Quantitative Intelligence Analysis by Edward Waltz

Author:Edward Waltz
Language: eng
Format: epub
ISBN: 9781442235878
Publisher: Rowman & Littlefield Publishers
Published: 2014-09-29T04:00:00+00:00

While data-modeling methods may choose from alternative forms of regression to improve the goodness of fit, alternative theoretical models may differ significantly as competing hypotheses to explain a system. Choosing among alternative hypotheses was discussed in the last chapter, and theoretical modelers must choose among theoretical models that best explain data. Besides goodness of fit measures, additional criteria used to evaluate theoretical models include:8

Model plausibility—Are the assumptions and behavioral theory reasonable and consistent? Are they credible as a hypothesis?

Explanatory adequacy—Is the theoretical explanation reasonable and consistent with accepted knowledge in the domain?

Interpretability—Does the model, its structure, components, and parameters make sense to a subject-matter expert in the domain, and are they understandable?

Descriptive adequacy—Does the model sufficiently describe the behavior of the observed data (this includes quantitative goodness of fit measures)?

Generalizability—This is a criterion that assesses the generality of the theory. Is the model sufficiently robust to produce accurate data for conditions that goes beyond the limited conditions (empirical data sets) used to test the model?

Parsimony (least complexity)—Does the model represent the system and its behavior the most succinct way and with the least assumptions?9

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.