Although researchers have documented that some data make larger contributions than others to predictions made with least squares models, it is relatively unknown that some data actually make no contribution to the predictions produced by these models. This article explores such noncontributory data. (Contains 1 table and 2 figures.)

The authors propose a general modeling framework called the general monotone model (GeMM), which allows one to model psychological phenomena that manifest as nonlinear relations in behavior data without the need for making (overly) precise assumptions about functional form. Using both simulated and real data, the authors illustrate that GeMM…

Multilevel modeling provides several advantages over traditional ordinary least squares regression analysis; however, reporting results to stakeholders can be challenging. This article suggests some strategies for presenting complex, multilevel data and statistical results to institutional and higher education decision makers. The article is…

Discusses the squared cross-validity coefficient as a measure of the predictive validity of a sample linear prediction equation. Presents sample-size tables that should result in very small discrepancies between the squared multiple correlation and the squared cross-validity correction, thus facilitating the selection of sample size for predictive…

Discusses the use of linear regression methods to extrapolate experimental data. Describes the method of averages and two weighted least squares. Calculates the error range of each method. (YP)