AND CAUSAL ANALYSIS
The initial chapters of this book focused on considerations relevant to the development and use of experimental designs. In these designs, participants' exposure to a treatment or manipulation is totally controlled by the researcher; the major purpose of such control is to reduce or eliminate the plausibility of alternative explanations of change in the dependent variable. In research of this type, there is a clear distinction between the independent (or causal) variable, which is controlled or manipulated by the experimenter, and the dependent variable, which is allowed to vary freely. In many areas of research in social science, however, experimental control over important variables is either impossible, unethical, or, at the very least, completely impractical.
The experimenter studying the effects of organismic characteristics such as sex, age, or height, or such relatively enduring personal attributes as religious affiliation, for example, is in no position to manipulate these variables. People arrive at the laboratory with predetermined levels of these characteristics, and these features of the individual are beyond the immediate influence of the experimenter. Similarly, if participants' levels of a relevant variable are determined by their responses on a measuring instrument, such as a scale of authoritarianism, extraversion, or need for cognition, the experimenter again is not in a position to manipulate the initial level of this variable. It is a feature of the participants themselves. In most situations of this type, the experimenter can no longer determine whether variations in the independent variable cause changes in the dependent variable; rather, the research question becomes whether the variables under investigation are in some way related to one another. The type of analysis thus becomes correlational, rather than causal.1
In most common correlational approaches, the variables are allowed to vary freely, and the researcher records the extent of their covariation, that is, the extent to which____________________