Postponement implementation in integrated production and inventory plan under deterioration effects: a case study of a juice producer with limited storage capacity

Abstract

The aim of this study is to develop a production and inventory plan for a fresh apple juice producer. During harvest season, the producer extracts premium juice from freshly picked apples and keeps an inventory of these premium apples in his temperature-controlled storage facility. The producer extracts also regular juice from regular apples purchased from third-party storages. To satisfy future demand, the producer carries inventories of juice and apple. The levels of apple inventories are constrained by the producer’s limited storage space, but he can replenish regular apples. To assist the producer in facing demand uncertainty and deterioration of apples, we develop a production and inventory plan that incorporates postponement to mitigate demand uncertainty. As postponement decisions are shaped by the cost structure of inventories, we integrate in one model the postponement decisions and the deterioration mitigation decisions that can alter the inventory costs. We build multi-period stochastic programming with recourse model to determine juice batch sizes and apple inventories that maximize the producer’s expected profit. The optimal solution illustrates the use of time and form postponements. We discuss the interactions between postponement implementation and decisions to mitigate apples deterioration. We compare the production and inventory plans with and without postponement and with and without apple deterioration. We also present sensitivity analyses for the plan under varying inventory cost and storage space.     

Modelling Poisson marked point processes using bivariate mixture transition distributions

A class of bivariate continuous-discrete distributions is proposed to fit Poisson dynamic models in a single unified framework via bivariate mixture transition distributions (BMTDs). Potential advantages of this class over the current models include its ability to capture stretches, bursts and nonlinear patterns characterized by Internet network traffic, high-frequency financial data and many others. It models the inter-arrival times and the number of arrivals (marks) in a single unified model which benefits from the dependence structure of the data. The continuous marginal distributions of this class include as special cases the exponential, gamma, Weibull and Rayleigh distributions (for the inter-arrival times), whereas the discrete marginal distributions are geometric and negative binomial. The conditional distributions are Poisson and Erlang. Maximum-likelihood estimation is discussed and parameter estimates are obtained using an expectation–maximization algorithm, while the standard errors are estimated using the missing information principle. It is shown via real data examples that the proposed BMTD models appear to capture data features better than other competing models.     

Fitting probability distributions to economic growth: a maximum likelihood approach

The growth rate of the gross domestic product (GDP) usually carries heteroscedasticity, asymmetry and fat-tails. In this study three important and significantly heteroscedastic GDP series are examined. A Normal, normal-mixture, normal-asymmetric Laplace distribution and a Student's t-Asymmetric Laplace (TAL) distribution mixture are considered for distributional fit comparison of GDP growth series after removing heteroscedasticity. The parameters of the distributions have been estimated using maximum likelihood method. Based on the results of different accuracy measures, goodness-of-fit tests and plots, we find out that in the case of asymmetric, heteroscedastic and highly leptokurtic data the TAL-distribution fits better than the alternatives. In the case of asymmetric, heteroscedastic but less leptokurtic data the NM fit is superior. Furthermore, a simulation study has been carried out to obtain standard errors for the estimated parameters. The results of this study might be used in e.g. density forecasting of GDP growth series or to compare different economies.     

A discrete model for the segmentation of chains and strings

A statistical model is presented that can be used to represent a discrete breakage process. It considers a fixed length chain or string made up of n +1 pieces joined together. The chain is stressed at each connection or link andrupture occurs at some of the links. Models are developed to answer the question, “what is the expected proportion of chain segments of a given size?” The model is modified to handle those experiments where only thetotal weight of a given size segment is known. Expressions are obtained for the expected value and variance of the number of segments of a given size. The model is used to predict the expected number of segments which results when a fixed length DNA molecule chain is subjected to carcinogenic agents and is applied to industrial examples.     

Toward re-engineering models and algorithms of facility layout

Models and algorithms are continuously being developed for the facility layout problem in various manufacturing settings. However, there could be practices and obstacles that weaken them and adversely impact the effectiveness of the layout. Thus, they should be obliterated in order to advance the layout problem. This paper suggests a set of guidelines that are directed at the process inherent in developing layout models, algorithms, expert systems, and software applications to assist in improving them and developing better layouts. Such guidelines are lacking in the literature of facility layout. Examples on the suitability and applicability of the suggested guidelines are given.     

Translating evidence into practice in childbirth: A case from the Occupied Palestinian Territory

ObjectiveTo investigate possible changes in practices during normal childbirth by implementing interventions which reduce the frequency of: intravenous fluids; bladder catheterization; analgesia; artificial rupture of membranes; oxytocin use for augmentation; vaginal examination; episiotomy, and increase: mobility; oral intake of fluids; and initiation of immediate breastfeeding.DesignAn operational research design.SettingA referral governmental hospital in the Occupied Palestinian Territory (oPt) between 2006 and 2010.Participants2345 women (baseline: 134 women, intervention: 1860 women, post-intervention: 351 women) and 17 providers (10 midwives and 7 physicians).InterventionsMultifaceted interventions; a combination of on-the-job training, audit, and feedback, supported by a core team and informal meetings.Main outcome measuresChange of practices during normal childbirth according to best evidence and the WHO recommendations.FindingsSignificant sustained improvements in practices during childbirth from baseline to post-intervention including artificial rupture of membranes, liberal use of oxytocin to augment normal labour, intravenous fluids, frequency of vaginal examinations, oral intake, immediate breastfeeding and routine episiotomy (P < 0.005). There was positive change in the mobility during labour, but this change was not sustained after 9 months from intervention to post-intervention. The usage of analgesia did not change.Key conclusionsCertain changes in practices during normal childbirth were possible in this hospital. A combination of on-the-job training with other interactive approaches increased midwives’ awareness, capacities and self-confidence to implement fewer interventions during normal labour.     

Why Do Migrant Workers Intend to Extend Their Stay in Host Countries? The Case of Bangladeshi Workers in Malaysia's Manufacturing Sector

This article explores various factors resulting in temporary migrant workers' decisions to extend their stay in host countries by means of a case study of Bangladeshi factory workers in Malaysia. The employment mediation and passage fees paid to brokers and agents by Bangladeshi workers are very large compared with general living standards in Bangladesh. These large sums are increasing steadily as the number of persons desiring to work overseas increases. Malpractice by brokers and agents causes Bangladeshi workers to overestimate the amount of remittances they can send home, and hence they pay higher mediation and passage fees to brokers or agents. From a humanitarian point of view, the Government should strictly regulate the activities of agents and brokers and provide accurate information to those who plan to work in Malaysia. Statistical analysis suggests that the lower real remittances fall below the expected amounts, and the lower real wages are, compared with passage and mediation fees, the more will Bangladeshi workers wish to extend their stay. These facts imply that if future Bangladeshi migrant workers to Malaysia have the correct information about income levels and living expenses in Malaysia, and hence mediation and passage fees become cheaper, the likelihood of their intending to extend their stays will be much lower.     

Welfare gains of the poor: An endogenous Bayesian approach with spatial random effects

We introduce a Bayesian instrumental variable procedure with spatial random effects that handles endogeneity, and spatial dependence with unobserved heterogeneity. We find through a limited Monte Carlo experiment that our proposal works well in terms of point estimates and prediction. We apply our method to analyze the welfare effects generated by a process of electricity tariff unification on the poorest households. In particular, we deduce an Equivalent Variation measure where there is a budget constraint for a two-tiered pricing scheme, and find that 10% of the poorest municipalities attained welfare gains above 2% of their initial income.     

Focused estimation for noisy and small data sets: a Bayesian minimum expected loss estimator approach

Central to many inferential situations is the estimation of rational functions of parameters. The mainstream in statistics and econometrics estimates these quantities based on the plug‐in approach without consideration of the main objective of the inferential situation. We propose the Bayesian Minimum Expected Loss (MELO) approach focusing explicitly on the function of interest, and calculating its frequentist variability. Asymptotic properties of the MELO estimator are similar to the plug‐in approach. Nevertheless, simulation exercises show that our proposal is better in situations characterised by small sample sizes and/or noisy data sets. In addition, we observe in the applications that our approach gives lower standard errors than frequently used alternatives when data sets are not very informative.