Madhuri S. Mulekar Pengarang

Bayesian Pint and Interval Prediction of Ordered Observations in Future Censored Samples from Contagious Geometric Distribution Jafer R ahman D epartment of Mathematics and Statistics, Hazara University, Garden Campus, Mansehra, Pakistan SYNOPTIC ABSTRACT Th is article presents the study of prediction analys is on future or dered sample observations from a two - component contagious model o f geom tric distribution using a Bayesian approach . To be more specifc, a theoretical methodology is proposed to get approximate point and interval prediction of ordered statistics in t he future samples when these samples are censored by right type-I, right type-II, and left censoring techniques. Point predictors are developed using a symmetric and an asymmetric loss function . To show the usefulness of the derived mathematical results, the study applies them to real-world data and considers, for illustration, the computation of point prediction for quartiles and 95% prediction intervals for median and inter quartile range in the future censored samples KEY WO RDS AND PHR ASES Bayesian predic tion; geometric distribution; mix t ure m odel; l oss func tions; ordered obser vation; censoring schemes G e neralize d H ybrid Ce nsored Reliabilit y Acceptance S ampling Plans for the Weibull Distribution Tanmay S en,a Ritwik Bhattacharya ,b Yogesh Mani Tripathi,a and Biswabrata Pradhan c aDepartment of Mathematics, Indian Institute of Technology Patna, India; bCentro de Investigación en Matemáticas (CIMAT), Monterrey, México; cSQC and OR Unit, Indian Statistical Institute, Kolkata, India SYNOPTIC ABSTR AC T This work considers determination of reliability acceptance sampling plans (RASPs) for the Weibull distribution under generalized hybrid censoring schemes (GHCSs). Sample size and an acceptability constant are determined for specifid producer’s and consumer’s risks, using the asymptotic normality of the maximum likelihood estimators of model parameters. A simulation study is undertaken to verify whether the RASPs meet the specifid risks for fiite sample size. Optimum RASPs are obtained based on a variance minimization criterion subject to a cost constraint. Suitable algorithms are proposed for computation of optimum RASPs. One data set is analyzed for the purpose of illustration in real-life application. KEY WO RDS AND PHR ASES Consumer’s risk; producer’s risk; maximum likelihood estimators; optimum sampling plan; hybrid censoring scheme Hybridizing Subgradient O ptimizat ion and Very Larg e Scale Neighborhood Search for Nurse Rostering Salim Haddadi and Fatima Guessoum LabSTIC, Universite  M ai , G uelma, Algeria SYNOPTIC ABSTR AC T The nurse rostering problem (NRP) requires the production of a roster for a set of nurses subjected to a predefied set of requirements. NRP is computationally intractable for general instances. This article presents a hybrid algorithm that integrates a very large scale neighborhood (VLSN) search metaheuristic within a subgradient optimization framework. The use of a subgradient optimization technique enables better navigation during the local search process. Searching the exponential size neighborhood amounts to solve a very small binary program (BP). The solution method is tested on benchmark instances from NSPLib. Its effctiveness and competitiveness with three recent methods are shown. KEY WO RDS AND PHR ASES Nurse ro stering; ver y l arge s c a l e n e i g h b o r h o o d s e a rc h ; subgra dient o ptimization; binar y program; NSPLib Optimal Pricing and Replenishment Policies for Instantaneous Deteriorating Items with Back logging and Permissible Delay in Payment u nder I nflation R amachandran Sundararajana and R. Uthayakumarb aPSNA College of Engineering and Technology, Dindigul, India; bGandhigram University, Dindigul, India SYNOPTIC ABSTR AC T In this article, we develop an economic order quantity model to investigate the optimal replenishment policies for instantaneous deteriorating items under infltion. Demand is assumed to be a linear function of the selling price and decreases negatively exponentially with time over a fiite planning horizon under delay in payment. Shortages are allowed and partially backlogged. Under these conditions, we model the retailer’s inventory system as a profi maximization problem to determine the optimal selling price, optimal order quantity, and optimal replenishment time. An easy-to-use algorithm is developed to determine the optimal replenishment policies for the retailer. We also provide optimal present value of profi when shortages are completely backlogged as a special case. Numerical examples are presented to illustrate the algorithm provided to obtain optimal profi. We also obtain managerial implications from numerical examples to substantiate our model KEY WO RDS AND PHR ASES Inventory; deterioration; trade credit; backlogging; inflation; time value of money; finite planning Optimal Redundancy Allocation in Homogeneous Multi-State Cohere nt Systems Debasis B hattachar yaa and Soma Roychowdhuryb aVisva-Bharati University, Santiniketan, India; bIndian Institute of Social Welfare and Business Management, Calcutta, India SYNOPTIC ABSTR AC T Reliability improvement and enhancing system performance through redundancy allocation are often discussed in the context of binary systems, where at any time the systems can be found in one of two states: either fully (perfectly) working or completely failed. But, in practice, the engineered systems might not always be binary. It is rather realistic to assume more than two possible states for components, as well as for the entire system. When the systems and their constituent components are no longer binary, the performance of a system depends on the particular state or level of functioning, and handling of any issues, including system defiition and performance evaluation, become much more complex. Here, a performance measure of a multi-state system based on the performance probabilities at diffrent functioning states is proposed. Not much work has been found in the literature about redundancy allocation in multi-state systems in order to improve the performance of such systems. The present work studies a homogeneous multi-state coherent system, develops basic results and relations, and provides an optimal solution to a redundancy allocation problem. The method derived here can be applied to any complex coherent multi-state system with non-overlapping or overlapping critical subsystems. Numerical examples are added to demonstrate the applicability of the proposed method. KEY WO RDS AND PHR ASES Homogeneous system; multi-state system; redundancy; stochastic order; system performance probability Purely Sequential Fixed Accuracy Confidence Intervals for P(X < Y) under Bivariate Exponential M odels Sudeep R. Bapat Universit y of California, Santa Barbara, U SA SYNOPTIC ABSTR AC T Th is ar ticle d eals with the estimation o f t he reliabilit y o r t he availabilit y parameter θ = P( X < Y) in a stress-strength model. We consider separate cases where ( X, Y) has a bivariate exponential distribution due to Marshall and Olkin (1976) and Freund (1961). We construct a purely sequential estimation methodology to fid a fied accuracy confience interval for the unknown θ in each case. First-order asymptotic effiency and consistency properties are also established of our proposed procedures. We then supplement extensive sets of simulation studies and real data analysis to show encouraging performances of our proposed stopping strategies. KEY WO RDS AND PHR ASES Diabetic retinopathy; laser p h o to co a g u l at i o n ; s t re s s - s t ren g t h m o d e l ; bivariate exponential; scale parameter; first- o rder a s y m p to t i c e ffi c i e n c y; first- o rder asymptotic co n s i s ten c y ; p u rel y sequential; simulations