James R. Buck

An investigation of the advantages of using a man-computer interactive scheduling methodology for job shops

Scheduling has been a difficult problem for job shops which manufacture discrete parts. The research described in this paper investigates the hypothesis that interactive man-computer scheduling methodology is more effective in this task than a batch scheduling methodology. This hypothesis is investigated under eight different problem configurations generated by varying three job description parameters. The results have been evaluated statistically and the effectiveness of an interactive schedule compared to the slack-per-remaining-operation heuristic is investigated. Influences of the level of variation in job description parameters on the quality of the interactive schedule have also been analysed in this study. Results show that scheduling interactively is significantly more effective in most problem situations, and that the level of variation of some of the parameters has a significant impact on the quality of the interactive schedule.

PARTIAL MEANS IN THE ECONOMIC RISK ANALYSIS OF PROJECTS.

Abstract Partial means constitute a new measure of economic risk that unifies and subsumes many less general measures. The partial mean of a random variable is its expected value conditioned on its falling within a given range. For a random variable such as the present worth of a return with uncertain timings, partial means are directly usable to discretize a continuum of outcomes in order to build a decision tree. More importantly, partial means can be used as building blocks in computing a variety of established risk measures - loss integrals, Fishbums risk measure, the expected value of perfect information - thus unifying these measures and elucidating their interrelationships. In this paper we define partial means and related measures, illustrate their characteristics through numerical examples, and show their relationships to several less general risk measures. Tables of partial mean properties are presented for various probability distributions, to facilitate computations and comparisons among comp...

Instructions and feedback effects on speed and accuracy with different learning curve models

Abstract This study compares powerform versus exponential learning curve models on the first ten trials of a task, using several dependent measures. Also shown are differences in instructions about speed emphasis, accuracy emphasis, and equal speed-accuracy emphasis. Empirical data were collected on human subjects performing a devised task on discovering a sequence of switch connections to lights. Learning curves of each model were fitted to the serial data and to cumulative average serial data on time, errors, and their product for each individual subject. Difficulties in fitting these models to data are reported along with supporting reasons. The quality of data fits to each model is examined for each criterion. It is shown that the exponential model exhibits more difficulties in being fitted to data, but that it provides a more accurate description of each criterion of learning in this task when the fit is good. Accuracy and speed operating characteristics are shown for each group of subjects who are g...

Presentation Effects and Eye-Motion Behaviors in Dynamic Visual Inspection

Dynamic visual inspection (DVI) occurs when objects on a moving conveyor are being individually examined for compliance with specifications. This study investigated the effect of the conveyor velocity and object interspacing on DVI performance and eye-motion behavior during this task. Nine combinations of these object presentation factors were examined where three pairs of these combinations each had a constant throughput rate (or exposure time). Horizontal eye-motion measurements were made through electrooculography recordings, and these measurements were analyzed to separately distinguish the visual acquisition time from the visual tracking time. Both of these time values tended to vary predictably with the available exposure time and consistently between people as a visual behavior strategy. Inspection errors were found to be highly correlated with the visual behavior.

Advances in Sequential Bayesian Work Sampling

Abstract Sequential Bayesian work sampling has been previously shown to be both more efficient and more adaptable than traditional methods of work sampling. However, a few deficiencies of the Bayesian approach remained. The advances to that methodology shown here greatly reduce or eliminate those deficiencies. These advances include beta parameter maps, confidence subinterval estimation in closed form, preposterior analysis, estimation methods for remaining sample sizes, and other aids to the management of Bayesian work-sampling studies.

Optimum Stratified Cycle Counting

Abstract Cycle counting is a recently devised procedure for continuously updating inventory record accuracy as a replacement for an annual complete inventory count. Cycle counting has been shown to provide greater inventory record accuracy for financial control and for production planning and purchasing operations. However, cycle counting procedures have used an arbitrary basis for classifying inventoried items and for setting the count frequency within each class. In this paper, cycle counting is characterized as stratified statistical sampling. Procedures are shown for maintaining the statistical accuracy required for financial control while reducing the amount of sampling and counting costs. Other criteria can be similarly used. These procedures include the Tschuprow-Neyman optimum allocation rule, the Dalenius-Hodges strata identification rule, a search for an optimum number of strata and improvements in the cycle counting procedures and crew size toward an optimum level: compatible methodologies. A n...

Bayesian Poisson rate estimation using parameter maps

This paper presents a procedure for the sequential estimation of the rate parameter for a Poisson process. The procedure is based on Bayes rule for combining new sample data with a prior estimate to obtain a posterior estimate. The procedure is facilitated by the use of a parameter map for monitoring the sequence of estimates and by a stationarity test for verifying the appropriateness of some of the assumptions.

Measuring Conditional Partial Expected Loss Under Uniformly Distributed Uncertain Timing

ABSTRACT This note extends the Initial partial-mean concept for present worth analysis of risk by Buck and Askin (1986) to a two random variable case where the magnitude of a single cash flow Is a random variable, and the time duration is a random variable with uniform distribution. This extension leads to the calculation of the expected magnitude of a project loss given that the loss occurs. Computational formulas and numerical Illustrations are presented.

Development and application of parameter maps

Abstract The parameter map of a probability distribution shows the relationships between the parameters of the distribution and its moments and sampling statistics. The availability of fast, easy to use computer graphics facilitates the use of parameter maps in a variety of applications. This first part of this paper shows how the equations for the isostatistic curves are derived and presents the equations for the isomen and isovariance curves for some common two-parameter distributions. The second part illustrates the application of parameter maps to statistical modeling, parameter estimation and sequential sampling.

STATUS REPORTING OF "EYES ON" AND PERIPHERAL DISPLAYS DURING TRACKING

In response to external requests, pilots often orally report status information read from scattered visual displays while simultaneously controlling an aircraft. For an experimentally controlled “status-reporting” task, we found that the input frequency on a concurrent-tracking task and the task stream-related factors of the rate, uncertainty, and timing of requests showed few significant effects on mean performance times and standard deviations. Tracking performance did vary greatly between the different phases of the “status-reporting” task, the different types of displays and their locations, and the different tracking-input frequencies. An elementary manual control model produced conformal tracking error means and standard deviations when parameters corresponding to behavioral changes were varied. These results indicated that both the performance time statistics of the “status-reporting” task and the influence of concurrent performance on tracking error can be estimated using simple methods.