Bayesian volumetric calibration: an application of reversible jump Markov chain Monte Carlo methods

Volumetric calibration is used for high accuracy estimation of the functional volume-to-level relationship for vessels used to store hazardous liquids. An example of calibration of a vessel for reprocessed nuclear material is used to illustrate an analysis of calibration data. We advocate a Bayesian approach, with proper account of genuine prior information, using a reversible jump Markov chain Monte Carlo method for estimation.     

Ecological structure of Winnipeg 1951 and 1961: a reappraisal*

Hunter and Latif (1973) performed a multi-method factorial ecology study of Winnipeg for 1951 and 1961. While the study is on the whole academically sound, the part dealing with temporal changes in the ecological structure contains methodological and interpretive errors. It is therefore the intention of this paper to draw attention to the errors the authors made and then on the basis of corrected values draw the proper conclusions about changes in Winnipeg's ecological structure.
The interested reader should analyze the original paper in order to follow the arguments presented here. However, to make this presentation relatively self-contained a short overview of the Hunter and Latif research is presented outlining their research objectives, methods of analysis, and interpretation of results.     

The Media as spectacle: September 11 as soap opera

The concept of “spectacle” is most often associated with the writings of Guy Debord, but has also been developed and extended by later theorists, most particularly Jonathon Crary. We make use of their ideas on the “spectacle” which is the mass media to address two important sets of questions: how and why does the media find itself in a position to carry out the “immobilising” function ascribed to it by both Debord and Crary; and what are the techniques and mechanisms that facilitate this operation? We then exemplify the process of the media as spectacle with regard to coverage of recent political events such as the September 11 attacks and the so‐called “war on terror” and its relation to what we call the hysterical order of the soap opera.

The whole of life of those societies in which modern conditions of production prevail presents itself as an immense accumulation of spectacle. All that once was directly lived has become mere representation. (Debord )     

Social skills of adopted Chinese girls at home and in school: Parent and teacher ratings

This study examines adopted Chinese girls' social skills at home and in school as well as the effect of pre-adoption adversity on these skills. Parent ratings of 869 girls and teacher ratings of 611 of the 869 girls were obtained using the Social Skills Rating System for parent (SSRS-P) and teacher (SSRS-T) respectively. The girls were adopted on average at 15.6 months (SD = 13.9) and were in three age groups, including preschool, elementary school, and secondary school. Data on five indicators of pre-adoption adversity (i.e., signs/symptoms, delays at adoption, initial refusal/avoidance of adoptive mothers, crying/clinging behaviors, and age at adoption) were obtained from the same adoptive parents 2 years prior. Findings suggest that both parents and teachers rated the girls as either similar to or better than US norms on the SSRS. Parent–teacher agreement on SSRS subscales was significant but modest (rs = 0.12–0.25). Two indicators of pre-adoption adversity (i.e., delays at adoption and initial refusal/avoidance of adoptive mothers) predicted poorer social skills at home; two other indicators of pre-adoption adversity (i.e., signs/symptoms and age at adoption) predicted poorer social skills in school.     

Preliminary Goodness-of-Fit Tests for Normality do not Validate the One-Sample Student t

One of the most basic topics in many introductory statistical methods texts is inference for a population mean, μ. The primary tool for confidence intervals and tests is the Student t sampling distribution. Although the derivation requires independent identically distributed normal random variables with constant variance, σ², most authors reassure the readers about some robustness to the normality and constant variance assumptions. Some point out that if one is concerned about assumptions, one may statistically test these prior to reliance on the Student t. Most software packages provide optional test results for both (a) the Gaussian assumption and (b) homogeneity of variance. Many textbooks advise only informal graphical assessments, such as certain scatterplots for independence, others for constant variance, and normal quantile–quantile plots for the adequacy of the Gaussian model. We concur with this recommendation. As convincing evidence against formal tests of (a), such as the Shapiro–Wilk, we offer a simulation study of the tails of the resulting conditional sampling distributions of the Studentized mean. We analyze the results of systematically screening all samples from normal, uniform, exponential, and Cauchy populations. This pretest does not correct the erroneous significance levels and makes matters worse for the exponential. In practice, we conclude that graphical diagnostics are better than a formal pretest. Furthermore, rank or permutation methods are recommended for exact validity in the symmetric case.     

Marginal Correlation in Longitudinal Binary Data Based on Generalized Linear Mixed Models

This work aims at investigating marginal correlation within and between longitudinal data sequences. Useful and intuitive approximate expressions are derived based on generalized linear mixed models. Data from four double-blind randomized clinical trials are used to estimate the intra-class coefficient of reliability for a binary response. Additionally, the correlation between such a binary response and a continuous response is derived to evaluate the criterion validity of the binary response variable and the established continuous response variable.