An Improved Boxplot for Univariate Data

The boxplot is an effective data-visualization tool useful in diverse applications and disciplines. Although more sophisticated graphical methods exist, the boxplot remains relevant due to its simplicity, interpretability, and usefulness, even in the age of big data. This article highlights the origins and developments of the boxplot that is now widely viewed as an industry standard as well as its inherent limitations when dealing with data from skewed distributions, particularly when detecting outliers. The proposed Ratio-Skewed boxplot is shown to be practical and suitable for outlier labeling across several parametric distributions.     

Serials spoken here: reports of conferences,institutes, and seminars

Abstract

Reports on the Ohio Valley Group of Technical Services Librarians (OVGTSL) Annual Conference, the April 2004 New England Technical Services Librarians (NETSL) Conference, the 2004 Acquisitions Institute at Timberline Lodge, and the 2004 Conference of the North American Serials Interest Group (NASIG).

Reports are from four conferences held in various parts of the United States and cover a wide range of topics. The Ohio Valley Group of Technical Services Librarians program emphasized the relationship between technical and public services. Education, both formal and continuing, was the theme for the New England Technical Services Librarians. Timberline Lodge hosted another Acquisitions Institute featuring sessions on new discoveries. The report on the 2004 North American Serials Group Annual Conference allows Conference Student Grant Award winner Chris Brady to include some personal reflections along with summaries of the sessions he attended.     

Constructing an Accounting Journal Website

Abstract

To increase the effectiveness and efficiency of searches for information, accounting students, researchers, practitioners, and regulators could benefit from a Website devoted to the electronic access to journals. The site described here addresses such a need in the business discipline of accounting. On the site, the titles of over 470 journals are listed and categorized by topical areas within accounting. Then, within each accounting category, the journals are grouped according to their Internet accessibility. To provide the user with quick access to the various journals, the site provides links to the homepages of the various journals. Serials Review 2002; 28:201–205.     

Functional sliced inverse regression analysis

Most of the usual multivariate methods have been extended to the context of functional data analysis. Our contribution concerns the study of sliced inverse regression (SIR) when the response variable is real but the regressor is a function. In the first part, we show how the relevant properties of SIR remain essentially the same in the functional context under suitable conditions. Unfortunately, the estimation procedure used in the multivariate case cannot be directly transposed to the functional one. Then, we propose a solution that overcomes this difficulty and we show the consistency of the estimates of the parameters of the model.     

Parameter estimation in nonlinear regression models 1

Fisher information contained in record values, inter-record times and their concomitants from a sample of fixed size is derived in general and explicit expressions are deduced for some specific known bivariate classes of distributions. A comparison between fixed sampling and inverse sampling schemes with equal number of records and concomitants is also carried out. We also consider parameter estimation based on bivariate records and a small simulation study is done.     

Parameter selection in modified histogram estimates

A multivariate modified histogram density estimate depending on a reference density g and a partition P has been proved to have good consistency properties according to several information theoretic criteria. Given an i.i.d. sample, we show how to select automatically both g and P so that the expected L ₁ error of the corresponding selected estimate is within a given constant multiple of the best possible error plus an additive term which tends to zero under mild assumptions. Our method is inspired by the combinatorial tools developed by Devroye and Lugosi [Devroye, L. and Lugosi, G., 2001, Combinatorial Methods in Density Estimation (New York, NY: Springer–Verlag)] and it includes a wide range of reference density and partition models. Results of simulations are also presented.