			Home About us Contact

Time Framework (time + framework)

Distribution by Scientific Domains

Business, Economics, Finance and Accounting	60%

Selected Abstracts

Sensitivity analysis of neural network parameters to improve the performance of electricity price forecasting

INTERNATIONAL JOURNAL OF ENERGY RESEARCH, Issue 1 2009
Paras Mandal
Abstract This paper presents a sensitivity analysis of neural network (NN) parameters to improve the performance of electricity price forecasting. The presented work is an extended version of previous works done by authors to integrate NN and similar days (SD) method for predicting electricity prices. Focus here is on sensitivity analysis of NN parameters while keeping the parameters same for SD to forecast day-ahead electricity prices in the PJM market. Sensitivity analysis of NN parameters include back-propagation learning set (BP-set), learning rate (,), momentum (,) and NN learning days (dNN). The SD parameters, i.e. time framework of SD (d=45 days) and number of selected similar price days (N=5) are kept constant for all the simulated cases. Forecasting performance is carried out by choosing two different days from each season of the year 2006 and for which, the NN parameters for the base case are considered as BP-set=500, ,=0.8, ,=0.1 and dNN=45 days. Sensitivity analysis has been carried out by changing the value of BP-set (500, 1000, 1500); , (0.6, 0.8, 1.0, 1.2), , (0.1, 0.2, 0.3) and dNN (15, 30, 45 and 60 days). The most favorable value of BP-set is first found out from the sensitivity analysis followed by that of , and ,, and based on which the best value of dNN is determined. Sensitivity analysis results demonstrate that the best value of mean absolute percentage error (MAPE) is obtained when BP-set=500, ,=0.8, ,=0.1 and dNN=60 days for winter season. For spring, summer and autumn, these values are 500, 0.6, 0.1 and 45 days, respectively. MAPE, forecast mean square error and mean absolute error of reasonably small value are obtained for the PJM data, which has correlation coefficient of determination (R2) of 0.7758 between load and electricity price. Numerical results show that forecasts generated by developed NN model based on the most favorable case are accurate and efficient. Copyright © 2008 John Wiley & Sons, Ltd. [source]

Interactions between dispersal, competition, and landscape heterogeneity

OIKOS, Issue 7 2007
Ace North
It is widely acknowledged that space has an important role in population regulation, yet more specific knowledge into how the relevant factors interact attains little consensus. We address this issue via a stochastic, individual based model of population dynamics, in a continuous space continuous time framework. We represent habitat quality as a continuously varying surface over the two-dimensional landscape, and assume that the quality affects either fecundity (rate of propagule production) or probability of propagule establishment. We control the properties of the landscape by two parameters, which we call the patch size (the characteristic length scale in quality variation), and the level of heterogeneity (the characteristic quality difference between poor quality and high quality areas). In addition to such exogenous variability, we also account for endogenous factors causing spatial variation by assuming localised dispersal and competition. We find that heterogeneity has a general positive effect on population density, and hence it is beneficial to improve best quality habitat at the expense of worst quality habitat. With regards to patch size, we find an intermediate optimum, due to a conflict between minimising the loss of propagules to low quality regions and maximising the benefits of heterogeneity. We address the consequences of regional stochasticity by allowing the environmental conditions change in time. The cost of having to continuously track where the favourable conditions have moved to ultimately reduces population size. [source]

An Intertemporal Capital Asset Pricing Model with Owner-Occupied Housing

REAL ESTATE ECONOMICS, Issue 3 2010
Yongqiang Chu
This article studies portfolio choice and asset pricing in the presence of owner-occupied housing in a continuous time framework. The unique feature of the model is that housing is a consumption good as well as a risky asset. Under general conditions, that is, when the utility function is not Cobb,Douglas and the covariance matrix is not block-diagonal, the model shows that the market portfolio is not mean-variance efficient, and the traditional capital asset pricing model fails. Nonetheless, a conditional linear factor pricing model holds with housing return and market portfolio return as two risk factors. The model also predicts that the nondurable consumption-to-housing ratio (ch) can forecast financial asset returns. The two factor pricing model conditioning on,ch,yields a good cross-sectional fit for Fama,French 25 portfolios. [source]

Nonlinear asymmetric models of the short-term interest rate

THE JOURNAL OF FUTURES MARKETS, Issue 9 2006
K. Ozgur DemirtasArticle first published online: 18 JUL 200
This study introduces a generalized discrete time framework to evaluate the empirical performance of a wide variety of well-known models in capturing the dynamic behavior of short-term interest rates. A new class of models that displays nonlinearity and asymmetry in the drift, and incorporates the level effect and stochastic volatility in the diffusion function is introduced in discrete time and tested against the popular diffusion, GARCH, and level-GARCH models. Based on the statistical test results, the existing models are strongly rejected in favor of the newly proposed models because of the nonlinear asymmetric drift of the short rate, and the presence of nonlinearity, GARCH, and level effects in its volatility. The empirical results indicate that the nonlinear asymmetric models are better than the existing models in forecasting the future level and volatility of interest rate changes. © 2006 Wiley Periodicals, Inc. Jrl Fut Mark 26:869,894, 2006 [source]

Minimum capital requirement calculations for UK futures

THE JOURNAL OF FUTURES MARKETS, Issue 2 2004
John Cotter
Key to the imposition of appropriate minimum capital requirements on a daily basis is accurate volatility estimation. Here, measures are presented based on discrete estimation of aggregated high-frequency UK futures realizations underpinned by a continuous time framework. Squared and absolute returns are incorporated into the measurement process so as to rely on the quadratic variation of a diffusion process and be robust in the presence of fat tails. The realized volatility estimates incorporate the long memory property. The dynamics of the volatility variable are adequately captured. Resulting rescaled returns are applied to minimum capital requirement calculations. © 2004 Wiley Periodicals, Inc. Jrl Fut Mark 24:193,220, 2004 [source]