Regression analysis is one of the most frequently used statistical techniques in institutional research. Principles of least squares, model building, residual analysis, influence statistics, and multi-collinearity are described and illustrated. (Author/MSE)

Path analysis and linear structural relations (LISREL) provide the institutional researcher with some extremely powerful statistical tools. However, they must be applied and interpreted carefully with a full understanding of their limitations and the statistical assumptions on which they are based. (Author)

This paper examines Longstreth's criticisms of Jensen's studies relating reaction-time to measures of intelligence and finds them unconvincing. While Longstreth raises some interesting questions, the authors found no evidence in the data for practice or order effects in a reaction-time paradigm. (BS)

This paper reports a Monte Carlo study of differences induced by different analysis choices over selected types of aptitude treatment interaction (ATI) data (nine combinations of three sample sizes and three population parameter effect sizes). Generally, ANOVA methods tended to overestimate smaller effect sizes and to underestimate larger effect…

The determinants of Scholastic Aptitude Test scores are estimated for 1982 in a regression analysis correcting for the proportion of students taking the test. Schooling variables and statewide graduation standards proved insignificant. Demographic variables (family size and education levels) proved significant and help explain SAT score decline in…

A social-learning model was tested for its ability to explain why adolescents drive under the influence of alcohol and ride with drinking drivers. The study demonstrates that if adolescent drinking and driving is to be prevented, careful attention must be prevented, careful attention must be paid to ways that it is learned and maintained.…

A method is suggested to incorporate instruction in the concept and the application of power considerations into an applied statistics course. This is based on designing one table usable for a wide range of the type of statistical tests usually introduced in such a course. (Author)

Advantages and disadvantages of three analytic methods are discussed. A hypothetical data set is employed to make the discussion complete. It is suggested that commonality analysis can be usefully employed in research studies in education, particularly when aptitute-treatment interaction studies are involved. (Author/LMO)

This study was designed to determine whether adjustments for the differential prediction observed among sex, racial/ethnic, or age subgroups in one freshman class at a college could be used to improve prediction accuracy for these subgroups in future freshman classes. (Author/LMO)

A universal criterion scale is applied to the direct estimation of validity for various groups of law school applicants and to the testing of the assumptions underlying the more familiar extrapolation methods. Data from American law schools are used to illustrate the procedures. (Author/BW)

A study of the use of logit analysis for examining an institution's retention of graduate students determined that when the independent variables are categorical and the dependent variables are dichotomous, logit analysis is more appropriate than discriminant analysis or multiple regression. (MSE)

The effect of administrative service as department chair on the scholarly careers of academic chemists is explored through an analysis of their publication and doctoral student productivity records over a two-decade period. The results indicate no significant difference in the productivity levels of the experimental and control groups. (Author/MLW)

Children were interviewed in two studies to compare the attribution patterns of those with and without learning problems. Normally achieving children in both studies followed the expected pattern of attributing success more internally and failure more externally. Learning disabled children did not follow the expected pattern for failure.…

Provides evidence that the Creek Nation's population increased during the late eighteenth century following a low point about 1750. Uses linear regression to project the Creek Indian population before the 1813-14 Creek War. Suggests that basic demographic factors may have played an important role in precipitating the Creek War. (SB)

This collection of activities is intended to enhance the teaching of college algebra through the use of modeling. The problems use real data and involve the representation and interpretation of the data. The concepts addressed include rates of change, linear and quadratic regression, and functions. The collection consists of eight problems, four…