Dichotomizing continuous predictors in multiple regression: a bad idea
Patrick J Royston, Douglas G. Altman, Willi Sauerbrei · Statistics in Medicine · 2005
In medical research, continuous variables are often converted into categorical variables by grouping values into two or more categories. We consider in detail issues pertaining to creating just two groups, a common approach in clinical research. We argue that the simplicity achieved is gained at a cost; dichotomization may create rather than avoid problems, notably a considerable loss of power and residual confounding. In addition, the use of a data-derived 'optimal' cutpoint leads to serious bias. We illustrate the impact of dichotomization of continuous predictor variables using as a detailed case study a randomized trial in primary biliary cirrhosis. Dichotomization of continuous data is unnecessary for statistical analysis and in particular should not be applied to explanatory variables in regression models.
Cited by 2,284 works. doi:10.1002/sim.2331
Authors
References
- Statistical Methods in Cancer Research
- Generalized Additive Models.
- Generalized Additive Models.
- Generalized Additive Models
- The Effectiveness of Adjustment by Subclassification in Removing Bias in Observational Studies
- Regression Using Fractional Polynomials of Continuous Covariates: Parsimonious Parametric Modelling
- Dangers of Using "Optimal" Cutpoints in the Evaluation of Prognostic Factors
- On the practice of dichotomization of quantitative variables.
- The Cost of Dichotomization
- Maximally Selected Chi Square Statistics