EXPERIMENTAL AND QUASI-EXPERIMENTAL DESIGNS FOR RESEARCH

• NCJ Number: 51452
• Author(s): D T CAMPBELL; J C STANLEY
• Date Published: 1966
• Length: 93 pages
• Sponsoring Agency: Carnegie Corporation of New York
• Corporate Author: Rand McNally and Co
• Sale Source: Rand McNally and Co
• Language: English
• Country: United States of America
• Note: *This document is currently unavailable from NCJRS. REPRINTED FROM HANDBOOK OF RESEARCH ON TEACHING, N L GAGE (EDITOR)

Annotation

PREEXPERIMENTAL DESIGNS, TRUE EXPERIMENTAL DESIGNS, QUASI-EXPERIMENTAL DESIGNS, AND CORRELATIONAL AND EXPOST FACTO DESIGNS FOR RESEARCH ARE DESCRIBED AND DISCUSSED IN TERMS OF APPROPRIATE USES AND LIMITATIONS.

Abstract

PREEXPERIMENTAL DESIGNS ARE THOSE USED TO DRAW SOME CAUSAL INFERENCES ABOUT THE EFFECT OF AN INTERVENTION WHERE THE TOTAL ABSENCE OF CONTROL MAKES SCIENTIFIC CONCLUSIONS IMPOSSIBLE. THE THREE PREEXPERIMENTAL DESIGNS DISCUSSED ARE: (1) THE ONE-SHOT CASE STUDY; (2) THE ONE-GROUP PRETEST-POSTTEST DESIGN; AND (3) THE STATIC-GROUP COMPARISON. THE TRUE EXPERIMENTAL DESIGNS CONSIDERED ARE PRESENTED AS THOSE CURRENTLY RECOMMENDED IN THE METHODOLOGICAL LITERATURE. THEY ARE LABELED AS THE MOST STRONGLY RECOMMENDED DESIGNS OF THE PRESENTATION, ALTHOUGH CERTAIN THREATS TO THEIR VALIDITY ARE INDICATED. THE PRETEST-POSTTEST CONTROL GROUP DESIGN, THE SOLOMON FOUR-GROUP DESIGN, AND THE POSTTEST-ONLY CONTROL GROUP DESIGN ARE THE TRUE EXPERIMENTAL DESIGNS EXAMINED. QUASI-EXPERIMENTAL DESIGNS ARE RECOMMENDED FOR MANY NATURAL SETTINGS WHERE THE RESEARCHER LACKS FULL CONTROL OVER THE SCHEDULING OF EXPERIMENTAL STIMULI, SUCH THAT A TRUE EXPERIMENTAL DESIGN IS IMPOSSIBLE. THE QUASI-EXPERIMENTAL DESIGNS DISCUSSED INCLUDE: THE TIME-SERIES DESIGN; THE EQUIVALENT TIME-SAMPLES DESIGN; THE EQUIVALENT MATERIALS DESIGN; THE NONEQUIVALENT CONTROL GROUP DESIGN; COUNTERBALANCED DESIGNS; THE SEPARATE-SAMPLE PRETEST-POSTTEST DESIGN; THE SEPARATE-SAMPLE PRETEST-POSTTEST CONTROL GROUP DESIGN; THE MULTIPLE TIME-SERIES DESIGN; THE RECURRENT INSITUTIONAL CYCLE DESIGN; AND REGRESSION-DISCONTINUITY ANALYSIS. CORRELATIONAL AND EXPOST FACTO DESIGNS ARE DISCUSSED AS RESEARCH DESIGN WITH A CONTROL FACTOR NOT CHARACTERISTIC OF THE OTHER QUASI-EXPERIMENTAL DESIGNS, BUT INSUFFICIENT TO QUALIFY AS TRUE EXPERIMENTAL DESIGNS. TABLES ARE PRESENTED INDICATING THE EXTERNAL AND INTERNAL THREATS TO VALIDITY CHARACTERISTIC OF EACH DESIGN DISCUSSED. REFERENCES AND NAME AND SUBJECT INDEXES ARE ALSO INCLUDED. (RCB)