New imperfect rankings models for ranked set sampling

Ranked set sampling is a sampling approach that leads to improved statistical inference in situations where the units to be sampled can be ranked relative to each other prior to formal measurement. This ranking may be done either by subjective judgment or according to an auxiliary variable, and it need not be completely accurate. In fact, results in the literature have shown that no matter how poor the quality of the ranking, procedures based on ranked set sampling tend to be at least as efficient as procedures based on simple random sampling. However, efforts to quantify the gains in efficiency for ranked set sampling procedures have been hampered by a shortage of available models for imperfect rankings. In this paper, we introduce a new class of models for imperfect rankings, and we provide a rigorous proof that essentially any reasonable model for imperfect rankings is a limit of models in this class. We then describe a specific, easily applied method for selecting an appropriate imperfect rankings model from the class.     

Plaid designs for the evaluation of training for medical practitioners

The training of medical practitioners to improve the practitioner/patient relationship may be difficult, as limitations often exist on the choice of patients included in the study. A specific study of this type of training is given. It is proposed that a simple modification and generalization of Yates' plaid-square designs be used. It is shown that a replicated plaid-design incorporates as a special case the criss-cross or strip-plot design. The usefulness of these designs in studies of the training of medical practitioners is illustrated. The basic characteristics of their analysis are outlined.     

Data skeletons: simultaneous estimation of multiple quantiles for massive streaming datasets with applications to density estimation

We consider the problem of density estimation when the data is in the form of a continuous stream with no fixed length. In this setting, implementations of the usual methods of density estimation such as kernel density estimation are problematic. We propose a method of density estimation for massive datasets that is based upon taking the derivative of a smooth curve that has been fit through a set of quantile estimates. To achieve this, a low-storage, single-pass, sequential method is proposed for simultaneous estimation of multiple quantiles for massive datasets that form the basis of this method of density estimation. For comparison, we also consider a sequential kernel density estimator. The proposed methods are shown through simulation study to perform well and to have several distinct advantages over existing methods.     

An alternative to model selection in ordinary regression

The weaknesses of established model selection procedures based on hypothesis testing and similar criteria are discussed and an alternative based on synthetic (composite) estimation is proposed. It is developed for the problem of prediction in ordinary regression and its properties are explored by simulations for the simple regression. Extensions to a general setting are described and an example with multiple regression is analysed. Arguments are presented against using a selected model for any inferences.     

Consistent maximum likelihood estimation of a unimodal density using shape restrictions

It is well known that the unimodal maximum likelihood estimator of a density is consistent everywhere but at the mode. The authors review various ways to solve this problem and propose a new estimator that is concave over an interval containing the mode; this interval may be chosen by the user or through an algorithm. The authors show how to implement their solution and compare it to other approaches through simulations. They show that the new estimator is consistent everywhere and determine its rate of convergence in the Hellinger metric.     

Organizational Compatibility and Workplace Drug Testing: Modeling the Adoption of Innovative Social Control Practices

Few researchers have examined organizational variation in the adoption of workplace drug testing, but innovation theory suggests that adoption is more likely when it is compatible with an organization's values, previously introduced ideas, and needs. Using data from the 1997 National Employee Survey, this research models the effects of organizational compatibility, industry, and establishment size on the adoption of drug testing. The data reveal that compatibility, as measured by an organization's rules orientation, presence of an employee assistance program, and mechanization, is associated with the adoption of drug testing. As predicted, the adoption of drug testing varies across industries and by establishment size.