skip navigation

PUBLICATIONS

Register for Latest Research

Stay Informed
Register with NCJRS to receive NCJRS's biweekly e-newsletter JUSTINFO and additional periodic emails from NCJRS and the NCJRS federal sponsors that highlight the latest research published or sponsored by the Office of Justice Programs.

NCJRS Abstract

The document referenced below is part of the NCJRS Virtual Library collection. To conduct further searches of the collection, visit the Virtual Library. See the Obtain Documents page for direction on how to access resources online, via mail, through interlibrary loans, or in a local library.

 

NCJ Number: 64394 Add to Shopping cart Find in a Library
Title: NONEXPERIMENTAL EVALUATION RESEARCH - CONTRIBUTIONS OF CAUSAL MODELING (FROM IMPROVING EVALUATIONS, 1979, BY LOIS-ELLIN DATTA AND ROBERT PERLOFF - SEE NCJ-64392)
Author(s): P M BENTLER; A WOODWARD
Corporate Author: Sage Publications, Inc
United States of America
Date Published: 1979
Page Count: 32
Sponsoring Agency: Sage Publications, Inc
Thousand Oaks, CA 91320
US Dept of Health, Education, and Welfare
Rockville, MD 20852
Grant Number: DA01070
Type: Program/Project Evaluation
Format: Document
Language: English
Country: United States of America
Annotation: THIS RESEARCH PAPER ON EVALUATION DESCRIBES AN APPROACH TO CAUSAL MODELING IN WHICH PROCESS DATA ARE USED TO SELECT THE MOST PLAUSIBLE OF ALTERNATIVE INTERPRETATIONS OF CHANGES ASSOCIATED WITH AN INTERVENTION.
Abstract: ALTHOUGH THE MERITS OF VARIOUS QUANTITATIVE TECHNIQUES FOR EVALUATION RESEARCH CAN BE DEBATED, CAUSAL MODELING, WHEN INTEGRATED INTO A CONCEPTUAL SCHEME INVOLVING CONSTRUCT VALIDATION, REPRESENTS A USEFUL TECHNIQUE FOR THIS FIELD. A CAUSAL MODEL CAN BE DEFINED AS THE REPRESENTATION OF A SUBSTANTIVE THEORY BY A STRUCTURAL MODEL AND A MEASUREMENT MODEL. THE STRUCTURAL MODEL REPRESENTS THE INTERRELATIONS AMONG CONSTRUCTORS THROUGH MATHEMATICAL EQUATIONS, WHEREAS THE MEASUREMENT MODEL REPRESENTS THE INTERRELATIONS BETWEEN CONSTRUCTS AND MANIFEST VARIABLES THROUGH MATHEMATICAL EQUATIONS. ONE MAJOR CONTRIBUTION OF CAUSAL MODELING METHODS MAY BE THE ATTRIBUTION OF CAUSE IN NONEXPERIMENTAL SETTINGS. WHILE SUCH CAUSAL EXPLANATION IS MOST GENERALLY ASSOCIATED WITH CLASSICAL EXPERIMENTAL METHODS INVOLVING RANDOMIZATION, THE OCCURRENCE OF ETHICAL, LEGAL, AND PRACTICAL CIRCUMSTANCES MAKE CLASSICAL METHODS DIFFICULT IN SOME AREAS OF EVALUATION RESEARCH. AN OVERVIEW OF RECENTLY DEVELOPED MODELS THAT CAN BE APPLIED TO THE PROBLEM OF MAKING CAUSAL INFERENCES IN NONEXPERIMENTAL DATA IS PRESENTED, AND TWO BROAD CATEGORIES OF MODELS DISCUSSED: (1) THOSE APPROPRIATE FOR QUANTITATIVE DATA AND (2) THOSE DESIGNED FOR QUALITATIVE DATA. DESCRIPTIONS ARE GIVEN OF SEVERAL CAUSAL MODELS FOR QUANTITATIVE DATA INCLUDING CONFIRMATORY FACTOR ANALYSIS, THREE-MODE FACTOR ANALYSIS, FACTOR ANALYSIS WITH STRUCTURED MEANS, STRUCTURAL EQUATION MODELS, AND ANALYSIS OF COVARIANCE WITH MEASUREMENT MODEL. CAUSAL MODELS FOR QUALITATIVE DATA, WHICH REQUIRE COMPUTER ASSISTANCE, ARE DISCUSSED INCLUDING THE FACTOR ANALYSIS MODEL, DICHOTOMOUS REGRESSION MODEL, STRUCTURAL EQUATION MODEL, AND THE LOG-LINEAR MODEL. A CASE STUDY APPLIES STRUCTURAL EQUATION MODELS TO THE PROBLEM OF EVALUATING THE EFFECT OF A SUMMER HEAD START PROGRAM ON FIRST GRADERS' COGNITIVE ABILITY. TABULAR DATA AND A LIST OF REFERENCES ACCOMPANY THE PAPER. (MJW)
Index Term(s): Evaluation; Evaluation techniques; Evaluative research; Program evaluation
To cite this abstract, use the following link:
http://www.ncjrs.gov/App/publications/abstract.aspx?ID=64394

*A link to the full-text document is provided whenever possible. For documents not available online, a link to the publisher's website is provided. Tell us how you use the NCJRS Library and Abstracts Database - send us your feedback.