Statistics in medicine
-
Statistics in medicine · Apr 1983
Comparative StudyDeficiencies in clinical reports for registration of drugs.
A considerable number of the clinical reports which are presented to the Dutch Board for the Evaluation of Drugs, have deficiencies and/or shortcomings. A number of these, including loose description of the target population and sampling method, methodological flaws, incorrect treatment of withdrawals, confounding of patients and observations per patient, incomplete or incorrect description of the data and incorrect or inappropriate use of statistical tests, are discussed.
-
Statistics in medicine · Apr 1983
Comparative StudyAn analysis of survival differences between clinically and screen-detected cancer patients.
Survival differences between clinically and screen-detected cancer patients partly result from biases. Well known are lead-time, length bias and overdiagnosis. The survival of the clinically detected patients in the study group of the HIP breast cancer screening project is corrected for these biases. ⋯ This bias would not have been detected if the HIP study had not contained a randomized control group. A misleading and pessimistic conclusion on the effectiveness of breast cancer screening would thus have resulted. This conclusion reinforces the need for randomized studies.
-
The general standard of statistics in medical journals is poor. This paper considers the reasons for this with illustrations of the types of error that are common. ⋯ Suggestions are made about ways in which the standard of statistics may be improved. Particular emphasis is given to the necessity for medical journals to have proper statistical refereeing of submitted papers.