all the mining sites. Raniganj exhibits the highest AOD value at all seasons and at all sites. In contrast, the lowest seasonal AOD values are observed during the post-monsoon season over Raniganj, Talcher, Wardha, Adilabad, Warangal, and Godavari Valley. Similarly, over Jharia, Bokaro, Bishrampur, Korba, and Cuddapah, the lowest AOD values are found in the winter season. Increasing trends in AOD550 have been observed over Raniganj, Bokaro, Bishrampur, Korba, Talcher, and Wardha as well as over Adilabad and Godavari Valley, which is in agreement with previous works. Negative or decreasing AOD trend is found only over Jharia, Warangal, and Cuddapah without being statistically significant. Seasonal trends in AODs have also been studied in the present paper.

WITHDRAWN: Recurrent NARX time series model prediction: A feedforward and recurrent radial basis function network

This article has been withdrawn at the request of the author(s) and/or editor. The Publisher apologizes for any inconvenience this may cause. The full Elsevier Policy on Article Withdrawal can be found at http://www.elsevier.com/locate/withdrawalpolicy.

A simple procedure for computing improved prediction intervals for autoregressive models

Abstract. This article concerns the construction of prediction intervals for time series models. The estimative or plug-in solution is usually not entirely adequate, since the (conditional) coverage probability may differ substantially from the nominal value. Prediction intervals with improved (conditional) coverage probability can be defined by adjusting the estimative ones, using rather complicated asymptotic procedures or suitable simulation techniques. This article extends to Markov process models a recent result by Vidoni, which defines a relatively simple predictive distribution function, giving improved prediction limits as quantiles. This new solution is fruitfully considered in the challenging context of prediction for time-series models, with particular regard to AR and ARCH processes.

Optimal estimating function for estimation and prediction in semi-parametric models

In a seminal paper, Godambe [1985. The foundations of finite sample estimation in stochastic processes. Biometrika 72, 419–428.] introduced the ‘estimating function’ approach to estimation of parameters in semi-parametric models under a filtering associated with a martingale structure. Later, Godambe [1987. The foundations of finite sample estimation in stochastic processes II. Bernoulli, Vol. 2. V.N.V. Science Press, 49–54.] and Godambe and Thompson [1989. An extension of quasi-likelihood Estimation. J. Statist. Plann. Inference 22, 137–172.] replaced this filtering by a more flexible conditioning. Abraham et al. [1997. On the prediction for some nonlinear time-series models using estimating functions. In: Basawa, I.V., et al. (Eds.), IMS Selected Proceedings of the Symposium on Estimating Functions, Vol. 32. pp. 259–268.] and Thavaneswaran and Heyde [1999. Prediction via estimating functions. J. Statist. Plann. Inference 77, 89–101.] invoked the theory of estimating functions for one-step ahead prediction in time-series models. This paper addresses the problem of simultaneous estimation of parameters and multi-step ahead prediction of a vector of future random variables in semi-parametric models by extending the inimitable approach of Godambe (1985, 1987). The proposed technique is in conformity with the paradigm of the modern theory of estimating functions leading to finite sample optimality within a chosen class of estimating functions, which in turn are used to get the predictors. Particular applications of the technique give predictors that enjoy optimality properties with respect to other well-known criteria.

NARMAX time series model prediction: feedforward and recurrent fuzzy neural network approaches

The nonlinear autoregressive moving average with exogenous inputs (NARMAX) model provides a powerful representation for time series analysis, modeling and prediction due to its capability of accommodating the dynamic, complex and nonlinear nature of real-world time series prediction problems. This paper focuses on the modeling and prediction of NARMAX-model-based time series using the fuzzy neural network (FNN) methodology. Both feedforward and recurrent FNNs approaches are proposed. Furthermore, an efficient algorithm for model structure determination and parameter identification with the aim of producing improved predictive performance for NARMAX time-series models is developed. Experiments and comparative studies demonstrate that the proposed FNN approaches can effectively learn complex temporal sequences in an adaptive way and they outperform some well-known existing methods.

On robust local polynomial estimation with long-memory errors

Prediction in time series models with a trend requires reliable estimation of the trend function at the right end of the observed series. Local polynomial smoothing is a suitable tool because boundary corrections are included implicitly. However, outliers may lead to unreliable estimates, if least-squares regression is used. In this paper, local polynomial smoothing based on M-estimation is considered for the case where the error process exhibits long-range dependence. In contrast to the iid case, all M-estimators are asymptotically equivalent to the least-square solution, under the (ideal) Gaussian model. The potential usefulness of the proposal for forecasting is illustrated by practical and simulated examples. A simulation study shows that outliers have a major effect on nonrobust bandwidth selection, in particular due to the change of the dependence structure.

BANDWIDTH SELECTION IN KERNEL SMOOTHING OF TIME SERIES

Abstract. The kernel smoothing method has been considered as a useful tool for identification and prediction in time series models. In practice this method is to be tuned by a smoothing parameter. For selection of the smoothing parameter, Härdle and Vieu (Kernel regression smoothing of time series. J. Time Ser. Anal. 13(1992), 209–32) considered a cross‐validation rule and proved its asymptotic optimality. In this paper we strengthen their result for a wider use of the kernel smoothing of time series.

COMBINING A RADIAL BASIS NEURAL NETWORK WITH TIME SERIES ANALYSIS TECHNIQUES TO PREDICT MANUFACTURING PROCESS PARAMETERS

The accurate prediction of the values of critical quality parameters of a product during the production stage is a key factor in the success of a manufacturing operation. Neural network algorithms have been used to successfully predict process parameter values. However, techniques to further improve the predictive capability of neural network models are sought. Thus, an analysis was conducted to determine if the predictive capability of the network would he improved if the prediction from a time series model of a manufacturing process parameter were included in the training data set of a radial basis function neural network model. A manufacturing process data set was evaluated, and the use of the time series model prediction significantly improved the neural network's prediction of critical process parameters. Often in a manufacturing environment, the collection of adequate amounts of data for network training is difficult. This integrated technique offers potential for improving network performance witho...

Bayesian long-run prediction in time series models

This paper considers Bayesian long-run prediction in time series models. We allow time series to exhibit stationary or nonstationary behavior and show how differences between prior structures which have little effect on posterior inferences can have a large effect in a prediction exercise. In particular, the Jeffreys prior given in Phillips (1991) is seen to prevent the existence of one-period-ahead predictive moments. In a more general context, a Bayesian counterpart is provided to Sampson (1991) who takes parameter uncertainty into account in a classical framework. An empirical example illustrates our results.