Search results

Many social scientists believe that dumping long lists of explanatory variables into linear regression, probit, logit, and other statistical equations will successfully "control" for the effects of auxiliary factors. Encouraged by convenient software and ever more powerful computing, researchers also believe that this conventional approach gives the true explanatory variables the best chance to emerge. The present paper argues that these beliefs are false, and that without intensive data analysis, linear regression models are likely to be inaccurate. Instead, a quite different and less mechanical research methodology is needed, one that integrates contemporary powerful statistical methods with deep substantive knowledge and classic data—analytic techniques of creative engagement with the data.

Two-step estimators for hierarchical models can be constructed even when neither stage is a conventional linear regression model. For example, the first stage might consist of probit models, or duration models, or event count models. The second stage might be a nonlinear regression specification. This note sketches some of the considerations that arise in ensuring that two-step estimators are consistent in such cases.

In the Symposium on Qualitative Comparative Analysis (QCA), the author critiques Charles Ragin's new methodological application Qualitative Comparative Analysis (QCA). The author addresses the scientists' three fundamental claims of quantitative methodology to argue that, although they agree on the claims of the case-study methodology & the inadequacies of quantitative research to represent social reality, Ragin's assertions of inadequate causal research is a primitive & gauche representation of actual quantitative research. Seawright's reduction of QCA to regression counters Ragin's arguments for the de-emphasis of statistical data by distinguishing the value of case-study analysis focusing on contextual & holistic effects that go back & forth between the model & the data in a rich dialogue. The author concludes that his argument for case studies verses regression does not advocate the abandonment of conventional statistical theory & techniques, but advocates determining how to combine quantitative & qualitative methodologies that surpass King, et al. References. J. Harwell

▪ Abstract  The past two decades have brought revolutionary change to the field of political methodology. Steady gains in theoretical sophistication have combined with explosive increases in computing power to produce a profusion of new estimators for applied political researchers. Attendance at the annual Summer Meeting of the Methodology Section has multiplied many times, and section membership is among the largest in APSA. All these are signs of success. Yet there are warning signs, too. This paper attempts to critically summarize current developments in the young field of political methodology. It focuses on recent generalizations of dichotomous-dependent-variable estimators such as logit and probit, arguing that even our best new work needs a firmer connection to credible models of human behavior and deeper foundations in reliable empirical generalizations.

The past two decades have brought revolutionary change to the field of political methodology. Steady gains in theoretical sophistication have combined with explosive increases in computing power to produce a profusion of new estimators for applied political researchers. Attendance at the annual Summer Meeting of the Methodology Section has multiplied many times, & section membership is among the largest in APSA. All these are signs of success. Yet there are warning signs, too. This paper attempts to critically summarize current developments in the young field of political methodology. It focuses on recent generalizations of dichotomous-dependent-variable estimators such as logit & probit, arguing that even our best new work needs a firmer connection to credible models of human behavior & deeper foundations in reliable empirical generalizations. 38 References. Adapted from the source document.

The Generalized Event Count (GEC) estimator (King 1989a) is a statistical model for event counts. Its great attraction is that it provides a general likelihood function for count data, regardless of whether the data come from a Poisson, binomial, or negative binomial distribution. In consequence, it has been used in several recent statistical studies of event counts in the social sciences.Underlying the GEC, however, are unorthodox substantive assumptions about how the event counts have been generated (Amato, this volume). This paper gives some simple examples in which the GEC logic is clearly visible, and it shows how failures of the implicit assumptions can lead to erroneous GEC coefficient estimates and standard errors.