A novel auto-regressive fractionally integrated moving average–least-squares support vector machine model for electricity spot prices prediction

In the framework of competitive electricity market, prices forecasting has become a real challenge for all market participants. However, forecasting is a rather complex task since electricity prices involve many features comparably with those in financial markets. Electricity markets are more unpredictable than other commodities referred to as extreme volatile. Therefore, the choice of the forecasting model has become even more important. In this paper, a new hybrid model is proposed. This model exploits the feature and strength of the auto-regressive fractionally integrated moving average model as well as least-squares support vector machine model. The expected prediction combination takes advantage of each model's strength or unique capability. The proposed model is examined by using data from the Nordpool electricity market. Empirical results showed that the proposed method has the best prediction accuracy compared to other methods.     

Information-based thinning of point processes and its application to shock models

Thinning of point processes is a useful operation that is implemented in various stochastic models. When the initial point process is the nonhomogeneous Poisson process (NHPP), the thinned processes are also nonhomogeneous Poisson processes independent of each other. The crucial assumption in deriving this result is that the corresponding classification of events is independent of all other events, including the history of the process. However, in practice, this classification is often dependent on the history. In our paper, we define and describe the thinned processes for the history-dependent case using different levels of available information. We also discuss the applications of the obtained general results to the corresponding shocks models.     

大城市外来人口分布态势的分析与启示——以上海为例

随着都市区这类新型城市化空间形态的发展,对大城市外来人口问题的研究不应仅仅停留在总量变动的探讨和空间无差别化的政策设计。近年人口普查数据显示,上海外来人口分布正扩散到全市的各个区域,呈"面状侵入"的发展态势,其中远郊区外来人口增长最为突出。外来人口与上海市户籍人口居住空间的交叉、重叠、渗透将普遍出现在全市各个环带。外来人口的性别、年龄、受教育程度等结构特征在都市区内部均呈现比较明显的环带差异。经济发展、产业结构调整、大型居住区规划建设等对外来人口分布变动产生较大影响。二元城市管理模式下,外来人口公共管理与服务的压力存在显著的空间非均衡性,为此应设计一套具有空间响应性的公共管理与服务机制。上海各类属性外来人口的空间分布也呈现明显的环带差异特征,这些都是将来精细化政策设计的现实依据。     

What Makes Koreans Happy?: Exploration on the Structure of Happy Life among Korean Adults

The current study explored the perceptions of Korean people about what can make them happy and constructed a comprehensive measurement of happiness of Korean. A total of 61 Korean adults participated in Focused Group Interview (FGI), where they were asked three questions (e.g., What makes you happy? What could make you happier than now? In general, who is a happy person?). Participants’ responses were reviewed by the present investigators independently and 152 statements of happy life with 18 categories were derived from content-analysis. The list of 152 statements of happy life was administered to 517 Korean adults to assess the importance of each item for Koreans’ happy life through the objective rating scale (6-point Likert scale). Confirmatory factor analysis showed that most factors were unidimensional. The items with low reliability were deleted and some new items were added, resulting in the experimental form of the Happy Life Inventory with 156 items and 18 categories including a new category of religion. The preliminary form of the Happy Life Inventory and the Psychological Well-being scale were administered to a nationwide sample of 1503 Korean adults in order to assess their happiness through 6-point Likert scale. The responses from 877 participants were submitted to exploratory factor analysis. The items with low factor loadings were excluded and 98 items with 16 factors were included in the final version of the Happy Life Inventory. Confirmatory factor analysis of the responses from 611 subjects confirmed that the 16 factor model was appropriate and most categories had one underlying dimension with moderate to high reliabilities. Correlations between the Happy Life Inventory and the psychological well-being scale supported construct validity of the Happy Life Inventory. Suggestions for further research were discussed.     

An integrated modelling approach for raw material management in a steel mill

An integrated modelling approach combining optimisation models with simulation is proposed for coordinated raw material management at steel works throughout the whole supply chain management process. The integrated model is composed of three components: ship scheduling, yard operation simulation and material blending models. The ship scheduling model determines which brands, how much and when they should be arrived, and the problem is modelled as mixed integer linear programming. The simulation model is used to simulate the whole processes from ships’ arrivals to the retrieval of the materials through the berthing and unloading the raw materials. Finally, the raw material blending model is developed for determining the brand and quantity of raw materials to be used. The proposed integrated modelling approach for raw material management has been successfully implemented and applied at steelwork to provide shipping schedules and predict future inventory levels at stock yards. By coordinating all the activities throughout the entire raw material supply chain management process, this article proposes an integrated approach to the problem and suggests a guideline by the appropriate simplification. The quantitative nature of the optimisation model and simulation facilitates an assessment of the risk factors in the supply chain, leading to an evaluation of a wide variety of scenarios and the development of multiple contingency plans. Further research is expected to supplement the ship scheduling models with heuristics for the idiosyncratic constraints of maritime transportation.     

Corporate Environmental Behaviors in Voluntary Programs: Does Timing Matter?*

Objective. Why do some firms participate in voluntary programs earlier than others? What conditions dictate whether firms participate in voluntary programs earlier rather than later? Current research on voluntary programs has not considered discrete processes in which corporate actors could have different motives and objectives in different time dimensions, that is, early versus late. Methods. We adopt a diffusion theory to disaggregate corporate voluntary participation behavior in the Environmental Protection Agency (EPA) sponsored Green Lights (GL) voluntary program. We focus on the GL participants during two periods—the early joiners in 1993–1994, and the late joiners in 1995–1996. Results. At the early diffusion stage, firms are more likely driven by the market motive that garners a “green” reputation, an important strategic asset to promote market competitiveness; at the late diffusion stage, firms are more driven by the institutional motive to improve their relationships with regulatory agencies and subsequently relieve regulatory pressures from them. Conclusion. We find that firms have different motives for GL participation at different diffusion stages. We suggest that policymakers who want to induce firms to join voluntary programs should pay more attention to program designs and implementation schemes that accommodate different corporate interests and objectives in different time orders of firms' participations in voluntary programs.     

性别角色差异在话语间接程度中的体现

仅仅用"直接的"和"间接的"两个形容词来区分男女的话语风格特点过于绝对和片面,不能解释生理性别与性别角色不相符的现象.话语间接程度是一个连续统一体,最低间接程度和最高间接程度分列两极.话语分析中的直接与间接程度应从相对而非绝对的角度去分析判断.     

Variables acceptance reliability sampling plan for repairable items

Traditionally, acceptance reliability sampling plans have been developed for non-repairable items. However, the functions required for items become more and more complex and, accordingly, the items are composed of several components and tend to be repairable. In this paper, we consider variables acceptance reliability sampling plan for repairable items. We develop a variables acceptance sampling plan based on the failure and repair data observed during the testing period. It is shown that the developed sampling plan improves the reliability characteristic of the population and that the lifetimes of items before and after the reliability sampling test are stochastically ordered.     

Cluster analysis using different correlation coefficients

Partitioning objects into closely related groups that have different states allows to understand the underlying structure in the data set treated. Different kinds of similarity measure with clustering algorithms are commonly used to find an optimal clustering or closely akin to original clustering. Using shrinkage-based and rank-based correlation coefficients, which are known to be robust, the recovery level of six chosen clustering algorithms is evaluated using Rand’s C values. The recovery levels using weighted likelihood estimate of correlation coefficient are obtained and compared to the results from using those correlation coefficients in applying agglomerative clustering algorithms. This work was supported by RIC(R) grants from Traditional and Bio-Medical Research Center, Daejeon University (RRC04713, 2005) by ITEP in Republic of Korea.