Negative Consequences of Dichotomizing Continuous Predictor Variables

By J. Irwin, G. McClelland. 2003

465 citations recorded by the source corpus.

Subfields: Food Science, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/c73ce5181cba441ee2759cf2af1c54614ee853ce

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Food Science

In Statistics and Probability

Citations in the corpus

The effect of information and values on acceptability of reduced street lighting (2014, background): “This is mainly due to the potential loss of information about individual differences, potential loss of effect size, and decrease in power (cf. Irwin & McClelland, 2003; MacCallum, Zhang, Preacher, & Rucker, 2002).”
Investigating an alternate form of the cognitive reflection test (2016, background): “…correlations because our sample size was much smaller and because dichotomous measures have been criticized for sacrificing statistical power (e.g., Irwin & McClelland, 2001, 2003; Jaccard et al., 2006; MacCallum, Zhang, Preacher & Rucker, 2002) and creating spurious effects (Maxwell & Delaney,…”
“Can’t Stop, Won’t Stop”: Self-Control, Risky Lifestyles, and Repeat Victimization (2012, methodology): “We present analyses using a continuous measure of victimization since dichotomizing a continuous variable is typically only appropriate when the distribution of that variable is highly skewed (Irwin & McClelland, 2003; Streiner 2002).”
Dichotomizing continuous predictors in multiple regression: a bad idea (2006, background): “However, a similar liking for reducing data to two groups has been observed in other elds including psychology [6] and marketing [7].”
Just a Game? Unjustified Virtual Violence Produces Guilt in Empathetic Players (2010, methodology): “Following recommendations from related methodological literature (Bissonnette, Ickes, Berstein, & Knowles, 2006; Cohen, 1983; Irwin & McClelland, 2003), we favored a moderated regression over an Analysis of Variance (ANOVA) in order to avoid dichotomization of the empathy variable based on a median…”
Balanced versus Unbalanced Psychological Contracts in Temporary and Permanent Employment: Associations with Employee Attitudes (2009, unknown): “(1997), Koh and Yer (2000), Shore and Barksdale (1998), and De Cuyper et al.”
Witnessing Incivility Among Employees: Effects on Consumer Anger and Negative Inferences About Companies (2010, background): “Such an analysis has the advantage of retaining the original manipulations in testing the mediating impact of anger on the incivility-inductive inferences relationship (Irwin and McClelland 2001, 2003).”
The moderating role of social ties on entrepreneurs' depressed affect and withdrawal intentions in response to economic stress (2012, result): “Thus, we retained our original analysis, as it is more consistent with best practices across literatures regarding the disadvantages of arbitrary dichotomization of continua (see, e.g., Irwin & McClelland, 2002; MacCallum, Zhang, Preacher, & Rucker, 2002; Royston, Altman, & Sauerbrei, 2006).”
A researcher's guide to regression, discretization, and median splits of continuous variables (2015, methodology): “(2015), Irwin and McClelland (2003), Lemon (2009), Maxwell and Delaney ), Royston et al. (2006), Streiner (2002), Vargha et al. (1996) 09), Hunter and Schmidt (1990), Lagakos (1988), Morgan and Elashoff (1986) Callum et al. (2002) collinearity is absent should not be accepted as sufficient…”
Toward a More Nuanced Understanding of the Statistical Properties of a Median Split (2015, unknown): “He references Irwin and McClelland (2003) and Maxwell and Delaney (1993), and argues that median splits should never be used because doing so, “…can at times create spurious significant results if the independent variables are correlated.””