A Guide for selecting statistical techniques for analyzing social science data

fully, skipping nothing, will be richly rewarded. The message he conveys is an important one, especially for political scientists seeking a bridge to economics and for economists seeking a bridge to politics. Political theorists will be most comfortable with Usher's reasoning and find familiar material provocatively presented in a different light, especially on the relationship between property, income, democracy, constitutional law and theory, and social justice. Of special interest should be the application of his streamlined equitable distribution model to capitalism and socialism and his comparative analysis of the functional relationship between these two systems and democracy. Usher relies on a simple hypothetical voting model "to demonstrate that government by majority rule, though necessary for the preservation of what we think of as a good society, is unstable and unworkable unless the range of issu»s to be settled by majority rule is severely circumscribed" (p. 10). The simplified model is then applied to more "complex and realistic" systems. Following a severe, some would argue too severe, critique of socialism's shortcomings as a means to achieve democracy, Usher comes down on the side of capitalism which "does contain a system of equity which, though far from complete or perfect, is probably sufficient to permit democracy to continue" (p. 10). In the concluding section, the thesis is tested against concrete policy problems in light of three interacting criteria: efficiency, equality, and equity. Usher devotes too much effort to convince us that "democracy is not inevitable, that it rests on an economic foundation and that it may be strengthened or destroyed altogether through the choice of economic policy" (p. 141). Few political scientists, and one must hope no political economist, should have difficulty with that thesis. One might fault Usher on other counts. Capitalism, he warns, is in constant danger from within, failure of its equity-assurance mechanism, and from without, "the legislature," i.e. government, assuming functions in the economy and thereby impeding proper working of the equity assurance mechanism. No attention is paid by Usher to the dangers threatening the capitalist mechanism from the capitalist manipulators. Put differently, Usher's capitalism where greed is curbed appears to be a system without capitalists.

[1]  Ulf Olsson,et al.  Measuring Correlation in Ordered Two-Way Contingency Tables , 1980 .

[2]  J. Kruskal,et al.  Candelinc: A general approach to multidimensional analysis of many-way arrays with linear constraints on parameters , 1980 .

[3]  Michael T. Hannan,et al.  METHODS FOR TEMPORAL ANALYSIS , 1979 .

[4]  N. Wermuth,et al.  A Simulation Study of Alternatives to Ordinary Least Squares , 1977 .

[5]  G G Koch,et al.  A computer program for the generalized chi-square analysis of categorical data using weighted least squares (GENCAT). , 1976, Computer programs in biomedicine.

[6]  Bradley R. Hertel Minimizing Error Variance Introduced By Missing Data Routines in Survey Analysis , 1976 .

[7]  H. M. Blalock,et al.  Can We Find a Genuine Ordinal Slope Analogue , 1976 .

[8]  Morton B. Brown,et al.  The Small Sample Behavior of Some Statistics Which Test the Equality of Several Means , 1974 .

[9]  R. Light Measures of response agreement for qualitative data: Some generalizations and alternatives. , 1971 .

[10]  K. Krippendorff Bivariate Agreement Coefficients for Reliability of Data , 1970 .

[11]  G. Glass,et al.  Measures of Association in Comparative Experiments: Their Development and Interpretation , 1969 .

[12]  L. A. Goodman,et al.  Measures of Association for Cross Classifications III: Approximate Sampling Theory , 1963 .

[13]  W. S. Robinson The statistical measurement of agreement. , 1957 .

[14]  A. Bowker,et al.  A test for symmetry in contingency tables. , 1948, Journal of the American Statistical Association.