This article is only available in the PDF format. Download the PDF to view the article, as well as its associated figures and tables.
To the Editor:—
In The Journal Sept. 5, page 33, the authors of the article, "Pathological Reports for Mortality Statistics," have attempted to determine the effect of statistics on statistics. This may be of interest to statisticians, but it can hardly yield much useful information for medical scientists. The statistical method the authors used offset errors of omission by errors of commission, and vice versa. False-positive diagnoses were used to cancel out false-negative diagnoses, and the reverse. This does produce a low net change in the final statistics, but it does not give the percentage of error in death certificates. In other words, two wrongs do not make a right.Statistics should be used as a scientific tool with the objective of arriving at new concepts or new significant data from the raw data available. To compile statistics for the sake of statistics alone is not usually very rewarding. Pathologists'
Ziegler EE. MORTALITY STATISTICS. JAMA. 1960;172(2):190. doi:https://doi.org/10.1001/jama.1960.03020020070024
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: