A two sample wilcoxon test for progressively censored data

A two sairmle Wilcoxon type statistic is proposed for analyzing data for which the pN(0<p≤l) smallest observations are to be observed sequentially and the study terminated as soon as a statistically significant difference is obtained. The statistic is a special case of a general formulation due to chatteriee and Sen (1973), The asymptotic null distribution is presented and simulation studies reported which indicate chat the asymptotic distribution is useful for pN>60. Monte clarlo experiments comparing this statistic with another Wilcoxon type statistic proposed by Halperin and Ware (1974) are presented.     

Repeated confidence intervals and prediction intervals using stochastic curtailment

Jennlson and Turnbull (1984,1989) proposed procedures for repeated confidence intervals for parameters of interest In a clinical trial monitored with group sequential methods. These methods are extended for use with stochastic curtailment procedures for two samples in the estimation of differences of means, differences of proportions, odds ratios, and hazard ratios. Methods are described for constructing 1) confidence intervals for these estimates at repeated times In the course of a trial, and 2) prediction intervals for predicted estimates at the end of a trial. Specific examples from several clinical trials are presented.     

Bayesian regression model for recurrent event data with event-varying covariate effects and event effect

In the course of hypertension, cardiovascular disease events (e.g. stroke, heart failure) occur frequently and recurrently. The scientific interest in such study may lie in the estimation of treatment effect while accounting for the correlation among event times. The correlation among recurrent event times comes from two sources: subject-specific heterogeneity (e.g. varied lifestyles, genetic variations, and other unmeasurable effects) and event dependence (i.e. event incidences may change the risk of future recurrent events). Moreover, event incidences may change the disease progression so that there may exist event-varying covariate effects (the covariate effects may change after each event) and event effect (the effect of prior events on the future events). In this article, we propose a Bayesian regression model that not only accommodates correlation among recurrent events from both sources, but also explicitly characterizes the event-varying covariate effects and event effect. This model is especially useful in quantifying how the incidences of events change the effects of covariates and risk of future events. We compare the proposed model with several commonly used recurrent event models and apply our model to the motivating lipid-lowering trial (LLT) component of the Antihypertensive and Lipid-Lowering Treatment to Prevent Heart Attack Trial (ALLHAT) (ALLHAT-LLT).     

Empirical Analysis of the Effects of Cyber Security Incidents

We analyze the time series associated with web traffic for a representative set of online businesses that have suffered widely reported cyber security incidents. Our working hypothesis is that cyber security incidents may prompt (security conscious) online customers to opt out and conduct their business elsewhere or, at the very least, to refrain from accessing online services. For companies relying almost exclusively on online channels, this presents an important business risk. We test for structural changes in these time series that may have been caused by these cyber security incidents. Our results consistently indicate that cyber security incidents do not affect the structure of web traffic for the set of online businesses studied. We discuss various public policy considerations stemming from our analysis.     

Processes Linking Social Class and Racial Socialization in African American Dual-Earner Families

We examined the links between social class, occupational self-direction, self-efficacy, and racial socialization in a sample of 128 two-parent African American couples raising adolescents. A series of multivariate, multilevel models revealed that mothers' SES was connected to self-efficacy via its association with occupational self-direction; in turn, self-efficacy partially explained the association between occupational self-direction and racial socialization. The link between maternal self-efficacy and racial socialization depended on whether or not children had experienced discrimination. For fathers, a strong link between SES and occupational self-direction emerged, but significant associations were not found between occupational self-direction and self-efficacy, or self-efficacy and racial socialization. The discussion focuses on mother-father differences and the role of child effects in racial socialization.     

Decisional Conflict and User Acceptance of Multicriteria Decision-Making Aids*

Despite the development of increasingly sophisticated and refined multicriteria decision-making (MCDM) methods, an examination of the experimental evidence indicates that users most often prefer relatively unsophisticated methods. In this paper, we synthesize theories and empirical findings from the psychology of judgment and choice to provide a new theoretical explanation for such user preferences. Our argument centers on the assertion that the MCDM method preferred by decision makers is a function of the degree to which the method tends to introduce decisional conflict. The model we develop relates response mode, decision strategy, and the salience of decisional conflict to user preferences among decision aids. We then show that the model is consistent with empirical results in MCDM studies. Next, the role of decisional conflict in problem formulation aids is briefly discussed. Finally, we outline future research needed to thoroughly test the theoretical mechanisms we have proposed.     

A HEURISTIC PROCEDURE FOR DETERMINING IN-PROCESS INVENTORIES

Most prior studies that examine in-process inventory requirements associated with a manufacturing facility employ an optimizing algorithm; this article proposes a heuristic procedure for determining such requirements. A procedure is given for determining “active” and “banked” work-in-process requirements. The two are combined to give total in-process requirements. A key factor presented in the paper is the relationship between in-process inventory requirements and the “balancing” of a production facility. Most prior researchers examine these problems independently. It will be shown that both problems can be resolved concurrently. The concepts are applicable to both an existing as well as a new manufacturing facility.     

Improving Computer Training Effectiveness for Decision Technologies: Behavior Modeling and Retention Enhancement*

Managers and analysts increasingly need to master the hands‐on use of computer‐based decision technologies including spreadsheet models. Effective training can prevent the lack of skill from impeding potential effectiveness gains from decision technologies. Among the wide variety of software training approaches in use today, recent research indicates that techniques based on behavior modeling, which consists of computer skill demonstration and hands‐on practice, are among the most effective for achieving positive training outcomes. The present research examines whether the established behavior‐modeling approach to software training can be improved by adding a retention enhancement intervention as a substitute for, or complement to, hands‐on practice. One hundred and eleven trainees were randomly assigned to one of three versions of a training program for spreadsheets: retention enhancement only, practice only, and retention enhancement plus practice. Results obtained while controlling for total training time indicate that a combination of retention enhancement and practice led to significantly better cognitive learning than practice alone. The initial difference in cognitive achievement was still evident one week after training. Implications for future computer training research and practice are discussed.     

How Long Should a Customer Wait for Service?

A major concern for service managers is the determination of how long a customer should wait to be served. Services, due to the customer's direct interaction with the process, must face a trade-off between minimizing the cost of having a customer wait and the cost of providing good service. A total cost model is presented for determining how long a customer should wait when these two conflicting cost components are considered. An integral part of this model includes a measure of customer satisfaction with waiting time which is used to develop a waiting cost function. The model is then applied to a major fast food chain, using data collected at several locations. Analysis of the data reveals that the “ideal” waiting time for this firm is significantly less than the current corporate waiting time policy. Thus, as indicated by the model, a corporate policy change is recommended to provide much faster service. The adoption of such a policy would result in increased labor costs, and would simultaneously increase the firm's overall profits. Although appearing contradictory, increases in current labor costs and long-term profits are both possible when management takes the long-range perspective suggested in this paper.