Making social sciences more scientific : the need for predictive models / Rein Taagepera.

Format:

Book

Author/Creator:

Taagepera, Rein.

Language:

English

Subjects (All):

Social sciences--Research.

Social sciences.

Social sciences--Fieldwork.

Social sciences--Methodology.

Sociology--Methodology.

Sociology.

Sociology--Research.

Physical Description:

1 online resource (271 pages)

Place of Publication:

Oxford ; New York : Oxford University Press, 2008.

Summary:

In his challenging new book Rein Taagepera argues that society needs more from social sciences than they have delivered. One reason for falling short is that social sciences have depended excessively on regression and other statistical approaches, neglecting logical model building. Science is not only about the empirical' What is?' but also very much about the conceptual' How should it be on logical grounds?' Statistical approaches are essentially descriptive, while quantitatively formulated logical models are predictive in an explanatory way. Why Social Sciences Are Not Scientific Enough contrasts the predominance of statistics in today's social sciences and predominance of quantitatively predictive logical models in physics. It shows how to construct predictive models and gives social science examples. Why Social Sciences Are Not Scientific Enough is useful to students who wish to learn the basics of the scientific method and to all those researchers who look for ways to do better social science.

Contents:

Why social sciences are not scientific enough

Can social science approaches find the law of gravitation?

How to construct predictive models: simplicity and nonabsurdity

Example of model building: electoral volatility

Physicists multiply, social scientists add

-even when it does not add up

All hypotheses are not created equal

Why most numbers published in social sciences are dead on arrival

Forbidden areas and anchor points

Geometric means and lognormal distributions

Example of interlocking models : party sizes and cabinet duration

Beyond constraint-based models : communication channels and growth rates

Why we should shift to symmetric regression

All indices are not created equal

From descriptive to predictive approaches

Recommendations for better regression

Converting from descriptive analysis to predictive models

Are electoral studies a rosetta stone for parts of social sciences?

Beyond regression : the need for predictive models.

Notes:

Includes bibliographical references (p. [241]-247) and index.

Description based on print version record.

Description based on publisher supplied metadata and other sources.

ISBN:

9780191560033

1-281-85317-8

9786611853174

0-19-156003-0

0-19-171592-1

OCLC:

302340141