Multilevel modeling (MLM), also referred to as hierarchical linear modeling (HLM) or mixed models, provides a powerful analytical framework through which to study colleges and universities and their impact on students. Due to the natural hierarchical structure of data obtained from students or faculty in colleges and universities, MLM offers many…

"Going Further" presents a roadmap to the works of the ACCLAIM (Appalachian Collaborative Center for Learning, Assessment, and Instruction in Mathematics) Research Initiative, the research effort of one the Centers for Learning and Teaching (CLTs) created with a grant (2001-2005) from the National Science Foundation. The Center began…

In most multi-campus studies of college impact that have been conducted over the past four decades, investigators have relied on ordinary least squares (OLS) regression as the analytic method of choice. Recently, however, some investigators have advocated the use of Hierarchical Linear Modeling (HLM), a method specifically designed for analyses…

Research on the validity of psychosocial factors (PSFs) and other noncognitive predictors of college outcomes has largely ignored the practical benefits implied by the validity. We summarize evidence of the validity of PSF measures as predictors of college outcomes and then explain how this validity directly translates into improved identification…

Statistical analysis must be approached rationally and with intent. The application of statistical analysis under the guise of the classical experimental paradigm when the underlying statistical assumptions are not met, as is often the case in institutional research, is neither efficient nor likely to produce useful results. (Author/MSE)

A systematic exploratory technique used primarily in the commercial sector to successfully identify market segments can be applied by an educational institution to a group of inquirers to learn more about its image and distinguish between distinct market subgroups that merit differentiated communication and program development strategies. (MSE)

Even the application of such mainstays of the institutional researcher's statistical tool kit as the t test and ANOVA is not always as straightforward as it seems. The researcher must first check to see that the underlying methodological and statistical assumptions are being met. (Author)

The study proposes using path analysis and residual plotting as methods supporting environmental scanning in strategic planning for higher education institutions. Path models of three levels of independent variables are developed. Dependent variables measuring applications and enrollments at Virginia Polytechnic Institute and State University are…

The data collection matrix makes possible the integration of functional area data from numerous assessment sources and presentation of the information in a unified composite report. This model is discussed in relation to the various assessment instruments and the evaluation of functional areas and programs in colleges and universities. (Author/MSE)

The ultimate goal of the institutional researcher is not always to test a research hypothesis, but more often simply to find an appropriate model to gain an understanding of the underlying characteristics and interrelationships of the data. Exploratory data analysis provides a means of accomplishing this. (Author)

This article suggests that the choice by institutional researchers to use qualitative or quantitative research is often dictated by time, money, resources, and staff and not necessarily with an understanding of the underlying philosophical assumptions structuring beliefs about methodology, knowledge, and reality. These underlying assumptions are…

An examination was conducted of the control chart as a quality improvement statistical method often used by Total Quality Management (TQM) practitioners in higher education. The examination used an example based on actual requests for information gathered for the Director of Human Resources at a medical center at a midwestern university. The…

The data collected in higher education research are not always quantitative or continuous. Statistical methods using the log-linear model provide the institutional researcher with a powerful set of tools for addressing research questions when data are categorical. (Author/MSE)

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)