检索结果-内蒙古大学图书馆

Risk inflation of sequential tests controlled by alpha investing

JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION 2015年第18期85卷 3613-3627页

作者： Foster, Dean P. Stine, Robert A. Univ Penn Wharton Sch Dept Stat Philadelphia PA 19104 USA

Streaming feature selection is a greedy approach to variable selection that evaluates potential explanatory variables sequentially. It selects significant features as soon as they are discovered rather than testing them all and picking the best one. Because it is so greedy, streaming selection can rapidly explore large collections of features. If significance is defined by an alpha investing protocol, then the rate of false discoveries will be controlled. The focus of attention in variable selection, however, should be on fit rather than hypothesis testing. Little is known, however, about the risk of estimators produced by streaming selection and how the configuration of these estimators influences the risk. To meet these needs, we provide a computational framework based on stochastic dynamic programming that allows fast calculation of the minimax risk of a sequential estimator relative to an alternative. The alternative can be data driven or derived from an oracle. This framework allows us to compute and contrast the risk inflation of sequential estimators derived from various alpha investing rules. We find that a universal investing rule performs well over a variety of models and that estimators allowed to have larger than conventional rates of false discoveries produce generally smaller risk.

关键词： stochastic dynamic programming testimator variable selection

来源：评论

学校读者我要写书评

暂无评论

The economic and environmental value of genetic improvements in fattening pigs: An integrated dynamic model approach

引用

JOURNAL OF ANIMAL SCIENCE 2015年第8期93卷 4161-4171页

作者： Niemi, J. K. Sevon-Aimonen, M. -L. Stygar, A. H. Partanen, K. Nat Resources Inst Finland Luke Econ & Soc FI-60320 Seinajoki Finland Nat Resources Inst Finland Luke Green Technol FI-31600 Jokioinen Finland MTT Agrifood Res Finland Econ Res FI-00790 Helsinki Finland MTT Agrifood Res Finland Anim Prod Res FI-31600 Jokioinen Finland

The selection of animals for improved performance affects the profitability of pig fattening and has environmental consequences. The goal of this paper was to examine how changes in genetic and market parameters impact the biophysical (feeding patterns, timing of slaughter, nitrogen excretion) and economic (return per pig space unit) results describing pig fattening in a Finnish farm. The analysis can be viewed as focusing on terminal line breeding goals. An integrated model using recursive stochastic dynamic programming and a biological pig growth model was used to estimate biophysical results and economic values. Combining these models allowed us to provide more accurate estimates for the value of genetic improvement and, thus, provide better feedback to animal breeding programs than the traditional approach, which is based on fixed management patterns. Besides the benchmark scenario, the results were simulated for 5 other scenarios. In each scenario, genotype was improved regarding daily growth potential, carcass lean meat content, or the parameters of the Gompertz growth curve (maturing rate [phi(i)], adult weight of protein [alpha(p)], and adult weight of lipid mass [alpha(L)]). The change in each parameter was equal to approximately 1 SD genetic improvement (ceteris paribus). Increasing phi(i), alpha(p), daily growth potential, or carcass lean meat content increased the return on pig space unit by (sic)12.60, (sic)7.60, (sic)4.10, or (sic)2.90 per year, respectively, whereas an increase in aL decreased the return by (sic)3.10. The genetic improvement in aL and fi resulted in the highest decrease in nitrogen excretion calculated in total or per kilogram of carcass gain but only under the optimal feeding pattern. Simulated changes in the Gompertz growth function parameters imply greater changes in ADG and lean meat content than changes in scenarios focusing on improving ADG and lean meat content directly. The economic value of genetic improvements as well as the

关键词： Gompertz growth model nitrogen excretion pig breeding stochastic dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Response-guided dosing for rheumatoid arthritis

引用

IIE Transactions on Healthcare Systems Engineering 2016年第1期6卷 1-21页

作者： Kotas, Jakob Ghate, Archis Department of Applied Mathematics University of Washington Seattle WA United States Departments of Industrial and Systems Engineering and Applied Mathematics University of Washington Seattle WA United States

Rheumatoid arthritis (RA) is an auto-immune disease with an unknown cause. Many patients receiving traditional methotrexate treatment continue to exhibit joint damage and are then treated with biologics. Biologic treatment is difficult owing to the uncertainty in dose-response, high cost, side effects, and intravenous administration. Recent clinical trials have therefore attempted response-guided dosing (RGD), where the hope is to adapt biologic doses over the treatment course based on each patient’s observed evolution of the 28-joint disease activity score (DAS28). We provide a stochastic dynamic programming (DP) framework to facilitate RGD. We present a concrete formulation where the DAS28 response is modeled using a stochastic Michaelis-Menten formula. The goal is to balance the DAS28 attained at the end of the course with the weighted total dose administered. We perform numerical experiments using data from the OPTION trial and observe that the optimal dosing policy gives higher doses in worse DAS28 scores. We present sensitivity analyses to provide further insights into this monotone dosing policy. This basic formulation is extended to a general stochastic DP for RGD. This is also applicable to other diseases and conditions such as hepatitis C, hyperlipidemia, hypertension, and AIDS. The DP allows for an arbitrary dose-response function, and balances the disutility of doses with the disutility of the disease condition reached. We prove that, when the decision-maker is risk-averse and the dose-response is supermodular and convex, there exists an optimal policy that gives higher doses in worse disease conditions. We provide several examples where these conditions are met. © 2016, © “IIE"”.

关键词： policy monotonicity stochastic dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Developing an integrated revenue management and customer relationship management approach in the hotel industry

引用

JOURNAL OF REVENUE AND PRICING MANAGEMENT 2015年第2期14卷 97-119页

作者： Vaeztehrani, Amirhossein Modarres, Mohammad Aref, Samin Sharif Univ Technol Dept Ind Engn Azadi AvePOB 11365-11155 Tehran Iran Univ Auckland Dept Comp Sci Auckland New Zealand

Revenue management (RM) and customer relationship management (CRM) are the standard strategies of many hotels to increase their profitability. Although the objectives and time horizons of RM and CRM are different, they can be considered as complimentary business strategies. However, the integration has received little attention both practically and theoretically. In this study, we develop an approach to jointly make the capacity allocation and overbooking decisions considering CRM strategies over a hotel network. Hotel customers are divided based on their lifetime value into two major groups of occasional and loyal customers. Price discounts and room availability guarantee (RAG) are offered to loyal customers, who are the hotel's essential source of profit. The main problem is tackled by a stochastic dynamic programming model whose expected value of objective function is approximated by two deterministic linear programming-based algorithms. The computational results indicate that the loyalty programs may lead to decrease in short-term net revenue. However, another analysis is required to decide upon cost-effectiveness of loyalty programs in an extended planning horizon. On the basis of an estimated discount-RAG response function, the cost-effectiveness of different loyalty programs is compared, which shows potential increase in hotel expected net revenue up to 3.5 per cent. The analytical long-term evaluation of loyalty programs introduced is capable of determining the most appropriate loyalty program factors. Moreover, it suggests discount-RAG response function and the level of tightness as sensitive parameters.

关键词： network revenue management customer relationship management hotel industry loyalty programs overbooking stochastic dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Playing the lottery or dressing up? A model of firm-level heterogeneity and the decision to export

引用

QUARTERLY REVIEW OF ECONOMICS AND FINANCE 2015年 58卷 1-17页

作者： Naude, Wim Gries, Thomas Bilkic, Natasa Maastricht Univ Sch Business & Econ Maastricht Sch Management Maastricht Netherlands Inst Study Labor IZA Bonn Germany Univ Paderborn Dept Econ Paderborn Germany Univ Paderborn Ctr Int Econ Paderborn Germany

In models of firm heterogeneity whether firms export or not depends on their productivity. These models assume that firms enter a market only to find their productivity levels revealed to them as in a lottery. However, if productivity is not determined as in a lottery, why do some firms export early and some late? In this paper we propose a model of firm heterogeneity to address this question. In our model exporting is an investment decision with a real option value. Our model illustrates that whether not a firm exports is a matter of timing. Some firms may always find it more worthwhile to postpone exporting, depending on the nature of the product, the target market, and firm-level characteristics. For instance, our model shows that firms evaluating exporting to a volatile, or two foreign market, will need more time to dress up (prepare) for this. We derive implications for policies to support exporting. (C) 2015 The Board of Trustees of the University of Illinois. Published by Elsevier B.V. All rights reserved.

关键词： International entrepreneurship Firm-level heterogeneity Start-ups Real options stochastic dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Why individualized contact policies are critical in the mass affluent market

引用

ACADEMIA-REVISTA LATINOAMERICANA DE ADMINISTRACION 2015年第2期28卷 251-272页

作者： Bitran, Gabriel Mondschein, Susana MIT Sloan Sch Business Cambridge MA 02139 USA Univ Adolfo Ibanez Fac Ingn & Ciencias Santiago Chile

Purpose - The purpose of this paper is to study the optimal contact policies for customers that belong to the mass affluent market. Design/methodology/approach - The authors formulate a stochastic dynamic programming model to determine the optimal frequency of contacts in order to maximize the expected return of the company. Findings - The authors show that personalized marketing strategies provide a competitive advantage to companies that contact their customers directly through, for example, phone calls or meetings. The authors show that a threshold policy is only optimal for customers with increasing sensitivity to contact. In all other cases, optimal policies might have a less intuitive structure. The authors also study the importance of the size of the customer database and determine the optimal maximum recency when maintenance costs are present. Practical implications - Contact policies should be tailored for each company/industry individually, due to their sensitivity to customers' purchasing behavior.

关键词： Marketing and advertising stochastic dynamic programming

来源：评论

学校读者我要写书评

暂无评论

A model based on stochastic dynamic programming for determining China's optimal strategic petroleum reserve policy

引用

ENERGY POLICY 2009年第11期37卷 4397-4406页

作者： Zhang, Xiao-Bing Fan, Ying Wei, Yi-Ming Chinese Acad Sci Ctr Energy & Environm Policy Res Inst Policy & Management Beijing 100080 Peoples R China

China's Strategic Petroleum Reserve (SPR) is currently being prepared. But how large the optimal stockpile size for China should be, what the best acquisition strategies are, how to release the reserve if a disruption occurs, and other related issues still need to be studied in detail. In this paper, we develop a stochastic dynamic programming model based on a total potential cost function of establishing SPRs to evaluate the optimal SPR policy for China. Using this model, empirical results are presented for the optimal size of China's SPR and the best acquisition and drawdown strategies for a few specific cases. The results show that with comprehensive consideration, the optimal SPR size for China is around 320 million barrels. This size is equivalent to about 90 days of net oil import amount in 2006 and should be reached in the year 2017, three years earlier than the national goal, which implies that the need for China to fill the SPR is probably more pressing;the best stockpile release action in a disruption is related to the disruption levels and expected continuation probabilities. The information provided by the results will be useful for decision makers. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： stochastic dynamic programming Strategic petroleum reserve Optimization

来源：评论

学校读者我要写书评

暂无评论

Approximate stochastic dynamic programming for sensor scheduling to track multiple targets

引用

DIGITAL SIGNAL PROCESSING 2009年第6期19卷 978-989页

作者： Li, Y. Krakow, L. W. Chong, E. K. P. Groom, K. N. Colorado State Univ Dept Elect & Comp Engn Ft Collins CO 80523 USA Colorado State Univ Dept Math Ft Collins CO 80523 USA Sandia Natl Labs Albuquerque NM 87185 USA

The problem of sensor scheduling is to select the number and combination of sensors to activate over time. The goal is usually to trade off tracking performance and sensor usage. We formulate a version of this problem involving multiple targets as a partially observable Markov decision process, and use this formulation to develop a nonmyopic sensor-scheduling scheme. Our scheme integrates sequential multisensor joint probabilistic data association and particle filtering for belief-state estimation, and use a simulation-based Q-value approximation method called completely observable rollout for decision making. We illustrate the effectiveness of our approach by an example with multiple sensors activated simultaneously to track multiple targets. We also explore the trade-off between tracking error and sensor cost using our nonmyopic scheme. (C) 2007 Elsevier Inc. All rights reserved.

关键词： Sensor scheduling stochastic dynamic programming Multiple target tracking Partially observable Markov decision process Particle filtering

来源：评论

学校读者我要写书评

暂无评论

Modeling a dynamic Portfolio for Pension Plans in Emerging Markets With Myopic and Nonmyopic Behavior

引用

EMERGING MARKETS FINANCE AND TRADE 2015年第Sup6期51卷 S14-S26页

作者： Pimentel, Livia F. Santiago, Leonardo P. Univ Fed Minas Gerais Dept Prod Engn BR-31270901 Belo Horizonte MG Brazil Copenhagen Business Sch Dept Operat Management Frederiksberg Denmark

We introduce a dynamic formulation for the problem of portfolio selection of pension funds in the absence of a risk-free asset. In emerging markets, a risk-free asset might be unavailable, and the approaches commonly used may no longer be suitable. We use a parametric approach to combine dynamic programming and Monte Carlo simulation to gain additional flexibility. This approach is general in the sense that optimal asset allocation is tractable for all HARA utility functions in the absence of a risk-free asset. The traditional case composed of several risky assets and one risk-free asset is compared to a case in which the risk-free asset is unavailable.

关键词： Monte Carlo simulation parametric methods pension plan portfolio selection stochastic dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Comparison of Policies Derived from stochastic dynamic programming and Genetic Algorithm Models

引用

WATER RESOURCES MANAGEMENT 2009年第8期23卷 1563-1580页

作者： Jothiprakash, V. Shanthi, Ganesan Indian Inst Technol Dept Civil Engn Mumbai 400076 Maharashtra India JJ Coll Engn & Technol Dept Civil Engn Tiruchirappalli 620009 Tamil Nadu India

A comprehensive Genetic Algorithm (GA) model has been developed and applied to derive optimal operational strategies of a multi-purpose reservoir, namely Perunchani Reservoir, in Kodaiyar Basin in Tamil Nadu, India. Most of the water resources problem involves uncertainty, in order to see that the GA model takes care of uncertainty in the input variable, the result of the GA model is compared with the performance of a detailed stochastic dynamic programming (SDP) model. The SDP models are well established and proved that it takes care of uncertainty in-terms of either implicit or explicit approach. In the present study, the objective function of the models is set to minimize the annual sum of squared deviation from desired target release and desired storage volume. In the SDP model the optimal policies are derived by varying the state variables from 3 to 9 representative class intervals, and then the cases are evaluated for their performance using a simulation model for longer length of inflow data, generated using a Thomas-Fiering model. From the performance of the SDP model policies, it is found that the system encountered irrigation deficit, whereas GA model satisfied the demand to a greater extent. The sensitivity analysis of the GA model in selecting optimal population, optimal crossover probability and the optimal number of generations showed the values of 150, 0.76 and 175 respectively. On comparing the performance of SDP model policy with GA model, it is found that GA model has resulted in a lesser irrigation deficit. Thus based on the present case study, it may be concluded that the GA model performs better than the SDP model.

关键词： stochastic dynamic programming Genetic algorithm Multi-purpose reservoir operation Simulation Synthetic stream flow generation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：