The Household Encyclopedia as Magic Kit: Medieval Popular Interest in Pranks and Illusions*

Each of us has wished at some time to send in three box tops andget a magic kit that contains itchingpowder to give to our enemies, instructions for tricks designed to baffle our friends, and potions to make us more desirable. Exactly so in the Middle Ages. Bruno Roy's delightful essay on medieval do-it-yourself magic reveals the strong popular interest in practical jokes, illusions and tricks. People in the Middle Ages were playful and high-spirited, waiting to entertain and be entertained. The transformative power implicit i n the tricks played by jugglers or entertainers appealed to all classes of society; these same jugglers not only dealt in illusory tricks but often used various chemicalpreparations, giving a “scientific” cast to their pranks. That so many of these tricks were related to the household in terms of the joke itself or the ingredients used suggests the widespread popularity of magic kits, a popularity that today perhaps resides only with the children who save the box tops.     

Analysis of ordered probit model with surrogate response data and measurement error in covariates

ABSTRACT

Often in data arising out of epidemiologic studies, covariates are subject to measurement error. In addition ordinal responses may be misclassified into a category that does not reflect the true state of the respondents. The goal of the present work is to develop an ordered probit model that corrects for the classification errors in ordinal responses and/or measurement error in covariates. Maximum likelihood method of estimation is used. Simulation study reveals the effect of ignoring measurement error and/or classification errors on the estimates of the regression coefficients. The methodology developed is illustrated through a numerical example.     

The robustness of the likelihood ratio test,the nonparametric sum rank test,and f-ratio tests when the populations are from the negative binomial family

In this study, the robustness of power and significance level of several statistical testing methods was evaluated under the assumption that the test populations were from Poisson, negative binomial, or geometric distributions. The F-ratio test, with or without appropriate transformations, was shown to be both safe and robust for all distributions examined.     

Establishment of risk acceptance criteria using Life Quality Index: Application to the Indian context

The formulation of risk acceptance criteria may be coupled gainfully with a prediction of the of investment required to comply with it, an exercise which can benefit from the application of socioeconomic indicators. The Life Quality Index (LQI) is one such indicator which amalgamates human mortality and wealth creation and places an implicit economic value on reduction of life risk. While there have been a number of studies to demonstrate the application of LQI pertaining to various technological systems, the present work extends it to estimate the sectoral level investment needed to reduce public risks to within the As Low As Reasonably Predictable region for the chemical industry, with specific illustration of the methodology for India. The potential reduction in public individual risk is computed as a function of percentage increase in safety investment expressed as a fraction of the industry's contribution to the nation's GDP. In addition, using a new, more accurate expression, estimates of a related parameter, the implied cost of averting a fatality (ICAF), are obtained for a number of developed economies and India. The ICAF estimates show reasonable agreement with the value of statistical life (VSL), a parameter which is integral to cost-benefit analysis of safety and environmental regulations.     

On the structure of minimal winning coalitions in simple voting games

According to Coleman’s index of collective power, a decision rule that generates a larger number of winning coalitions imparts the collectivity a higher a priori power to act. By the virtue of the monotonicity conditions, a decision rule is totally characterized by the set of minimal winning coalitions. In this paper, we investigate the structure of the families of minimal winning coalitions corresponding to maximal and proper simple voting games (SVG). We show that if the proper and maximal SVG is swap robust and all the minimal winning coalitions are of the same size, then the SVG is a specific (up to an isomorphism) system. We also provide examples of proper SVGs to show that the number of winning coalitions is not monotone with respect to the intuitively appealing system parameters like the number of blockers, number of non-dummies or the size of the minimal blocking set.