Rubing Chen, J. Yuan, Qiulan Zhao, C. T. Ng, T. Edwin Cheng
In this article, we study bicriterion Pareto‐scheduling on a single machine of equal‐length jobs, where one of the criteria is the total weighted late work. Motivated by two Pareto‐scheduling open problems where one criterion is the total (weighted) late work and the other criterion is the weighted number of tardy jobs, we show that 12 constrained scheduling problems unaddressed in the literature are binary NP$$ NP $$ ‐hard, implying that the Pareto‐scheduling versions of these problems are also binary NP$$ NP $$ ‐hard. Moreover, we introduce the concept of dummy due dates (DDD) for equal‐length jobs to be scheduled in equal‐length intervals. Intriguingly, we find that a DDD‐based technique outperforms the existing solution methods and improves the known time complexities of the related problems. In addition, we extend our research to the two‐agent scheduling model under the assumption of equal‐length or partially equal‐length jobs by including the total weighted late work as the criterion of one agent. For these problems, our results also improve the known time complexity results.
{"title":"Bicriterion Pareto‐scheduling of equal‐length jobs on a single machine related to the total weighted late work","authors":"Rubing Chen, J. Yuan, Qiulan Zhao, C. T. Ng, T. Edwin Cheng","doi":"10.1002/nav.22103","DOIUrl":"https://doi.org/10.1002/nav.22103","url":null,"abstract":"In this article, we study bicriterion Pareto‐scheduling on a single machine of equal‐length jobs, where one of the criteria is the total weighted late work. Motivated by two Pareto‐scheduling open problems where one criterion is the total (weighted) late work and the other criterion is the weighted number of tardy jobs, we show that 12 constrained scheduling problems unaddressed in the literature are binary NP$$ NP $$ ‐hard, implying that the Pareto‐scheduling versions of these problems are also binary NP$$ NP $$ ‐hard. Moreover, we introduce the concept of dummy due dates (DDD) for equal‐length jobs to be scheduled in equal‐length intervals. Intriguingly, we find that a DDD‐based technique outperforms the existing solution methods and improves the known time complexities of the related problems. In addition, we extend our research to the two‐agent scheduling model under the assumption of equal‐length or partially equal‐length jobs by including the total weighted late work as the criterion of one agent. For these problems, our results also improve the known time complexity results.","PeriodicalId":19120,"journal":{"name":"Naval Research Logistics (NRL)","volume":"19 1","pages":"537 - 557"},"PeriodicalIF":0.0,"publicationDate":"2023-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90961914","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The pursuit of lower costs and the volatility of spot prices force shipping companies to sign fuel supply contracts with suppliers in advance. Meanwhile, suppliers that take on price risks typically seek further information on spot market prices. Furthermore, they need to consider whether to share the information with shipping companies as such information can affect shipping companies' decision on speed and, hence, their fuel consumption and shipper business. To study the refueling and information issues of the shipping supply chain, we describe a game between a shipping company and a supplier on the basis of a fuel supply contract. Results show that compared with the case without information sharing, the case with information sharing with a possibly lower spot price can bring higher profits for the shipping company and supplier. At this point, the shipping company will increase its navigation speed and benefit from the resulting increase in shipper business. Meanwhile, the supplier can benefit from the shipping company's increased fuel consumption. The supplier decides to share information with the shipping company before receiving signals only when the prediction accuracy is high, indicating that the supplier's prediction motivation is to sway the shipping company's risk assessment. Restricted by prediction costs, the supplier will not improve the prediction accuracy indefinitely, but such improvement can always benefit the shipping company. Hence, information prediction can be a win‐win strategy for the shipping company and supplier.
{"title":"Bunkering and information decisions in the sea cargo service industry based on uncertain spot price","authors":"Zhuzhu Song, Man Xu, Pingping Chen","doi":"10.1002/nav.22102","DOIUrl":"https://doi.org/10.1002/nav.22102","url":null,"abstract":"The pursuit of lower costs and the volatility of spot prices force shipping companies to sign fuel supply contracts with suppliers in advance. Meanwhile, suppliers that take on price risks typically seek further information on spot market prices. Furthermore, they need to consider whether to share the information with shipping companies as such information can affect shipping companies' decision on speed and, hence, their fuel consumption and shipper business. To study the refueling and information issues of the shipping supply chain, we describe a game between a shipping company and a supplier on the basis of a fuel supply contract. Results show that compared with the case without information sharing, the case with information sharing with a possibly lower spot price can bring higher profits for the shipping company and supplier. At this point, the shipping company will increase its navigation speed and benefit from the resulting increase in shipper business. Meanwhile, the supplier can benefit from the shipping company's increased fuel consumption. The supplier decides to share information with the shipping company before receiving signals only when the prediction accuracy is high, indicating that the supplier's prediction motivation is to sway the shipping company's risk assessment. Restricted by prediction costs, the supplier will not improve the prediction accuracy indefinitely, but such improvement can always benefit the shipping company. Hence, information prediction can be a win‐win strategy for the shipping company and supplier.","PeriodicalId":19120,"journal":{"name":"Naval Research Logistics (NRL)","volume":"10 1 1","pages":"522 - 536"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83591775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the online retailing, consumers are commonly uncertain about the product's quality and fitness. To resolve these uncertainties, many pure e‐tailers adopt various omnichannel strategies to provide tactile product information for consumers. We build a model to investigate a pure e‐tailer's decision on whether to adopt an omnichannel strategy. Our result indicates that when the cost for each physical store is sufficiently low, the e‐tailer always adopts the omnichannel strategy regardless of the product quality. Moreover, the low‐quality e‐tailer's willingness to adopt the omnichannel strategy is nonmonotonic with the fitness probability when the travel cost factor is high. In contrast, if the cost for each physical store is moderate, the e‐tailer adopts the omnichannel strategy if and only if the product quality is above a threshold. The quality threshold may increase with the fitness probability. Higher fitness probability means a lower return rate and fewer benefits brought by the omnichannel strategy. Thus, the threshold of the quality is increased to guarantee a sufficiently large price increase when choosing the omnichannel strategy. Furthermore, when the cost for each physical store is high, the e‐tailer with a high‐quality product would abandon the omnichannel strategy if the fitness probability is moderate. Finally, we consider the scenarios in which the e‐tailer can endogenously determine the number of physical stores or provide a partial refund policy.
{"title":"Information disclosure, consumer returns, and operational costs in omnichannel retailing","authors":"Jie Liu, Hui Xiong","doi":"10.1002/nav.22101","DOIUrl":"https://doi.org/10.1002/nav.22101","url":null,"abstract":"In the online retailing, consumers are commonly uncertain about the product's quality and fitness. To resolve these uncertainties, many pure e‐tailers adopt various omnichannel strategies to provide tactile product information for consumers. We build a model to investigate a pure e‐tailer's decision on whether to adopt an omnichannel strategy. Our result indicates that when the cost for each physical store is sufficiently low, the e‐tailer always adopts the omnichannel strategy regardless of the product quality. Moreover, the low‐quality e‐tailer's willingness to adopt the omnichannel strategy is nonmonotonic with the fitness probability when the travel cost factor is high. In contrast, if the cost for each physical store is moderate, the e‐tailer adopts the omnichannel strategy if and only if the product quality is above a threshold. The quality threshold may increase with the fitness probability. Higher fitness probability means a lower return rate and fewer benefits brought by the omnichannel strategy. Thus, the threshold of the quality is increased to guarantee a sufficiently large price increase when choosing the omnichannel strategy. Furthermore, when the cost for each physical store is high, the e‐tailer with a high‐quality product would abandon the omnichannel strategy if the fitness probability is moderate. Finally, we consider the scenarios in which the e‐tailer can endogenously determine the number of physical stores or provide a partial refund policy.","PeriodicalId":19120,"journal":{"name":"Naval Research Logistics (NRL)","volume":"1 1","pages":"376 - 391"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79560069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jianjun Xu, Matthew F. Keblis, Youyi Feng, S. Zhou
We study the problem of optimally managing an inventory system with backorders over a finite time horizon where the objective is minimization of expected total discounted costs. The system consists of two locations each stocking the same product. At the beginning of each time period decisions are made about replenishment at each location and about any quantity to transship between the locations before demand is observed. Leveraging the L♮‐convexity of the problem's cost function; we characterize the optimal replenishment and transshipment policy for this system. More specifically, we show the optimal policy can be described using switching curves monotone in the system state. We also discuss two extensions. For a lost‐sales model, we establish L♮‐convexity and apply it to characterize the optimal policy, simplifying the analysis found in previous work. In the other extension, we investigate the optimal policy for a partial transshipment problem where only one location orders from the external supply source and then transships to the other location.
研究了在有限时间范围内以期望总贴现成本最小化为目标的库存系统的最优管理问题。该系统由两个地点组成，每个地点储存相同的产品。在每个时间段的开始，在观察到需求之前，决定在每个地点补充和在地点之间转运的数量。利用问题成本函数的L -凸性;我们描述了该系统的最佳补货和转运政策。更具体地说，我们证明了最优策略可以用系统状态下的单调开关曲线来描述。我们还讨论了两个扩展。对于损失销售模型，我们建立了L - vii -凸性并将其应用于表征最优策略，简化了先前工作中发现的分析。在另一个扩展中，我们研究了部分转运问题的最优策略，其中只有一个位置从外部供应源订购，然后转运到另一个位置。
{"title":"Optimal replenishment and transshipment management with two locations","authors":"Jianjun Xu, Matthew F. Keblis, Youyi Feng, S. Zhou","doi":"10.1002/nav.22098","DOIUrl":"https://doi.org/10.1002/nav.22098","url":null,"abstract":"We study the problem of optimally managing an inventory system with backorders over a finite time horizon where the objective is minimization of expected total discounted costs. The system consists of two locations each stocking the same product. At the beginning of each time period decisions are made about replenishment at each location and about any quantity to transship between the locations before demand is observed. Leveraging the L♮‐convexity of the problem's cost function; we characterize the optimal replenishment and transshipment policy for this system. More specifically, we show the optimal policy can be described using switching curves monotone in the system state. We also discuss two extensions. For a lost‐sales model, we establish L♮‐convexity and apply it to characterize the optimal policy, simplifying the analysis found in previous work. In the other extension, we investigate the optimal policy for a partial transshipment problem where only one location orders from the external supply source and then transships to the other location.","PeriodicalId":19120,"journal":{"name":"Naval Research Logistics (NRL)","volume":"4 1","pages":"305 - 319"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73175658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We develop a Stackelberg differential game to analyze the economic effects of the reduction plan through two policy instruments, tradable permits and taxes on emissions. Emissions are a by‐product of firm output. The authority acts as a Stackelberg leader, able to set the optimal instrument's level in the light of a finite‐horizon environmental target. We show that the optimal solution of the game is dynamically consistent. Moreover, optimal environmental policies substantially impact the level and composition of economic activity. The differentiation between “clean” and “dirty” firms allows us to assess distributional effects and how environmental technology may influence the game's outcome. Results are shown to be robust under different parameterizations.
{"title":"Environmental policies in a Stackelberg differential game","authors":"R. Cerqueti, L. Correani, F. Di Dio","doi":"10.1002/nav.22099","DOIUrl":"https://doi.org/10.1002/nav.22099","url":null,"abstract":"We develop a Stackelberg differential game to analyze the economic effects of the reduction plan through two policy instruments, tradable permits and taxes on emissions. Emissions are a by‐product of firm output. The authority acts as a Stackelberg leader, able to set the optimal instrument's level in the light of a finite‐horizon environmental target. We show that the optimal solution of the game is dynamically consistent. Moreover, optimal environmental policies substantially impact the level and composition of economic activity. The differentiation between “clean” and “dirty” firms allows us to assess distributional effects and how environmental technology may influence the game's outcome. Results are shown to be robust under different parameterizations.","PeriodicalId":19120,"journal":{"name":"Naval Research Logistics (NRL)","volume":"67 1","pages":"358 - 375"},"PeriodicalIF":0.0,"publicationDate":"2023-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75834493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article examines the information acquisition strategy of a dual‐channel supply chain, in which a manufacturer sells a product both through a retailer and through its own direct channel. Either the manufacturer or the retailer can acquire demand information from a third‐party marketing research company. The manufacturer first decides whether or not to acquire such information, and then the retailer decides whether or not to acquire information. This setup implies a signaling game (either the manufacturer or the retailer may have private demand information) with an endogenous information structure. We identify conditions under which neither of the firms will acquire demand information, even when the cost of implementation is negligible. We also show that information acquisition can have a negative impact on the retailer, the supply chain, customers, and society. The manufacturer who acquires information always prefers to share information with the retailer, which benefits the retailer. The retailer who acquires information, however, may not want to share information with the manufacturer. The managerial insight of our paper is that firms that have more accurate demand data must develop strategies for the appropriate use of that information, both in their own planning and within the context of their dual‐channel supply chain.
{"title":"Demand information acquisition strategy in a dual channel supply chain","authors":"Jing Chen, H. Pun, Qiaoxi Zhang","doi":"10.1002/nav.22100","DOIUrl":"https://doi.org/10.1002/nav.22100","url":null,"abstract":"This article examines the information acquisition strategy of a dual‐channel supply chain, in which a manufacturer sells a product both through a retailer and through its own direct channel. Either the manufacturer or the retailer can acquire demand information from a third‐party marketing research company. The manufacturer first decides whether or not to acquire such information, and then the retailer decides whether or not to acquire information. This setup implies a signaling game (either the manufacturer or the retailer may have private demand information) with an endogenous information structure. We identify conditions under which neither of the firms will acquire demand information, even when the cost of implementation is negligible. We also show that information acquisition can have a negative impact on the retailer, the supply chain, customers, and society. The manufacturer who acquires information always prefers to share information with the retailer, which benefits the retailer. The retailer who acquires information, however, may not want to share information with the manufacturer. The managerial insight of our paper is that firms that have more accurate demand data must develop strategies for the appropriate use of that information, both in their own planning and within the context of their dual‐channel supply chain.","PeriodicalId":19120,"journal":{"name":"Naval Research Logistics (NRL)","volume":"140 1","pages":"340 - 357"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78582519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Most engineering systems operate under stochastic dynamic environments. The variability and stochasticity of environmental conditions have a non‐negligible impact on the failure behavior of engineering systems. This article develops a reliability modeling and assessment framework for systems operating under a Markovian dynamic environment. The stochastic dynamic environment is characterized by a continuous‐time Markov chain. Using the cumulative exposure principle, the stochastic time scale, resulting from the cumulative effect of the Markovian dynamic environment, is computed via a Markov reward model. Based on the above settings, the system reliability model under the Markovian dynamic environment is developed. The maximum likelihood estimates and confidence intervals for the model parameters, including the transition rate matrix of the Markov chain, the reward rates of the Markov reward model, and the parameters of the baseline lifetime distribution, are obtained by utilizing the collected environment and lifetime data. The system reliability is then assessed with the estimated parameters. The effectiveness of the proposed framework are validated using simulation and through an application to a long‐term storage system. The results show that the unknown reliability model parameters can be accurately estimated, and the proposed model with the consideration of the cumulative effect of the Markovian dynamic environment can provide a more accurate reliability estimate than that without such a consideration.
{"title":"A stochastic time scale based framework for system reliability under a Markovian dynamic environment","authors":"Tao Jiang, Yu Liu, Z. Ye","doi":"10.1002/nav.22096","DOIUrl":"https://doi.org/10.1002/nav.22096","url":null,"abstract":"Most engineering systems operate under stochastic dynamic environments. The variability and stochasticity of environmental conditions have a non‐negligible impact on the failure behavior of engineering systems. This article develops a reliability modeling and assessment framework for systems operating under a Markovian dynamic environment. The stochastic dynamic environment is characterized by a continuous‐time Markov chain. Using the cumulative exposure principle, the stochastic time scale, resulting from the cumulative effect of the Markovian dynamic environment, is computed via a Markov reward model. Based on the above settings, the system reliability model under the Markovian dynamic environment is developed. The maximum likelihood estimates and confidence intervals for the model parameters, including the transition rate matrix of the Markov chain, the reward rates of the Markov reward model, and the parameters of the baseline lifetime distribution, are obtained by utilizing the collected environment and lifetime data. The system reliability is then assessed with the estimated parameters. The effectiveness of the proposed framework are validated using simulation and through an application to a long‐term storage system. The results show that the unknown reliability model parameters can be accurately estimated, and the proposed model with the consideration of the cumulative effect of the Markovian dynamic environment can provide a more accurate reliability estimate than that without such a consideration.","PeriodicalId":19120,"journal":{"name":"Naval Research Logistics (NRL)","volume":"116 1","pages":"320 - 339"},"PeriodicalIF":0.0,"publicationDate":"2023-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88082658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hui Xiao, Yao Zhang, Gang Kou, Si Zhang, Juergen Branke
In many real‐world applications, designs can only be evaluated pairwise, relative to each other. Nevertheless, in the simulation literature, almost all the ranking and selection procedures are developed based on the individual performances of each design. This research considers the statistical ranking and selection problem when the design performance can only be simulated pairwise. We formulate this new problem using the optimal computing budget allocation approach and derive the asymptotic optimality condition based on some approximations. The numerical study indicates that our approach can reduce the number of simulations required to confidently identify the best design.
{"title":"Ranking and selection for pairwise comparison","authors":"Hui Xiao, Yao Zhang, Gang Kou, Si Zhang, Juergen Branke","doi":"10.1002/nav.22093","DOIUrl":"https://doi.org/10.1002/nav.22093","url":null,"abstract":"In many real‐world applications, designs can only be evaluated pairwise, relative to each other. Nevertheless, in the simulation literature, almost all the ranking and selection procedures are developed based on the individual performances of each design. This research considers the statistical ranking and selection problem when the design performance can only be simulated pairwise. We formulate this new problem using the optimal computing budget allocation approach and derive the asymptotic optimality condition based on some approximations. The numerical study indicates that our approach can reduce the number of simulations required to confidently identify the best design.","PeriodicalId":19120,"journal":{"name":"Naval Research Logistics (NRL)","volume":"12 1","pages":"284 - 302"},"PeriodicalIF":0.0,"publicationDate":"2023-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80126612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We study a set of scheduling problems in a distributed flow‐shop scheduling system consisting of several flow‐shop production systems (factories) working in parallel. Our objective is to assign the jobs to the factories, and to devise a job schedule for each of the factories such that the weighted number of jobs completed in just‐in‐time mode is maximized. We classify computational complexity of the problems, including the special cases of unit weights and job‐ or machine‐independent processing times.
{"title":"Maximizing the weighted number of just‐in‐time jobs in a distributed flow‐shop scheduling system","authors":"D. Shabtay","doi":"10.1002/nav.22097","DOIUrl":"https://doi.org/10.1002/nav.22097","url":null,"abstract":"We study a set of scheduling problems in a distributed flow‐shop scheduling system consisting of several flow‐shop production systems (factories) working in parallel. Our objective is to assign the jobs to the factories, and to devise a job schedule for each of the factories such that the weighted number of jobs completed in just‐in‐time mode is maximized. We classify computational complexity of the problems, including the special cases of unit weights and job‐ or machine‐independent processing times.","PeriodicalId":19120,"journal":{"name":"Naval Research Logistics (NRL)","volume":"39 1","pages":"274 - 283"},"PeriodicalIF":0.0,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72696326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Although Phase I analysis of multivariate processes has been extensively discussed, the discussion on techniques for Phase I monitoring of high‐dimensional processes is still limited. In high‐dimensional applications, it is common to observe that a large number of components but only a limited number of them change at the same time. The shifted components are often sparse and unknown a priori in practice. Motivated by this, this article studies Phase I monitoring of high‐dimensional process mean vectors under an unknown sparsity level of shifts. The basic idea of the proposed monitoring scheme is to first employ the false discovery rate procedure to estimate the sparsity level of mean shifts, and then to monitor the mean changes based on the maximum of the directional likelihood ratio statistics over all the possible shift directions. The comparison results based on extensive simulations favor the proposed monitoring scheme. A real example is presented to illustrate the implementation of the new monitoring scheme.
{"title":"A phase I change‐point method for high‐dimensional process with sparse mean shifts","authors":"Wenpo Huang, L. Shu, Yanting Li, Luyao Wang","doi":"10.1002/nav.22095","DOIUrl":"https://doi.org/10.1002/nav.22095","url":null,"abstract":"Although Phase I analysis of multivariate processes has been extensively discussed, the discussion on techniques for Phase I monitoring of high‐dimensional processes is still limited. In high‐dimensional applications, it is common to observe that a large number of components but only a limited number of them change at the same time. The shifted components are often sparse and unknown a priori in practice. Motivated by this, this article studies Phase I monitoring of high‐dimensional process mean vectors under an unknown sparsity level of shifts. The basic idea of the proposed monitoring scheme is to first employ the false discovery rate procedure to estimate the sparsity level of mean shifts, and then to monitor the mean changes based on the maximum of the directional likelihood ratio statistics over all the possible shift directions. The comparison results based on extensive simulations favor the proposed monitoring scheme. A real example is presented to illustrate the implementation of the new monitoring scheme.","PeriodicalId":19120,"journal":{"name":"Naval Research Logistics (NRL)","volume":"127 1","pages":"261 - 273"},"PeriodicalIF":0.0,"publicationDate":"2023-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75673015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：