On the Practice of Dichotomizing Quantitative Variables

Department of Psychology, Ohio State University, Columbus 43210-1222, USA.
Psychological Methods (Impact Factor: 4.45). 04/2002; 7(1):19-40. DOI: 10.1037/1082-989X.7.1.19
Source: PubMed


The authors examine the practice of dichotomization of quantitative measures, wherein relationships among variables are examined after 1 or more variables have been converted to dichotomous variables by splitting the sample at some point on the scale(s) of measurement. A common form of dichotomization is the median split, where the independent variable is split at the median to form high and low groups, which are then compared with respect to their means on the dependent variable. The consequences of dichotomization for measurement and statistical analyses are illustrated and discussed. The use of dichotomization in practice is described, and justifications that are offered for such usage are examined. The authors present the case that dichotomization is rarely defensible and often will yield misleading results.

Download full-text


Available from: Shaobo Zhang
  • Source
    • "Descriptive statistics, reliabilities, and correlations are displayed in Table 1. To test the hypotheses, motivations (i.e., self-determination and non-self-determination) were median split to create low and high groups (see MacCallum, Zhang,Preacher, & Rucker, 2002). The median score for selfdetermination was 4.83 and for non-self-determination was 4.67. "
    [Show abstract] [Hide abstract]
    ABSTRACT: We investigate the extent to which individuals' global motivation (self-determined and non-self-determined types) influences adjustment (anxiety, positive reappraisal) and engagement (intrinsic motivation, task performance) in reaction to changes to the level of work control available during a work simulation. Participants (N = 156) completed 2 trials of an inbox activity under conditions of low or high work control-with the ordering of these levels varied to create an increase, decrease, or no change in work control. In support of the hypotheses, results revealed that for more self-determined individuals, high work control led to the increased use of positive reappraisal. Follow-up moderated mediation analyses revealed that the increases in positive reappraisal observed for self-determined individuals in the conditions in which work control was high by Trial 2 consequently increased their intrinsic motivation toward the task. For more non-self-determined individuals, high work control (as well as changes in work control) led to elevated anxiety. Follow-up moderated mediation analyses revealed that the increases in anxiety observed for non-self-determined individuals in the high-to-high work control condition consequently reduced their task performance. It is concluded that adjustment to a demanding work task depends on a fit between individuals' global motivation and the work control available, which has consequences for engagement with demanding work. (PsycINFO Database Record
    Full-text · Article · Jan 2016 · Journal of Occupational Health Psychology
  • Source
    • "To begin with, the method capitalizes on chance by selecting the variables with the largest effect sizes. It also discards most of the information in those variables by reducing them to three categories, a problematic and potentially misleading practice (e.g., Altman & Royston, 2006; MacCallum, Zhang, Preacher, & Rucker, 2002). Most importantly, the method employs an unrealistically strict criterion for " internal consistency " coupled with a lax criterion for " substantial variability. "

    Full-text · Technical Report · Dec 2015
  • Source
    • "The authors concluded that the inflated error was likely the result of transforming a continuous scale of measurement into a binary model in which scores at or below a cut-point are considered to be indicative of a disorder. Problems associated with artificially dichotomizing continuous data have long been known (Cohen, 1983;MacCallum, Zhang, Preacher, & Rucker, 2002). However, it is important to note that multidisciplinary evaluation teams must make " yes/no " eligibility decisions according to IDEA (2004) and some degree of decision error will undoubtedly occur when cut-scores are used to diagnose SLD as a result. "
    [Show abstract] [Hide abstract]
    ABSTRACT: As a result of the upcoming Federal reauthorization of the Individuals With Disabilities Education Improvement Act (IDEA), practitioners and researchers have begun vigorously debating what constitutes evidence-based assessment for the identification of specific learning disability (SLD). This debate has resulted in strong support for a method that appraises an individual’s profile of cognitive test scores for the purposes of determining cognitive processing strengths and weaknesses, commonly referred to as patterns of strengths and weaknesses (PSW). Following the Fuchs and Deshler model, questions regarding the psychometric and conceptual integrity of the PSW model are addressed. Despite the strong claims made by many PSW proponents, the findings by this review demonstrate the need for additional information to determine whether PSW is a viable alternative to existing eligibility models and worthy for large scale adoption for SLD identification. Implications for public policy and future SLD research are also discussed.
    Full-text · Article · Dec 2015 · Learning Disability Quarterly
Show more