Neil W. Henry

Conceptualization and Measurement in the Social Sciences.

Introduction Fundamental Measurement, Scaling, and Dimensionality Issues The Comparability of Measures Categorical Variables, Conceptualization, and Comparability Some Implications of Omitting Variables from Causal Explanations The Confounding of Variables and Oversimplified Interpretations Aggregation and Measurement Error in Macro-Analyses Appendix Assessing Comparability with Multiple Indicators

Jackknifing Measures of Association

Standard errors of estimates of gamma and Kendalls tau-b are estimated using Tukeys jackknife method and the results are compared with Kritzers application of asymptotic theory. The method is used to test the hypothesis that a pair of partial association coefficients are equal.

Thoughts on the Concept and Application of Statistical Models

Freedman’s arguments about the misuse of statistical models are sound, but I would go further. The mathematical statistician’s models are too often taken to be models for substantive theory rather than justifications for examining data in specific ways. Foundational problems relating to the validity of models of theory are the responsibility of the scientists who adopt them and cannot be resolved by statisticians independently of subject matter considerations.