Search

Discusses the link between family structures and politics in the United States. `Family gap' in the 1992 presidential election, with parents of young children voting more Republicans; Partisan effects of family structure variables; Model of vote choice.

in this article, we consider the relationship between voter turnout and voter evaluations of the candidates. Using thermometer data and the 1976 voter validation study, we investigate the magnitude of indifference, alienation, and satisfaction effects. Overall, we find candidate-based abstention in 1976 to be minimal, suggesting that nonvoting in American presidential elections must be understood in terms of factors unrelated to panics' choices of nominees. [ABSTRACT FROM AUTHOR]

We outline several criteria for evaluating student statistical software programs and review four programs (SPSS 6.1, Mystat 2 1, ET 3.0, and StataQuest 2). Although all four programs perform adequately on many, if not all, criteria, we recommend SPSS for class use, given adequate resources. Mystat, SPSS, and StataQuest emphasize introductory data analysis techniques, whereas ET is geared toward (and excels at) more advanced statistical techniques. 1Keywords computing, data analysis, statistical software, classroom, student, statistics. [ABSTRACT FROM PUBLISHER]

The transfers of cabinet secretaries from one department to another are analyzed from the perspective of progressive ambition as an indicator of departmental prestige. Through the end of 1985, 59 transfers are found. Transfers are more frequent among the generalist inner cabinet departments. However, the frequency of transfers among the outer cabinet departments and between the inner and outer cabinet is sufficient to question the view of outer cabinet as specialists. This supports classifying the secretaries rather than the departments. The obtained prestige hierarchy of departments is similar to the order of succession to the presidency, but with some deviations. [ABSTRACT FROM PUBLISHER]

The first eigenvalue of a correlation matrix indicates the maximum amount of the variance of the variables which can be accounted for with a linear model by a single underlying factor. When all correlations are positive, this first eigenvalue is approximately a linear function of the average correlation among the variables. While that is not true when not all the correlations are positive, in the general case the first eigenvalue is approximately equal to a lower bound derived in the paper. That lower bound is based on the maximum average correlation over reversals of variables and over subsets of the variables. Regression tests show these linear approximations are very accurate. The first eigenvalue measures the primary cluster in the matrix, its number of variables and average correlation. [ABSTRACT FROM PUBLISHER]