Experimental measurement of preferences in health care using best-worst scaling (BWS): theoretical and statistical issues.

For optimal solutions in health care, decision makers inevitably must evaluate trade-offs, which call for multi-attribute valuation methods. Researchers have proposed using best-worst scaling (BWS) methods which seek to extract information from respondents by asking them to identify the best and worst items in each choice set. While a companion paper describes the different types of BWS, application and their advantages and downsides, this contribution expounds their relationships with microeconomic theory, which also have implications for statistical inference. This article devotes to the microeconomic foundations of preference measurement, also addressing issues such as scale invariance and scale heterogeneity. Furthermore the paper discusses the basics of preference measurement using rating, ranking and stated choice data in the light of the findings of the preceding section. Moreover the paper gives an introduction to the use of stated choice data and juxtaposes BWS with the microeconomic foundations.

Developing Quantitative Methodologies for the Digital Humanities: A Case Study of 20th Century American Commentary on Russian Literature

Using scientific methods in the humanities is at the forefront of objective literary analysis. However, processing big data is particularly complex when the subject matter is qualitative rather than numerical. Large volumes of text require specialized tools to produce quantifiable data from ideas and sentiments. Our team researched the extent to which tools such as Weka and MALLET can test hypotheses about qualitative information. We examined the claim that literary commentary exists within political environments and used US periodical articles concerning Russian literature in the early twentieth century as a case study. These tools generated useful quantitative data that allowed us to run stepwise binary logistic regressions. These statistical tests allowed for time series experiments using sea change and emergency models of history, as well as classification experiments with regard to author characteristics, social issues, and sentiment expressed. Both types of experiments supported our claim with varying degrees, but more importantly served as a definitive demonstration that digitally enhanced quantitative forms of analysis can apply to qualitative data. Our findings set the foundation for further experiments in the emerging field of digital humanities.

Assessing segmentation processes by click detection: online measure of statistical learning, or simple interference?

Statistical learning can be used to extract the words from continuous speech. Gómez, Bion, and Mehler (Language and Cognitive Processes, 26, 212–223, 2011) proposed an online measure of statistical learning: They superimposed auditory clicks on a continuous artificial speech stream made up of a random succession of trisyllabic nonwords. Participants were instructed to detect these clicks, which could be located either within or between words. The results showed that, over the length of exposure, reaction times (RTs) increased more for within-word than for between-word clicks. This result has been accounted for by means of statistical learning of the between-word boundaries. However, even though statistical learning occurs without an intention to learn, it nevertheless requires attentional resources. Therefore, this process could be affected by a concurrent task such as click detection. In the present study, we evaluated the extent to which the click detection task indeed reflects successful statistical learning. Our results suggest that the emergence of RT differences between within- and between-word click detection is neither systematic nor related to the successful segmentation of the artificial language. Therefore, instead of being an online measure of learning, the click detection task seems to interfere with the extraction of statistical regularities.

Models of core/periphery structures

A common but informal notion in social network analysis and other fields is the concept of a core/periphery structure. The intuitive conception entails a dense, cohesive core and a sparse, unconnected periphery. This paper seeks to formalize the intuitive notion of a core/periphery structure and suggests algorithms for detecting this structure, along with statistical tests for testing a priori hypotheses. Different models are presented for different kinds of graphs (directed and undirected, valued and nonvalued). In addition, the close relation of the continuous models developed to certain centrality measures is discussed.

Research in statistical education — planning of an international survey

As announced in the November 2000 issue of MathStats&OR [1], one of the projects supported by the Maths, Stats & OR Network funds is an international survey of research into pedagogic issues in statistics and OR. I am taking the lead on this and report here on the progress that has been made during the first year. A paper giving some background to the project and describing initial thinking on how it might be implemented was presented at the 53rd session of the International Statistical Institute in Seoul, Korea, in August 2001 in a session on The future of statistics education research [2]. It sounded easy. I considered that I was something of an expert on surveys having lectured on the topic for many years and having helped students and others who were doing surveys, particularly with the design of their questionnaires. Surely all I had to do was to draft a few questions, send them electronically to colleagues in statistical education who would be only to happy to respond, and summarise their responses? I should have learnt from my experience of advising all those students who thought that doing a survey was easy and to whom I had to explain that their ideas were too ambitious. There are several inter-related stages in survey research and it is important to think about these before rushing into the collection of data. In the case of the survey in question, this planning stage revealed several challenges. Surveys are usually done for a purpose so even before planning how to do them, it is advisable to think about the final product and the dissemination of results. This is the route I followed.

Statistical analysis of extreme forest fires

Forest fires can cause extensive damage to natural resources and properties. They can also destroy wildlife habitat, affect the forest ecosystem and threaten human lives. In this paper extreme wildland fires are analysed using a point process model for extremes. The model based on a generalised Pareto distribution is used to model data on acres of wildland burnt by extreme fire in the US since 1825. A semi-parametric smoothing approach is adapted with maximum likelihood method to estimate model parameters.

Statistical investigations - drawing it all together

The author's approach to teaching an integrative unit to a small group of master’s level Applied Statistics students in 2000-2001 is described. Details of the various activities such as data analysis, reading and discussion of papers, and training in consultancy skills are given, as also are details of the assessment. The students’ and lecturer’s views of the unit are discussed.

The Royal Statistical Society and statistical education

This paper describes the role of the Royal Statistical Society in shaping statistical education within the UK and further afield. Until 2001 the Society had four agencies concerned with education at all levels. The work of these is discussed and recent new arrangements are outlined. The Society’s efforts to disseminate good practice through organising meetings and running a network of Associate Schools and College are explored in some detail.