On the practice of dichotomization of quantitative variables.

Abstract

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.We consider here some simple statistical procedures for studying relationships of one or more independent variables to one dependent variable, where all variables are quantitative in nature and are measured on meaningful numerical scales. Such measures are often referred to as individual-differences measures, meaning that observed values of such measures are interpretable as reflecting individual differences on the attribute of interest. It is of course straightforward to analyze such data using correlational methods. In the case of a single independent variable, one can use simple linear regression and/or obtain a simple correlation coefficient. In the case of multiple independent variables, one can use multiple regression, possibly including interaction terms. Such methods are routinely used in practice.However, another approach to analysis of such data is also rather widely used. Considering the case of one independent variable, many investigators begin by converting that variable into a dichotomous variable by splitting the scale at some point and designating individuals above and below that point as defining two separate groups. One common approach is to split the scale at the sample median, thereby defining high and low groups on the variable in question; this approach is referred to as a median split. Alternatively, the scale may be split at some other point based on the data (e.g., 1 standard deviation above the mean) or at a fixed point on the scale designated a priori. Researchers may dichotomize independent variables for many reasons-for example, because they believe there exist distinct groups of individuals or because they believe analyses or presentation of results will be simplified. After such dichotomization, the independent variable is treated as a categorical variable and statistical tests then are carried out to determine whether there is a significant difference in the mean of the dependent variable for the two groups represented by the dichotomized independent variable. When there are two independent variables, researchers often dichotomize both and then analyze effects on the dependent variable using analysis of variance (ANOVA).There is a considerable methodological literature exam...

The behavioral inhibition system and the verbal information pathway to children's fears.

“…when the degrees of freedom for the effect are 1). BIS was treated as a continuous variable throughout because of the statistical problems in creating artificial categories from continuous variables (see MacCallum, Zhang, Preacher & Rucker, 2002).…”

Modeling the relationship between circulating tumour cells number and prognosis of metastatic breast cancer

“…In addition, in the absence of a priori information, ''optimal'' cutpoints are usually obtained by trying many thresholds and choosing the one which, to some extent, gives the most satisfactory result, for example, choosing the value which minimizes the P-value of the Log-rank test [13]. The disadvantages of this approach, related to multiple testing and generalizability of the results, have been abundantly discussed in the literature [15,16,[21][22][23]. Alternative strategies to dichotomization, in which continuous predictors are kept continuous and trends are investigated, have been proposed: among these, the most commonly used are fractional polynomials and spline regression models [23][24][25][26][27][28].…”

Use of the Extreme Groups Approach: A Critical Reexamination and New Recommendations.

“…For additional problems associated with dichotomization of continuous scores see studies by J. Cohen (1983), Irwin andMcClelland (2003), andMacCallum, Zhang, Preacher, andRucker (2002).…”

“…If the two variables subjected to EGA are correlated in the population, dichotomizing both variables results in a pseudoorthogonal design, as the two independent variables will appear to be uncorrelated (orthogonal) in the sample even if they are actually correlated in the population. In such designs, effect sizes (standardized and unstandardized) and p values can be severely biased (Humphreys & Dachler, 1969a, 1969bMacCallum et al, 2002). Campbell and Kenny (1999) noted that problems associated with the regression to the mean phenomenon are especially likely to occur with extreme groups.…”