Synopses & Reviews
Synopsis
Where an assumption of unidirectionality in causal effects is unrealistic, ′recursive′ models cannot be used, and more complex ′nonrecursive′ models are necessary. Unfortunately, many nonrecursive models (unlike recursive models) are ′unidentified′, which makes meaningful parameter estimation impossible. Even when they are identified, it would be inappropriate to use OLS regression techniques (appropriate for recursive models) for the purpose of estimation. The concept of identification, and the factors that lead to it are explained; and various tests for determination are provided. Illustrations from a variety of social science disciplines are used throughout the book.
Synopsis
Many substantive research problems in the social sciences (for which the underlying assumption of unidirectionality in causal effects is unrealistic) do not lend themselves to 'recursive' models. In such cases, more complex 'nonrecursive' models are necessary.
The great difficulty with nonrecursive models is that (unlike recursive models) many are 'unidentified', making meaningful parameter estimation impossible. Even when they are identified, it would be inappropriate to use OLS regression techniques (appropriate for recursive models) for the purpose of parameter estimation.
The author defines the concept of identification and explains what 'goes wrong' with some nonrecursive models to make them nonidentified. He provides various tests which can be used to determine whether a nonrecursive model is identified, and reviews the most common techniques for estimating the parameters of an identified model.
Illustrations from a variety of social science disciplines are used throughout the book. Familiarity with Causal Analysis (Asher, vol 3) is necessary for a proper understanding of this book.