This Week In The Bmj

Over-matching can cause bias

BMJ 2002; 325 doi: (Published 10 August 2002) Cite this as: BMJ 2002;325:f

Over-matching in case-control studies can be a design fault and may lead to bias, say Marsh andcolleagues (p 327). They describe a case-control study of workers at a nuclear reprocessing plant in which over-matching obscured the relation between cumulative radiation dose and mortality from leukaemia.