A Bayesian method for classification and discrimination

We discuss Bayesian analyses of traditional normal-mixture models for classification and discrimination. The development involves application of an iterative resampling approach to Monte Carlo inference, commonly called Gibbs sampling, and demonstrates routine application. We stress the benefits of exact analyses over traditional classification and discrimination techniques, including the ease with which such analyses may be performed in a quite general setting, with possibly several normal-mixture components having different covariance matrices, the computation of exact posterior classification probabilities for observed data and for future cases to be classified, and posterior distributions for these probabilities that allow for assessment of second-level uncertainties in classification.     

Efe fathers: one among many? A comparison of forager children's involvement with fathers and other males

The study reported describes Efe (pygmy) forager one-, two-, and three-year-olds' involvement with males. The Efe of northeastern Zaïre were chosen because their social organization allows us to examine hypotheses based on studies in Western, technologically complex societies about the distinctive role fathers play in the lives of their young children. Behavioral observations of Efe children's day-to-day activities with fathers, men and boys were recorded using a focal subject sampling technique (Altmann, 1974). Two behavioral measures were created to capture the extent to which males were involved with children: Social engagement describes males' involvement with children and social attention describes eavesdropping by children on males' everyday activities. Eight one-year-olds, 7 two-year-olds and 8 three-year-olds were each observed for six, one-hour observation sessions that were distributed evenly over the daylight hours. Data were analyzed using the traditional measure of involvement (e.g., adult males) and using a newly developed measure of the involvement of the average individual (e.g., average adult mate). Comparisons at each of the ages showed that fathers were consistently like other men in the extent to which children participated in social activities with them and watched their activities. Only fathers' level of social engagement declined significantly as children grew older. Boys' role relative to other males became increasingly distinctive as children aged. The findings suggest that Efe fathers may not be unique in the same sense assumed by Western study ideals, and raise questions about the special status given to fathers in Western theory and data. The patterning of mate involvement with children is discussed in terms of Efe community life, and in terms of Efe children's developing understanding of their relationship with fathers and other males.     

Lines through the origin—is NO INT the answer?

The fitting of a straight line that must pass through (0, 0) is a frequently encountered application of linear regression. Many computer packages provide a least-squares option sometimes identified as NO INT, or even NOINT, or as ‘suppressing the intercept’. Often these procedures are invalid or do not correspond to the most suitable model. This paper questions the least-squares-line approach and suggests some alternatives. Two measures are proposed for comparing the fit of alternative models.     

State of the unions: Assessment by elite American labor leaders

One hundred and sixty-four elite union leaders in the United States completed a survey to assess the condition of the American labor movement and the factors affecting it. The respondents included high-level international union and state federation officers, central labor presidents, and 58 shop stewards. This study compares the responses of these labor officials and finds that they have similar, negative assessments of the condition of the American labor movement. The study also finds that these leaders agree that the most important factors affecting the labor movement are collective bargaining rights, union leadership, union member solidarity, and the NLRB.     

Fast retraction of evidence in a probabilistic expert system

We present and justify a propagation algorithm to facilitate the simultaneous calculation, for every node in a probabilistic exper system of the distribution of the associated random quantity, conditional on all the evidence obtained about the remaining nodes.     

Estimation of parameters for rounded data from non-normal distributions

This paper is concerned with how standard estimation procedures perform in terms of eficiency for non-normal rounded data. Previous research has shown that the loss in eficiency due to rounding normal data is small. However, evidence from the non-normal distribution considered in this paper suggests, if rounding is coarse or the distribution is very skewed the loss in efficiency due to rounding can be considerable.