Residuals for log-Burr XII regression models in survival analysis

In this paper, we compare three residuals to assess departures from the error assumptions as well as to detect outlying observations in log-Burr XII regression models with censored observations. These residuals can also be used for the log-logistic regression model, which is a special case of the log-Burr XII regression model. For different parameter settings, sample sizes and censoring percentages, various simulation studies are performed and the empirical distribution of each residual is displayed and compared with the standard normal distribution. These studies suggest that the residual analysis usually performed in normal linear regression models can be straightforwardly extended to the modified martingale-type residual in log-Burr XII regression models with censored data.     

Likelihood‐based inference for correlated diffusions

The authors address the problem of likelihood‐based inference for correlated diffusions. Such a task presents two issues; the positive definite constraints of the diffusion matrix and the likelihood intractability. The first issue is handled by using the Cholesky factorization on the diffusion matrix. To deal with the likelihood unavailability, a generalization of the data augmentation framework of Roberts and Stramer [Roberts and Stramer (2001) Biometrika 88(3), 603–621] to d‐dimensional correlated diffusions, including multivariate stochastic volatility models, is given. The methodology is illustrated through simulated and real data sets. The Canadian Journal of Statistics 39: 52–72; 2011 © 2011 Statistical Society of Canada     

The Consequences of the Tajikistani Civil War for Abortion and Miscarriage

Although a great deal of attention is paid to reproductive health during violent conflicts, the literature is sparse on the consequences of conflict for abortion and miscarriage. This research provides an analysis of a recent historical case: the 1992–1997 civil war in Tajikistan, using the female questionnaire of the 2007 Tajik Living Standards Survey to examine a subsample of 1445 women surveyed who had reached menarche during or after the war and had been pregnant at least once by the time of the survey. The analysis leverages the uneven geographical scope of conflict events during the civil war to pinpoint women’s exposure to violence, measured by the Uppsala Conflict Data Program. The results show that for women who had reached menarche during or after the civil war, exposure to conflict events increases the likelihood of ever experiencing miscarriage, but not abortion. Including a spatial lag operator reveals that there were also spillover effects for abortion, in which women who were in a broader region of uncertainty were more likely to induce an abortion. These findings highlight the role of institutional changes in affecting pregnancy loss during and after civil war.

     

A framework for production rescheduling in sociotechnical manufacturing environments

No plan survives contact with reality. Despite the rich research base regarding handling uncertainty in production planning and control systems, there is an intellectual gap between theory and practice with regard to handling unforeseen events generated by internal and external factors, such as unforeseen machine downtimes and changes in demand. Motivated by longitudinal observations in two industrial settings and an analysis of the relevant literature, a framework for rescheduling decision-making in the face of unforeseen production events is proposed. In practical settings, the effectiveness of decisions depends on a set of situational factors. The findings of this research can be utilised further to provide guidelines for developing effective decision support principles and systems, addressing the needs of organisational decision-makers.     

Managing seasonal fluctuations in demand. Practice and experience of selected industrial enterprises

Principles and methods of production management only seldom address the issue of seasonal variation. Yet, many industrial enterprises are confronted with heavy fluctuations over the year. This article reports on an industrial study of methods developed and applied in six Danish industrial enterprises. The methods represent different approaches to the management of seasonal variation and they often challenge traditions and call for a mental shift on the part of both management and workers.     

A modelling approach for production costing and continuous improvement of manufacturing processes

It is shown how production management constraints can be taken into account as early as the design stage of the product. It is then shown that the indication of physical and economic performances is a means to obtain integration and to continually improve the manufacturing processes. To perform continuous and efficient evaluation of physical and economic performances, the concept of activity is introduced, now acknowledged as a basic concept of cost management systems. A modelling approach is then proposed to allow each member of the design team, in a concurrent engineering context, to perform activity based modelling and estimations with simulation. After describing the set of possible situations in which this approach can be used, an application case is presented concerning a French firm, and the advantages and disadvantages of the approach are discussed.     

Priority class scheduling: Production scheduling for multi-objective environments

A new scheduling framework (priority class scheduling) is devised which reduces the conflict in the manufacturingmarketing interface. Priority class scheduling rewards manufacturing for making small improvements in efficiency, involves marketing in the setting of production priorities, improves customer service by putting in place realistic production timetables, allows manufacturing to concentrate on improving both quality and efficiency, and improves both the communication and cooperation between the shop floor, the production scheduler, marketing, and customer service. Within a production period, all jobs are classified into priority classes based on both their due dates and importance. Production is scheduled within each production period to maximize throughput subject to the priority class constraints- if any job in priority class i is started in the production period, then all jobs in priority class i - 1 must be completed within the production periods.     

Performance analysis of a multi-agent scheduling and control system under manufacturing disturbances

This paper is concerned with evaluating the performance of alternative multi-agent approaches to manufacturing planning and control. In order to separate the influence of ‘control algorithm’ from that of ‘control architecture’, a simple local control algorithm is chosen as a common starting point for developing the agent-based system. Two sets of experiments are then reported to evaluate how changes in individual agent characteristics can affect the control system's flexibility and adaptability against disturbances. These experiments show that the manufacturing and control system performance is not affected by architecture if the control algorithm remains fixed, however, altering the characteristics of the control system decision-makers influences both systems’ performance.     

A modified internal rate of return model for capital rationing in project selection

The ability of a company to finance viable projects depends on the availability of funds, and this too is a function of time, interest rate and risk factors among others. Factors such as these would lead to limited fund availability, which would necessitate capital rationing. Linear/integer programming and profitability index are often used to tackle this problem for optimal solution. A third approach utilizing a modified internal rate of return (IRR) is proposed. To overcome the difficulty usually encountered in calculating IRR, a small program coded in BASIC is presented. Even though discounting the cash outflows beyond the initial year should have been ideal in the linear programming formulation, this paper casts doubts as to the validity of the solution derived from it, as different discount rates seem to produce very conflicting results from the same set of investment options. This is also applicable to profitability index. While efforts are being made to correct these lapses, the modified IRR model has been found useful in arriving at an optimum solution both for the single-period as well as for the multi-stage situation.