Why carve up your continuous data?

Authors

  • Steven V. Owen,

    Corresponding author
    1. University of Texas Health Science Center at San Antonio, San Antonio, Texas
    • Department of Pediatrics, School of Medicine, and Center for Epidemiology & Biostatistics, University of Texas Health Science Center at San Antonio, San Antonio, TX.
    Search for more papers by this author
    • Professor.

  • Robin D. Froman

    1. University of Texas Health Science Center at San Antonio, San Antonio, Texas
    Search for more papers by this author
    • Professor and Dean.


Abstract

Continuous data are commonplace in social, biophysical, and health research. For various reasons, researchers often carve up data into ordered chunks. Such data carving results in less information being carried by the data, a reduction or spurious increase in statistical power, and resultant Type I or Type II errors. We give examples of data carving in selected nursing literature, and illustrate how unnecessary categorization can produce erroneous statistical results. Finally, we propose credible alternatives to data carving. © 2005 Wiley Periodicals, Inc. Res Nurs Health 28:496–503, 2005

Ancillary