Factors relevant to the validity of experiments in social settings.

Abstract

This chapter attempts a specification of the major categories of extraneous variables and employs these categories in evaluating the validity of standard designs for experimentation in the social sciences. The extraneous variables affecting internal validity are introduced in the process of analyzing three pre-experimental designs. In the subsequent evaluation of the applicability of three true experimental designs, factors leading to external invalidity are introduced. In analyzing the extraneous variables which experimental designs for social settings seek to control, seven categories have been distinguished: history, maturation, testing, instrument decay, regression, selection, and mortality. In general, the simple or main effects of these variables jeopardize the internal validity of the experiment and are adequately controlled in standard experimental designs. The interactive effects of these variables and of experimental arrangements affect the external validity of generalizability of experimental results. Standard experimental designs vary in their susceptibility to these interactive effects.