Nearly all quantitative analyses in higher education draw from incomplete datasets-a common problem with no universal solution. In the first part of this paper, we explain why missing data matter and outline the advantages and disadvantages of six common methods for handling missing data. Next, we analyze real-world data from 5,905 students across…

This methodological note illustrates how a commonly used calculation of the Delta-p statistic is inappropriate for categorical independent variables, and this note provides users of logistic regression with a revised calculation of the Delta-p statistic that is more meaningful when studying the differences in the predicted probability of an…

Purpose: The use of e-learning is largely predicated upon the assumption that it can facilitate improvements in student learning and therefore can be more effective than conventional techniques. This assumption has been supported by some in the literature but has been questioned by a continuing body of contrary or indifferent evidence. The purpose…

Despite the widespread belief in a positive influence of research on education, the empirical evidence is lacking (Hattie and Marsh 1996). Several authors have questioned the appropriateness of the operationalisation of both aspects of the relation between teaching and research. This article takes a closer look at the research questions in…

This paper presents a model which illustrates the cyclical and interactive nature of the basic elements of the research design process. Rather than presenting each research design component in isolation, the model emphasizes their interrelationships. A brief discussion is presented on each of the following components of the model: (1) the "words"…

This paper examines some of the problems that arise when conducting multivariate analyses with incomplete data. The literature on the effectiveness of several missing data procedures (MDP) is summarized. The most widely used MDPs are: (1) listwise deletion; (2) pairwise deletion; (3) variable mean; (4) correlational methods. No MDP should be used…

This paper zeroes in on a subset of descriptors and predictors of undergraduate success, namely those which are neither cognitive measures (such as, high school grade point averages or aptitude test scores) nor personality test variables. The descriptors and predictors considered are broadly classed as: high school related; family and peer…

Social facilitation can be defined as the effect of an audience or coactors on performance. Research on social facilitation effects has produced some contradictory and confusing findings. Some studies have found that the presence of others enhances performance; other studies have found that the presence of an audience or coactors impairs…

Family socioeconomic status, ability, high school curriculum, scholarship receipt, age, race, marital status, enrollment status, employment status, and type of college attended were examined. The importance of these factors varied widely with year of college completed. Results demonstrated that these factors cannot be molded into a single equation…

A study of predictors of academic success among Nigerian students in two U.S. universities encountered the problem of too small a sample despite methodological precautions. It raised the question of whether it is possible to establish general placement recommendations applicable to foreign students in different institutions and from different…

An unsuccessful attempt to develop a standard battery of aptitude measures to distinguish practicing dentists is reinterpreted. A sample of 116 dentists showed few differences from the norm group on 22 potential predictors, with some differences counterintuitive. It is concluded that broad conceptualization of characteristics required to complete…

Examines the methodologies, objectives, and assumptions of existing national enrollment projection studies. (Author/MLF)

Problems with using stepwise analytic methods are discussed, and better alternatives are illustrated. To make the illustrations concrete, an actual data set, involving responses of 91 medical school admissions directors to 30 variables, was used. The 30 variables involved perceptions of barriers to medical school with respect to characteristics of…

Found low intercorrelations among social involvement, academic achievement, and occupational aspiration in a national sample of Black undergraduates attending predominantly White, State-supported universities. Suggests that future research on Black student success should explore factors internal to the person, institutional characteristics, and…

Reviews school desegregation literature to assess how well existing research provides information on school desegregating effects. Identifies disparities in methods and other characteristics among different studies and explores areas for improvement in the methodology and theory of future work. (Author/MJL)