Planning with uncertain materials availability: The value of workday flexibility

In this paper, we consider the problem of a manufacturer that faces uncertainty in the availability of its raw materials. This can occur, for example, in a remanufacturing setting where replacements for damaged components are not always available as needed. We examine the potential for flexible workday policies to mitigate the impact of uncertain materials availability, and present a simulation optimization approach to determine staffing levels under various levels of workday flexibility. An example implementation of the aggregate planning model we develop is provided using data from a cell phone reassembly facility in Hong Kong. Our model provides insights for managers regarding the benefits of increasing levels of workday flexibility when raw material availability is uncertain.     

A reformulation of the aggregate planning problem

This article proposes a reformulation of the aggregate planning problem which more closely agrees with situations frequently encountered in practice. The proposed reformulation assumes that a firm's production planners want to determine the expected service and inventory levels for a given production profile in the face of uncertain seasonal demand. By using several different production profiles that are each consistent with the firm's staffing, subcontracting, and overtime policies, it is possible to pick the profile that best meets the firm's preferences for service level and inventory turns. Actually, the trade-offs between inventory and service levels are examined so that an informed choice can be made by all of those concerned.One of the advantages of the proposed model is that communications can be established among production, marketing, and finance managers who often have conflicting goals. Also, levels for inventory turns, service, and production can be set that are consistent with each other. Furthermore, several alternative production profiles can be examined in a relatively short time through the use of the simulation model proposed.An application of the model to the Wagner Spray Tech Company, a producer of painting equipment, is presented. In this particular case, where forecasting errors are quite high, some of the potential uses of the model are presented. Also, reasons are given why this particular reformulation of the aggregate planning problem was found to be useful.     

Selection and Training for Integrated Manufacturing: The Moderating Effects of Job Characteristics

This study examined the conditions under which aspects of integrated manufacturing (e.g. advanced manufacturing technology, total quality management, just-in-time inventory control) lead to selection and/or training for technical and problem-solving skills of employees. Results from our study of 74 plants showed main effects of advanced manufacturing technology and total quality management on training for technical and problem-solving skills, but no main effects on selection. In addition, employee job characteristics were studied to examine the degree to which they might moderate the effects of integrated manufacturing. Several interaction effects were found as they related to staffing and training practices. In general, staffing was used less in response to integrated manufacturing when employees' jobs involved high levels of task uncertainty and interdependence. In contrast, the effects on training remained steady or increased under conditions of task uncertainty. Based on this, we conclude that staffing and training are emphasized under different circumstances and, therefore, should not be simply viewed as substitutes for one another in responding to the demands of integrated manufacturing. Our results are discussed in terms of their theoretical and practical implications.     

Back to the roots of the M/D/s queue and the works of Erlang, Crommelin and Pollaczek

A.K. Erlang introduced the M/D/ s queue in 1917, while F. Pollaczek and C.D. Crommelin formalized the theory using complex analysis and transforms. Let D ( s , λ ) denote the stationary probability of experiencing no waiting time in the M/D/ s queue with arrival rate λ and service requirement 1. We use D ( s , λ ) as a vehicle to give an overview of some of the results we obtained over the last years, including explicit characterizations of the roots, the derivation of infinite series from expressions in terms of roots using Fourier sampling and heavy-traffic limits obtained from square-root staffing. We propose to call D ( s , λ ) the Erlang D formula, for which several new results are presented and compared with the results of Pollaczek.     

Dilemmas in linking succession planning to individual executive learning

This paper examines the issue of linking the selection of top-level executives with the development of these people. It first describes three stages in an organization's development of a succession system which promotes the attainment of a firm's objectives: 1) oneposition staffing, 2) replacement planning, and 3) succession planning. Then we examine the other piece to be connected to succession planning: executive learning. It is argued that most planned executive development is aimed at task learning, not personal learning. Consistent with this condition, most executive education activities overstress classroomstyle receptive methods, while neglecting active learning. Reasons for this state of affairs are proposed. The paper concludes with recommendations for enhancing personal learning for executives and for better integrating this learning with the strategic succession planning of the organization. This sort of strategic approach to executive succession is seen as the “acid test” in a firm's strategic planning process.     

Combining prediction intervals in the M4 competition

The 2018 M4 Forecasting Competition was the first M Competition to elicit prediction intervals in addition to point estimates. We take a closer look at the twenty valid interval submissions by examining the calibration and accuracy of the prediction intervals and evaluating their performances over different time horizons. Overall, the submissions fail to estimate the uncertainty properly. Importantly, we investigate the benefits of interval combination using six recently-proposed heuristics that can be applied prior to learning about the realizations of the quantities. Our results suggest that interval aggregation offers improvements in terms of both calibration and accuracy. While averaging interval endpoints maintains its practical appeal as being simple to implement and performs quite well when data sets are large, the median and the interior trimmed average are found to be robust aggregators for the prediction interval submissions across all 100,000 time series.     

Engaging the professional: organising call centre agents in India

The extremely challenging external environment poses numerous challenges to union formation among call centre agents in India. Complicating matters is the acquired professional identity of call centre agents. In this scenario, the union organising call centre employees envisaged that partnership with employers was the only possibility acceptable to call centre agents, employer organisations and society at large, enabling them to regain some acceptability and credibility for the heretofore tainted Indian trade union movement.     

Economic Design of EWMA Charts with Variable Sampling Intervals

Control charting is a graphical expression and operation of statistical hypothesis testing. In the present paper, we develop the economic design of the variable sampling intervals (VSI) exponentially weighted moving average (EWMA) charts to determine the values of the six test parameters of the charts (i.e., the sample size, the long sampling interval, the short sampling interval, the warning limit coefficient, the control limit coefficient, and exponential weight constant) such that the expected total cost is minimized. The genetic algorithm (GA) is applied to search for the optimal values of the six test parameters of the VSI EWMA chart, and an example is provided to illustrate the solution procedure. A sensitivity analysis is then carried out to investigate the effects of model parameters on the solution of the economic design.     

Do cultural differences explain differences in attitudes towards unions? Culture and attitudes towards unions among call centre workers in Britain and India

This article adds to the literature on worker attitudes towards unions by investigating the impact of cultural attitudes and the call centre labour process on union attitudes among call centre workers in Britain and India. It is hypothesised that workers with egalitarian and collectivist cultural attitudes will be more likely to have pro‐union attitudes than other workers, although if the impact of cultural attitudes is mediated by history and institutions, it might be expected that this relationship is stronger for British than Indian workers. Conversely, if union attitudes are largely a function of the call centre labour process, we would expect union attitudes to be similar among workers in both countries. Our results only partially support our hypotheses. Collectivist attitudes are only weakly related to union attitudes among the British sample but are more strongly related in the Indian sample. There are significant differences between union attitudes among our British and Indian samples. The article concludes that relationship between cultural attitudes and union attitudes are heavily dependent on institutional context. Cultural attitudes are unlikely to be either a constraint or a facilitator of union efforts to organise workers.     

区间时间序列预测准确度探讨

区间时间序列在决策过程中提供重要的信息,特别是在经济发展、人口政策、规划管理或金融监管等方面,因此如何计算出预测区间的精确度成为一个重要议题。本文提出两种区间预测准确度分析的方法,通过估计预测结果的平均区间误差平方和及平均相对区间误差和,比较不同预测方法的优劣。并由预测区间与实际区间的重叠位置,充分说明预测方法所具有的有效性。这些分析预测区间准确度的方法,将为管理者提供更客观的决策空间。     

Staffing and equipment decisions for services: An experimental analysis

Many service-oriented firms face demand/work load variations that occur both within and between days, and seasonally during the year. These service firms tend to develop staffing plans based on peak periods, resulting in substantial idle time during low demand periods. To counter this, some firms hire part-time employees to work peak periods to improve productivity. In this way, the cost per customer/transaction (unit) can be reduced.However, the staffing decision is more complex than just determining the number and timing of the work force. The development of good staffing plans must consider the impact of available work stations like telephone consoles and data entry terminals. To use effectively more personnel during peak periods, the firm must have sufficient work stations to assign this work force. Effective staff scheduling must consider simultaneously the work load variations, employ capabilities, and equipment requirements. This article presents a model that incorporates these factors into the decision-making process and examines their interaction.The model analysis illustrates how uncertainty in work load forecasts and staffing flexibility influence expected cost performance and equipment requirements. A set of computer simulation experiments are conducted using operating data from the proof and encoding departments for Ohio National Bank and Chemical Bank. The results suggest that increased staffing flexibility reduces the needed equipment investment, since part time staff can be scheduled more conveniently to meet varying work loads. Also, basing capital equipment decisions on peak work load levels can substantially increase total operating costs. With these costs explicitly estimated, managers can weigh them against desired service level goals to determine the appropriate balance.     

A Path Construction for the Virtual Waiting Time of an M/G/1 Queue

Consider the M/G/1 queue, the finite dam M/G/1 with capacity T, and the impatient customer M/G/1 model, where customers become lost customers if their waiting time exceeds τ. In this note we prove that for all three models and each xe(0, r) the distribution of the number of downcrossings of the virtual waiting time process with level x during a busy cycle is identical. This implies the weaker statement that on [0, T) the distribution functions of the steady state distributions of the amount of unprocessed work (virtual waiting time) are proportional. A number of applications is given.     

The viability of alternative call centre production models

In this article we outline three alternative production models and discuss their applicability to call centre management. These include the classic mass production model, the professional service model and the mass customisation model. We then develop a theoretical framework that identifies potential causal links between management practices, workers? affective and cognitive reactions, and performance outcomes. We use this framework to review literature on service workplaces in organisational behaviour and HR studies and to assess the empirical evidence regarding these causal explanations. Finally, we present two recent quantitative studies of call centre performance – one that examines affective explanations and one that explores cognitive explanations for the HRperformance link. We conclude with directions for future research.     

Een nomogram voor betrouwbaarheidsgrenzen van quantielen en overschrijdingskansen bij normaal verdeelde grootheden

A nomogram for confidence intervals and exceedance probabilities.
In this paper two problems are considered regarding the probability β that an observation on a normally (μ, σ²)-distributed random variable exceeds a given value W:

If μ and σ² are unknown, the two problems are as follows:
1)if Wis given, to determine a confidence interval for β and
2)if β is given, to determine a confidence interval for W.
For these two essentially equivalent problems graphs are given from which the confidence intervals can be determined. The graphs are given in terms of:

and are based on an approximation for the distribution of x¯ +k s .     

Threshold preferences and the environment

In this article we study the implication of thresholds in preferences. To model this we extend the basic model of John and Pecchenino (1994) by allowing the current level of environmental quality to have a discrete impact on how an agent trades off future consumption and environmental quality. Thus, we endogenize the semi-elasticity of utility based on a step function. We find that for low (high) thresholds, environmental quality converges to a low (high) steady state. For intermediate levels it converges to a stable p-cycle, with environmental quality being asymptotically bounded below and above by the low and high steady state. As policy implications we study shifts in the threshold. Costless shifts of the threshold are always worthwhile. If it is costly to change the threshold, then it is worthwhile to change the threshold if the threshold originally was sufficiently low. Lump-sum taxes lead to a development trap and a proportional income tax should be preferred.     

Fiducial inference in the classical errors-in-variables model

For the slope parameter of the classical errors-in-variables model, existing interval estimations with finite length will have confidence level equal to zero because of the Gleser–Hwang effect. Especially when the reliability ratio is low and the sample size is small, the Gleser–Hwang effect is so serious that it leads to the very liberal coverages and the unacceptable lengths of the existing confidence intervals. In this paper, we obtain two new fiducial intervals for the slope. One is based on a fiducial generalized pivotal quantity and we prove that this interval has the correct asymptotic coverage. The other fiducial interval is based on the method of the generalized fiducial distribution. We also construct these two fiducial intervals for the other parameters of interest of the classical errors-in-variables model and introduce these intervals to a hybrid model. Then, we compare these two fiducial intervals with the existing intervals in terms of empirical coverage and average length. Simulation results show that the two proposed fiducial intervals have better frequency performance. Finally, we provide a real data example to illustrate our approaches.     

Locating fire stations: An integrated approach for Belgium

This paper illustrates the potential of a decision-support system developed for Belgium by a consortium of universities and a private firm, in the framework of a public call made by the Ministry of the Interior. The system is designed to provide the Belgian emergency management administration with a complete decision-aid tool for the location of fire stations. The originality of the project is that it includes a risk-modeling approach developed at a national scale. This analysis involves a multiscale GIS that includes a thorough representation of the physical, human and economic spatial realities, a risk-modeling approach, an adequate optimal location and allocation model (taking into account both queuing and staffing problems). The final result is an interactive operational tool for defining locations, equipment allocations, staffing, response times, the cost/efficiency trade-off, etc. This flexible tool can be used in an assessment as well as a prospective context. It has been used to draw a national reorganization plan for fire stations that started being implemented in 2010.     

机关事业单位编制改革问题探究

随着经济社会的不断发展,机关事业单位编制供需在总量和结构上的矛盾凸显,由此出现了大量的“超编”、无编制财政支付和编外人员增多的现象,编制改革的紧迫性增加,必须对机关事业单位分类施策,机关主要在总量控制范围内,通过统筹协调使用和调整编制结构,事业单位可通过统筹协调、实行编制周转池、编制备案制等来解决。     

Confidence Intervals for the Area Under the Receiver Operating Characteristic Curve in the Presence of Ignorable Missing Data

Receiver operating characteristic curves are widely used as a measure of accuracy of diagnostic tests and can be summarised using the area under the receiver operating characteristic curve (AUC). Often, it is useful to construct a confidence interval for the AUC; however, because there are a number of different proposed methods to measure variance of the AUC, there are thus many different resulting methods for constructing these intervals. In this article, we compare different methods of constructing Wald‐type confidence interval in the presence of missing data where the missingness mechanism is ignorable. We find that constructing confidence intervals using multiple imputation based on logistic regression gives the most robust coverage probability and the choice of confidence interval method is less important. However, when missingness rate is less severe (e.g. less than 70%), we recommend using Newcombe's Wald method for constructing confidence intervals along with multiple imputation using predictive mean matching.     

Advances in forecasting with neural networks? Empirical evidence from the NN3 competition on time series prediction

This paper reports the results of the NN3 competition, which is a replication of the M3 competition with an extension of the competition towards neural network (NN) and computational intelligence (CI) methods, in order to assess what progress has been made in the 10 years since the M3 competition. Two masked subsets of the M3 monthly industry data, containing 111 and 11 empirical time series respectively, were chosen, controlling for multiple data conditions of time series length (short/long), data patterns (seasonal/non-seasonal) and forecasting horizons (short/medium/long). The relative forecasting accuracy was assessed using the metrics from the M3, together with later extensions of scaled measures, and non-parametric statistical tests. The NN3 competition attracted 59 submissions from NN, CI and statistics, making it the largest CI competition on time series data. Its main findings include: (a) only one NN outperformed the damped trend using the sMAPE, but more contenders outperformed the AutomatANN of the M3; (b) ensembles of CI approaches performed very well, better than combinations of statistical methods; (c) a novel, complex statistical method outperformed all statistical and CI benchmarks; and (d) for the most difficult subset of short and seasonal series, a methodology employing echo state neural networks outperformed all others. The NN3 results highlight the ability of NN to handle complex data, including short and seasonal time series, beyond prior expectations, and thus identify multiple avenues for future research.