Letters Section Editor: Stephen J. Lurie,
MD, PhD, Senior Editor.
To the Editor: In the study by Dr Aiken and
colleagues,1 it is puzzling that clinical
outcomes were significantly related to nurses' education and staffing but
not to to their years of experience. It is possible, however, that education
may be a proxy for certification, with which it could be confounded. To the
extent that this is true, education and experience may be collinear, and thus
the statistical analysis would be unlikely to find that both variables are
significantly related to the outcome. This is particularly a problem because
the unit of analysis was hospitals, not individual nurses or patients.
Burger D. Relationship Between Patient Mortality and Nurses' Level of Education. JAMA. 2004;291(11):1320-1323. doi:10.1001/jama.291.11.1321-b