Search results

The purpose of this paper is to show how to properly use the method of replacement to construct mixed two- and four-level minimum setup split-plot type designs to accommodate the presence of hard-to-assemble parts.

Split-plot type designs are economical approaches in industrial experimentation. These types of designs are particularly useful for situations involving interchangeable parts with different degrees of assembly difficulties. Methodologies for designing and analyzing such experiments have advanced lately, especially for two-level designs. Practical needs may require the inclusion of factors with more than two levels. Here, the authors consider an experiment to improve the performance of a Baja car including two- and four-level factors.

The authors find that the direct use of the existing minimum setup maximum aberration (MSMA) catalogs for two-level split-plot type designs may lead to inappropriate designs (e.g. low resolution). The existing method of replacement for searching exclusive sets of the form (α, β, αβ) available in the literature is suitable for completely randomized designs, but it may not provide efficient plans for designs with restricted randomization.

The authors provide a general framework for the practitioners and have extended the algorithm to find out the number of generators and the number of base factor at each stratum, which guide the selection of mixed two-level and four-level MSMA split-plot type designs.

The chapter considers the ethical problems engendered by random assignment and privacy concerns in randomised controlled experiments and cluster randomised trials. The particular focus is on procedural, legislative and technical approaches to reducing or avoiding the problems. Examples are given from a variety of disciplines including health and education, though the main emphasis is on research in crime and delinquency.

When there are few treated clusters in a pure treatment or difference-in-differences setting, t tests based on a cluster-robust variance estimator can severely over-reject. Although procedures based on the wild cluster bootstrap often work well when the number of treated clusters is not too small, they can either over-reject or under-reject seriously when it is. In a previous paper, we showed that procedures based on randomization inference (RI) can work well in such cases. However, RI can be impractical when the number of possible randomizations is small. We propose a bootstrap-based alternative to RI, which mitigates the discrete nature of RI p values in the few-clusters case. We also compare it to two other procedures. None of them works perfectly when the number of clusters is very small, but they can work surprisingly well.

Meat consumption has a variety of implications in society. While various types of meat-restricted diets exist to address this, not enough is known about how the average meat consumer views different avenues to lessening their intake. In response, this study aims to assess US omnivores’ impressions of three meat-restricted diets.

An online survey was administered to a cross-sectional, census-balanced sample from Nielsen of 30,000+ US adults. Omnivores (N = 928) were randomized into one of the three conditions where they were asked about their perceptions of a vegetarian diet, a reduced-meat diet or a chicken-free diet as individuals not currently following that dietary pattern.

The findings showed that omnivores had a more favorable perception of a reduced-meat diet on a greater number of study variables as compared to the vegetarian or chicken-free diets. The research also demonstrated that a majority of omnivores were in the precontemplation stage of cognitive change, suggesting that most American omnivores are not actively demonstrating a readiness to alter their meat consumption in the ways presented.

This research is the first to examine the comparative trends around these three diets among omnivores. It also speaks to how the desirability of meat restriction varies by type of approach, i.e. elimination or reduction, and if the latter, what type. The findings may be of relevance for efforts to reduce global meat consumption for ethical, health, or environmental reasons.

The purpose of this paper is to present the results of a pilot trial, investigating the accessibility provided by a tablet computer (Apple iPad) to individuals with visual impairment. The study was designed around an N-of-1 randomised controlled trial (RCT), which was replicated for 12 participants. It served as an opportunity to evaluate the use N-of-1 trials in studies involving people who are visually impaired.

The study centred round an N-of-1 RCT, comparing the accessibility provided by control equipment (Windows computer) against the intervention equipment (Apple iPad). Twelve participants conducted six tests on the equipment as per randomisation, followed by a quantitative-based evaluation and short interviews.

One-sided individual randomisation tests showed a significant result for overall satisfaction in favour of the tablet at the 0.05 significance level for seven of the participants. Participants identified several strengths of the iPad in helping a partially sighted user in accessing the internet: inbuilt zoom and magnification options; increased control as a result of the touch screen; and accessibility tools being built into the operating system. The main limitation suggested was the way the zoom function operates by enlarging the onscreen keyboard. This caused difficulties for those with more severe visual impairments using this function in inputting text.

There has been limited research to substantiate positive reviews of the tablet computer for low-vision users. The results of this pilot study gives evidence in support of these potential benefits, and demonstrates the importance of a more thorough investigation.

Confounding is of central importance in epidemiologic studies. Its definition has been under wide debate over the past decades. The classical definition is straightforward and easy-to-implement. Nevertheless, it is data-driven and has drawbacks. The more recent counterfactual definition captures the essential roles a confounder plays in causal inference. It would be beneficial for researchers to grasp substantive knowledge in causal structure and broadly adopt the latter definition. There are various methods of handling confounding issues. The choice of one option over another depends on various factors, including the nature of the study, sample size and rarity of events.

This paper aims to examine the level of open access (OA) adoption by researchers in Indian Institutes of Technology (IITs), identify predictors of OA status (OA vs non-OA) and explore the availability of OA versions of the articles and venues used by the researches for hosting of their articles.

Articles contributed by the researchers in IITs were searched using an advance search option in the Web of Science Core collection database. The search was restricted to journal articles published in English language in the year 2015. Of the 10,049 articles retrieved, 1,023 (10 per cent of the total) were chosen randomly. Articles selected after randomizations were exported to MS Excel for further analyses. Title of each article was searched in Google Scholar to assess its OA availability and venues used by the author for self-archiving. Details of ten articles could not be traced in Google Scholar, and they were excluded from the analysis. Based on the analysis of URLs, all OA articles were classified into three categories: gold OA, green OA and both gold and green OA. The OA articles available through green route were further classified into six categories based on the analysis of the websites and the self-archiving venues used by the authors: institutional repository, subject repository, researcher or scholar’s website, organizational website, ResearchGate and other websites.

Of 1,013 articles examined, OA versions were found for 68.70 per cent of articles. Of the total OA articles, 10.26 per cent articles were available through gold OA and 58.44 per cent were available through green OA, while remaining 6.21 per cent were available via both gold and green OA routes. Although researchers use different venues for self-archiving their articles, ResearchGate and institutional repositories are the most preferred choices by the researchers in IITs. Researchers in IITs are seemed to be unaware of the self-archiving policies of publishers, as more than 85 per cent self-archived articles were found as final PDF versions that are normally not allowed by the publishers.

This study is limited to IITs, but it offers theoretical implications for extending its scope to different subjects and institutes. The findings of the study may be useful for the publishers and institutions for formulating OA policies. The findings of the study might be used for raising awareness of OA among researchers and encouraging them to contribute their research outcome in OA outlets.

This is the first study in India focusing on the availability of OA research.

We review the experimental evidence on risk aversion in controlled laboratory settings. We review the strengths and weaknesses of alternative elicitation procedures, the strengths and weaknesses of alternative estimation procedures, and finally the effect of controlling for risk attitudes on inferences in experiments.

Reassesses the Minneapolis Domestic Violence Experiment (MDVE) data of the 1980s which said that “arrest works best”. Examines the potential effects of a small number of officers generating a relatively large number of MDVE cases. Expresses concern that a few officers submitting a high rate of cases might have an inordinately large effect on the experimental outcomes. Seeks to determine whether they followed the experimental protocol but finds instead that it was the low rate officers who failed to do so. Finds that officers who submitted experimental cases at a high rate were also different in other ways from the rest of the officers. Finally, excludes findings relating to lower case officers and thereby reveals that recidivism in domestic violence was not reduced by the arrests.

Social networks are seen to influence the use of health and social care services. In a secondary analysis of data from a longitudinal study of befriending of carers of people with dementia, we studied the relationship between network type and support from family/ friends, voluntary sector befriending and residential/nursing care. Using Wenger's typology of social networks, findings suggest that the pattern of support use varies by differences in the structure of networks. It is recommended that questions on social networks should be widely incorporated into carers' assessments to help identify need for social support interventions and to enable the sensitive selection of appropriate types of carer support to be provided.