This paper provides logit estimates of the probability that students will cheat in a specific class using randomized response and direct question data in two logit models. The results predict that there are several indicators of the probability of cheating occurring in a class. These factors include both student and instructor characteristics. They suggest several steps that can be taken to reduce the incidence of cheating which are relatively inexpensive yet potentially very successful. Further, this study explores the usefulness of the randomized response survey technique in obtaining information about sensitive behavior. Estimates indicate that there are steps that instructors can take to reduce the amount of cheating that takes place in their classes. This study suggests that using multiple versions of each exam, non-multiple choice exams and reducing the weight of each exam score toward the final course grade are all measures which will lower the incidence of academic dishonesty in a class. By allowing a respondent more anonymity the randomized response method encourages more truthful answers than direct questioning. In both models studied here, randomized response yields higher estimates of cheating. The randomized response estimates also appear to be more consistent with previous estimates of cheating than do the direct question estimates. This lends confidence to the conclusion that when surveying respondents about potentially sensitive or threatening information the direct question method yields inaccurate predictions of actual behavior and randomized response is a more appropriate methodology. / Graduation date: 1994

This three-article dissertation aims to apply Bayesian data analysis to improve the methodologies that process effectiveness findings, cost information and subjective judgments with the purpose of providing clear, localized guidance for decision makers in educational resource allocation. The first article shows how to use a Bayesian hierarchical model to capture the uncertainty of the effectiveness-cost ratio. The uncertainty information produced by the model may inform the decision makers of the best- and worst-case scenarios of the program efficiency if it is replicated. The second article introduces Bayesian decision theory to address a subset of methodological barriers that hamper the influence of research on educational decision-making, including how to generalize or extrapolate effectiveness and cost information from the evaluation site(s) to a specific context, how to incorporate information from multiple sources, and how to aggregate multiple consequences of an intervention into one framework. The purpose of this article is to generate evidence of program comparison that applies to a specific school facing a decision problem by incorporating the decision-makers' subjective judgements and modeling their specific preference on multiple consequences. The third article proposes a randomized control trial to detect whether principals and practitioners update their beliefs on the effectiveness and cost of educational programs in the light of uncertainty information and localized evidence. Supplemented by a pilot qualitative study that guides decision makers to work on self-defined decision problems, the pilot testing of the experiment provides some evidence on the plausibility of using an experiment to identify the causal impact of research evidence on decision-making.