A new energy model to capture the behavior of energy price processes

Owing to the vague fluctuation of energy prices from time to time, a new energy model, which considers both the mean-reverting behavior and the long memory property, is proposed in this paper. Since the problem of estimating parameters, in discrete time for this model, plays a central role in forecast inference, the problem of estimating the unknown parameters has been dealt with for the fractional Ornstein–Uhlenbeck process observed discretely. The asymptotic properties of these estimates are also provided. The numerical simulation results confirm the theoretical analysis and show that our method is effective. To show how to apply our approach in realistic contexts, an empirical study of energy in China, namely Daqing crude oil, is presented. The empirical results seem reasonable when compared to the real data.     

A hybrid parallel genetic algorithm for yard crane scheduling

This paper aims at postulating a novel strategy in terms of yard crane scheduling. In this study, a dynamic scheduling model using objective programming for yard cranes is initially developed based on rolling-horizon approach. To resolve the NP-complete problem regarding the yard crane scheduling, a hybrid algorithm, which employs heuristic rules and parallel genetic algorithm (PGA), is then employed. Then a simulation model is developed for evaluating this approach. Finally, numerical experiments on a specific container terminal yard are used for system illustration. Computational results suggest that the proposed method is able to solve the problem efficiently.     

Fast delta computations in the swap-rate market model

We develop an efficient algorithm to implement the adjoint method that computes sensitivities of an interest rate derivative to different underlying rates in the co-terminal swap-rate market model. The order of computation per step of the new method is shown to be proportional to the number of rates times the number of factors, which is the same as the order in the LIBOR market model.     

Coverage area expansion, customer switching, and household profiles in the Japanese broadband access market

This paper examines the diffusion process of Internet broadband access in Japan by modeling the household choice of access modes. Estimates reveal that the characteristics of users, rather than those of the access modes, play a significant role in demand substitution across the modes. Simulation exercises indicate that had optic fibers (fiber-to-the-home; FTTH) been made available to the whole country in 2005, only 10% of households would have switched to that mode. This result implies that once chosen, the household choice of access mode persists, and that indirect network effects are an important element in decisions to adopt the new technology of broadband. Finally, policy implications are discussed.     

Small-sample Properties of Panel Spatial Autoregressive Models: Comparison of the Bayesian and Maximum Likelihood Methods

Abstract

This article considers autoregressive (SAR) models. We method to estimate the parameters of likelihood (ML) method. Our Bayesian by the Monte Carlo studies. We found the efficient as the ML estimators.     

基于PCAIDS模型的单边价格效应模拟——以国际铁矿石巨头力拓与必和必拓拟议的兼并为例

本文基于爱泼斯坦和鲁宾菲尔德提出的PCAIDS 模型,模拟了国际铁矿石生产和出口巨头力拓与必和必拓之间2007 年10 月提出的兼并的单边效应.研究发现,该兼并对世界铁矿石市场价格将产生重要影响,特别是兼并后形成的新企业将大幅度提高其产品的价格.兼并也会引起印度、巴西和南非铁矿石提价,尽管幅度要比"两拓"要小一些.中国的进口铁矿石主要来自于两拓、巴西、印度和南非,因此,如果"两拓"兼并将极大地提高我国进口铁矿石的成本.     

How effective are heuristic solutions for electricity planning in developing countries

Heuristic algorithms have been widely used to provide computationally feasible means of exploring the cost effective balance between grid versus off grid sources for universal electrification in developing countries. By definition in such algorithms however, global optimality is not guaranteed. We present a computationally intensive but globally optimal mixed integer non-linear programming (MINLP) model for electricity planning and use it in a Monte Carlo simulation procedure to test the relative performance of a widely used heuristic algorithm due to [28]. We show that the overall difference in cost is typically small suggesting that the heuristic algorithm is generally cost effective in many situations. However we find that the relative performance of the heuristic algorithm deteriorates with increasing degree of spatial dispersion of unelectrified settlements, as well as increasing spatial remoteness of the settlements from the grid network, suggesting that the effectiveness of the heuristic algorithm is context specific. Further, we find that allocation of off grid sources in the heuristic algorithm solution is often significantly greater than in the MINLP model suggesting that heuristic methods can overstate the role of off-grid solutions in certain situations.     

Estimation employing a priori information within mass appraisal and hedonic pricing models

Both statistical appraisal and hedonic pricing models decompose houses into a set of individual characteristics. Regression estimates yield the contribution of each characteristic to total value. Unfortunately, straightforward application of OLS may produce untenable results such as implausible coefficient magnitudes or incorrect signs. Often the suspected cause is multicollinearity. This article examines the effect on estimation efficiency of differing levels of multicollinearity, R², and a priori information in the form of sub-market cost data, by comparing inequality restricted least squares (IRLS) with OLS in a series of Monte Carlo experiments. The IRLS procedure investigated here hybridizes the statistical market approach implemented by OLS, and the more traditional cost approach. The experiments show dramatic gains in estimation efficiency from exploiting a priori information through IRLS.     

Bias in estimates of discrimination and default in mortgage lending: The effects of simultaneity and self-selection

The common practices of estimating single-equation models of mortgage rejection to test for discrimination in mortgage markets or single-equation ex ante mortgage default equations to validate underwriting criteria produce biased and inconsistent parameter estimates. This is due to problems of simultaneous equations bias which arise because, in a world of imperfect information, mortgage terms are not exogenous to the rejection or default decision. In addition, mortgage default estimates are also subject to selection bias. Monte Carlo experiments are used to study the nature and extent of likely bias in single-equation estimation results. We find that rejection equation estimates indicate discrimination when none exists and that estimated coefficients of mortgage terms, such as the loan-to-value ratio, are also subject to significant bias in both rejection and default equations.     

MC's for MCMC'ists

We develop a minimum amount of theory of Markov chains at as low a level of abstraction as possible in order to prove two fundamental probability laws for standard Markov chain Monte Carlo algorithms:
1. The law of large numbers explains why the algorithm works: it states that the empirical means calculated from the samples converge towards their "true" expected values, viz. expectations with respect to the invariant distribution of the associated Markov chain (=the target distribution of the simulation).
2. The central limit theorem expresses the deviations of the empirical means from their expected values in terms of asymptotically normally distributed random variables. We also present a formula and an estimator for the associated variance.