The medical scientist is not concerned with the prevailing use of statistics, as described recently by Professor Ripley: "Statistics are not intended primarily to tell the truth. They are uttered for the purpose of proving a point." The scientist wants his statistics to prove something, and especially he wants them to be unuttered when they do not "primarily tell the truth."
The publication of statistics on cancer has occupied much space in the medical literature for many years, so that there is no lack of material for consideration, yet it seems not unfair to state at this time that there are few if any facts concerning cancer that can be established beyond dispute by the published statistical data. The statistics certainly fail to prove any points, even if not intentionally untruthful. No matter what the question may be, the statistics that have been published will be found to
WELLS HG. CANCER STATISTICS AS THEY APPEAR TO A PATHOLOGIST. JAMA. 1927;88(6):399–403. doi:10.1001/jama.1927.92680320033010a
* * SCHEDULED MAINTENANCE * *
The JAMA Network Sites will be conducting routine maintenance from 10/20/2017 through 10/21/2017. During this window access to content and authentication may be intermittently available. The JAMA Store will be completely unavailable during the maintenance window.