Search results

The commitment to statistical process control programmes is becoming commonplace in US industry. However, some companies are experiencing failure of these programmes, particularly in multi‐strata (population) production processes. Even if such a process is in a state of statistical control, there is a high likelihood that one or more strata could drift away from the target owing to an assignable cause. The success of a QC programme depends on the ability of a quality control practitioner to detect this shift with a greater statistical power (sensitivity) and take corrective actions. Addresses the problem faced by the multi‐strata production process of a local manufacturing company in detecting a single stratum shift from the target with a high level of sensitivity. Proposes the selection of an appropriate sampling method (stratified or random) to have a strong bearing on the relative sensitivity of detecting the above shift in a single stratum. Develops power curves for the above mentioned process under stratified and random sampling scenarios, when a shift occurs in a single stratum. Examines the relationship of sample size to the threshold level of the stratum shift and the preferred sampling method.

Nearest neighbor imputation has a long tradition for handling item nonresponse in survey sampling. In this article, we study the asymptotic properties of the nearest neighbor imputation estimator for general population parameters, including population means, proportions and quantiles. For variance estimation, we propose novel replication variance estimation, which is asymptotically valid and straightforward to implement. The main idea is to construct replicates of the estimator directly based on its asymptotically linear terms, instead of individual records of variables. The simulation results show that nearest neighbor imputation and the proposed variance estimation provide valid inferences for general population parameters.

This paper seeks to address the administration of Standardized Assessment of Information Literacy Skills (SAILS), the use of SAILS report data, and respondent perceptions of the utility of SAILS at institutions that comprise the “All Institutions Benchmark” – the institutions which participated in the SAILS testing through the Spring 2007 testing period.

An online survey was used to collect qualitative and quantitative data for the study. Overall response rate for the survey was 63.9 percent. Disregarding unusable responses, the response rate for the data analysis was 57.8 percent.

The large majority of institutions used convenience sampling in administering SAILS. With regard to the SAILS report data, there are indications that those institutions that received support for data analysis were more likely to find the results useful; the utility of the SAILS report data can also be correlated with institutional type.

Results from this study suggest that SAILS can be most effective if there is statistical/institutional research support for data analysis, if the sampling method for selecting test takers is more rigorous, if SAILS is used in conjunction with other instruments, and if the SAILS data is correlated with other institutional data.

There have been few published studies on the large‐scale administration of standardized information literacy assessments. Moreover, there has been no other published research study assessing multiple institutions' experience of administering SAILS and using SAILS results. Institutions interested in the use of SAILS and other well‐known standardized information literacy tests will find this paper especially relevant.

The purpose of this paper is to compare two ways of collecting job quality data in Britain using a common set of questions. One way is through a short quiz taken by a self-selected sample and completed by clicking on a web link www.howgoodismyjob.com. The other way is via an invitation to take part in a long-running survey of working life – the Skills and Employment Survey. The survey takes much longer to complete, is carried out face-to-face and is based on random probability principles.

To be content-comparable, the quiz uses tried and tested questions contained in recent waves of the Skills and Employment Survey. Each survey comprises a nationally representative sample of workers in Britain aged 20–65 years. However, the quiz is based on uncontrolled convenience sampling prompted, in large part, by a Facebook advertising campaign, whereas survey participants are randomly selected. In this paper, the authors compare the profile of respondents and their responses to these two different modes of data collection and therefore shine a light on any biases in the samples and differences in the results respondents report.

The paper shows that while the number taking in the quiz is impressive, participation in the quiz – unlike the survey – is heavily skewed. Weighting can be used to correct some of these sample selection biases. But, even then, the picture painted by the quiz and survey data varies with the quiz under-reporting the intrinsic quality of jobs, while over-reporting on the extrinsic rewards. This suggests that how job quality data are collected can have a strong influence on the results produced.

The findings suggest that a number of biases are in operation, both in terms of those who take part and the answers they give. This makes comparison between data collected using radically different methods, at best, inadvisable and, at worst, misleading. Nevertheless, quizzes are a good way of engaging large numbers of people in public debates, gathering additional data, extending the reach of academic work and prompting action to improve working life. However, the limitation of this study is that it does not offer a true experiment of different ways of collecting the same data. The quiz and survey were, for example, not carried out at the same time, but were some 14 months apart.

Over 50,000 people took part in the quizzes reported in the paper and almost 1,300 investigated joining a trade union as a result. The reach of the quiz far exceeds the 3,306 people who took part in the Skills and Employment Survey 2017.

This paper focusses on how job quality data are collected and the consequences this has for the validity of the data gathered. This is a unique contribution to international debates about the measurement and monitoring of trends in job quality.

Testing of hypothesis, also known as sample-testing, is a common feature with almost every social and management research. We draw conclusion on population (characteristics) based on available sample information, following certain statistical principles. This paper will introduce the fundamental concepts with suitable examples, mostly in Indian context. This section is expected to help scholar readers, to learn, how hypothesis tests for differences means (or proportions) take different forms, depending on whether the samples are large or small; and also to appreciate hypothesis-testing techniques, on how it could be used in similar decision-making situations, elsewhere.

Bounds on the rate of convergence of learning processes based on random samples and probability are one of the essential components of statistical learning theory (SLT). The constructive distribution‐independent bounds on generalization are the cornerstone of constructing support vector machines. Random sets and set‐valued probability are important extensions of random variables and probability, respectively. The paper aims to address these issues.

In this study, the bounds on the rate of convergence of learning processes based on random sets and set‐valued probability are discussed. First, the Hoeffding inequality is enhanced based on random sets, and then making use of the key theorem the non‐constructive distribution‐dependent bounds of learning machines based on random sets in set‐valued probability space are revisited. Second, some properties of random sets and set‐valued probability are discussed.

In the sequel, the concepts of the annealed entropy, the growth function, and VC dimension of a set of random sets are presented. Finally, the paper establishes the VC dimension theory of SLT based on random sets and set‐valued probability, and then develops the constructive distribution‐independent bounds on the rate of uniform convergence of learning processes. It shows that such bounds are important to the analysis of the generalization abilities of learning machines.

SLT is considered at present as one of the fundamental theories about small statistical learning.

This paper aims to review the latest management developments across the globe and pinpoint practical implications from cutting-edge research and case studies.

This briefing is prepared by an independent writer who adds their own impartial comments and places the articles in context.

The results show that the sample recruited for participation in the online quiz is skewed towards those working in the public sector, people in higher education and towards younger age groups and women whereas the random probability survey is more representative of the adult working population in the UK.

The briefing saves busy executives, strategists and researchers hours of reading time by selecting only the very best, most pertinent information and presenting it in a condensed and easy-to-digest format.