attrition—in the context of research studies, refers to the gradual loss of study participants, some percentage of whom often drop out.
benefit-cost analysis—a method of economic analysis in which both costs and outcomes of an intervention are valued in monetary terms, permitting a direct comparison of the benefits produced by the intervention with its costs (also referred to as cost-benefit analysis).
contingent valuation analysis—a method of obtaining estimates of the worth of a social good or benefit in which people are asked how much they would pay for a particular outcome, given a particular hypothetical scenario.
cost-effectiveness analysis—a method of economic analysis in which outcomes of an intervention are measured in nonmonetary terms. The outcomes and costs are compared with both the outcomes (using the same outcome measures) and the costs for competing interventions, or with an established standard, to determine if the outcomes are achieved at reasonable monetary cost.
dependent variable—the factor(s) that change as a result of an experimental treatment or intervention, such as, for example, the academic skills of children who have participated in an early childhood education program.
discount rate—a factor used to estimate future costs or the value of future benefits at the current equivalent value, used with the goal of attempting to take into account likely changes in valuation, opportunity costs, and other factors.
economy of scale—advantages that accrue when a project is conducted on a larger scale than initially, which result from opportunities to use resources more efficiently and to reduce costs.
effect size—the magnitude of results (or effects on participants) of a particular treatment or intervention that is being studied.
independent variable—one of the characteristics of an experiment’s subjects that are considered in the study design, such as, for example, the age and gender of the participants in an early childhood program.
intent-to-treat—the group of study participants randomly selected to receive the intervention being studied.
multivariate regression model—a statistical procedure for examining experimentally the relationship among several variables. By making it possible to distinguish the impact on outcomes of one variable from the impacts of others, this analysis makes it possible to control for factors that may influence the results and obscure the effects the experiment is intended to identify.
opportunity cost—the value of alternatives not chosen, calculated as part of an analysis of the costs of the alternative that was chosen.
plug-in—estimates for particular costs that can be used to streamline cost analysis.
p-value—calculation of the probability that the data indicate a significant difference.
quasi-experimental design—an experiment designed to produce evidence of causality when randomized controlled trials are not possible, using alternative statistical procedures to compensate for nonrandom factors.
randomized controlled trial—an experiment in which the participants are assigned by chance either to receive the intervention or treatment being studied or not to receive it, so that the results can be compared across
statistical identical groups. When this is done with a large enough number of participants, any differences among them that might influence their response to the treatment will be distributed evenly.
regression adjustment—a statistical technique for reducing bias in an experiment that can occur when variables other then the one(s) being studied may affect the results in nonrandom ways.
regression discontinuity design—a quasi-experimental analysis that can be used in program evaluation when randomized assignment is not feasible. It is based on the assumption that individuals who fall just above or below a cut-off point on a particular scale are likely to be similar, so that this group can be treated as varying randomly.
selection bias—an unrecognized difference in the characteristics of the subjects of an experiment who do or do not receive the treatment, or who or do not benefit from it, that will affect the results.
shadow value/shadow price—the true value or cost of the results of a particular decision, as calculated when no market price is available; a dollar value attached to an opportunity cost.
worst-case bounds—a statistical analysis in which the outer limit assumptions for an experiment—both the best possible and worst possible outcomes in terms of the data supporting or not supporting the experimental hypothesis-—are examined. This analysis provides a way of assessing the significance of actual error that may occur in any experiment.