A stochastic model for test-retest correlations

A simple stochastic model is formulated in order to determine the optimal time between the first test and the second test when the test-retest method of assessing reliability is used. A forgetting process and a change in true score process are postulated. The optimal time between tests is derived by maximizing the probability that the respondent has not remembered the response on the first test and has not had a change in true score. The resulting test-retest correlation is then found to be a linear function of the true reliability of the test, where the slope of this function is the key probability of not remembering and having no change in true score. Some numerical examples and suggestions for using the results in empirical studies are given. Specific recommendations are presented for improved design and analysis of intentions data.This research was made possible by a grant from the Center for Food Policy Research, Graduate School of Business, Columbia University, New York, New York, 10027.     

Predicting contraceptive behavior from attitudes: a comparison of within- versus across-subjects procedures

Within- versus across-subjects procedures for predicting behavior from attitudes were contrasted. Each procedure requires a comparison among attitudes in order to generate a prediction; the comparison is either among the same attitudes held by different people (across subjects) or among different attitudes held by the same person (within subject). It was hypothesized that the within-subject model provides a more adequate explanation of behavior from attitudinal constructs and, hence, more accurate prediction of behavior from attitudes than does the across-subjects model. To test this view, a sample of 349 married couples was administered a questionnaire containing measures of three attitudinal components--affect, cognition, and conation--toward each of four contraceptive methods--oral contraceptives, IUD, diaphragm, and condoms. Contraceptive behavior was assessed 1 year later. In support of the hypothesis, the within-subject predictions bore a significantly stronger relation to the behavioral criteria than did the across-subjects predictions. This effect was consistent for each of the three components of attitude, for the prediction of behavior and behavioral intention, for male and female respondents, and for a variety of contraceptive behaviors. In addition, both the within- and the across-subjects analyses demonstrated a clear rank ordering in the predictive validity of the three attitudinal components: Conation was a better predictor of behavior than was affect, which, in turn, was better than cognition.     

Control of CRT intensity via Apple II software

An inexpensive, easy-to-build device for the Apple II microprocessor is described. The modification permits software control of four levels of relative screen intensity (contrast) settings for any video monitor. The relationship of the technology to choice reaction time and perception research is briefly indicated. Principles governing operation of the modification are also discussed. Finally, a set of step-by-step instructions for building the device is provided.