Search

Quantitative sociology has grown by burrowing methods from the experimental sciences even though. for the most part, our data are observational. Where the procedures of experimental science can he applied, data analysis can exploit simplifying assumptions because good experimental design removes correlations among independent variables that exist nature, outside the experiment, as well as effects or unmeasured variables. Where the science is of necessity, observational, these simplifications can not be guaranteed and, as a result, the analyses reached through by use of some of the standard "workhorse" techniques of the statistical repertoire may not be valid and conclusions reached by the application of these techniques are in doubt, This paper explores an alternative framework for data analysis in quantitative sociology, bypassing the statistics associated with experimental methods. Specifically, it explores generalizations of the method and quantitative theory used by physical surveyors, generalizing them to the needs of observational data. Application of this framework to text, including editorials and free answers to questionnaires as well as application to (social) survey data, supports their its for these purposes and the cartographic methods suggest that micro theories embedded in these methods reduce the load of a priori assumptions "normally" required for both text analysis and survey analysis. The applications suggest a research path applicable to "ordinary" sociological variables, including education, income, occupation, and gender. that shifts the burden of argument away from variance explained criteria and toward an integration of theory and method, guided by principles of parsimony and consistency. [ABSTRACT FROM AUTHOR]

Various theoretical concerns often require researchers to answer questions of the form does co-member- ship in a group predict other ties between those individuals. Data appropriate for answering such a question often is referred to as network data Network data exhibits row-column dependencies that often invalidate traditional statistical methods for doing group comparisons such as analysis of variance and the Kruskal-Wallis Procedure. Because of the positive dependence within rows/columns the significance probabilities of such traditional methods may be exaggerated. This paper uses restricted-randomization to develop exact permutation tests for network data where co-membership in coups can be specified a priori. This enables the nonparametric estimation of the significance of standard statistics for group- difference tests and ordered-alternative tests where the group orderings have been prespecified. These methods are demonstrated by examining three different data sets: Sampson's Monastery data, Carley's Tutor Selection data, and Humana's Human Rights data. [ABSTRACT FROM AUTHOR]

The models of Taylor and Russell (1939) or Abrahams, Alf and Wolfe (1971) can be used to predict structure in a selected group provided there are only two groups and the correlation between predictor and group membership variable is known. They are usually used in applied psychology to predict the proportion of successful candidates in a selected group, but they can also be used to predict any dichotomous structure (e.g., sex structure). This paper gives two models for the generalized case of m-groups. The first model assumes that the Ns, means and standard deviations of the normally distributed predictor in m-groups, are known, i.e., 3m parameters. The second model assumes that the distribution of the predictor and group membership variable is bivariate normal (and the regression is, therefore, linear), and that the total mean, standard deviation and correlation are known, i.e., 3+m parameters. When tested with a practical example whose distributions strongly violate the assumption of normality, the models seem to be quite robust. [ABSTRACT FROM AUTHOR]

This paper develops a method for calculating the tendency towards transitivity while keeping constant the number of choices which are made by each member of the group (U[SUBN](X[SUBi+]) distribution) or the number of times each member is chosen (UN(X[SUB+J]) distribution). Such a calculation was suggested by Wasserman, who used the triad census developed by Holland and Leinhardt. This work presents a simpler way. This is accomplished by developing a path census and two supplementary functions. Our technique can be used to calculate the mean and variance of other quantities, such as mutuality and intransitivity. In order to enable researchers to use this technique, we present explicitly the mean and variance of the path census. [ABSTRACT FROM AUTHOR]