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:—
Reading the lead article "Response of Hyperlipoproteinemia to Cholestyramine Resin" by Fallon and Woods (204:1161, 1968) combined with participation on various drug committees compels me to take microphone in hand and dictate a response.This manuscript is an excellent example for elementary biostatistics courses to show beginning students how one can take a set of data which shows practically no drug effect and leave the unsuspecting reader with the implication that the drug was effective. In any study aimed at determining the efficacy of a drug on people with hyperlipoproteinemia the target population (the group of people about which conclusions are to be drawn) should be all people with hyperlipoproteinemia. A random sample is then selected and statistical tests may be used to draw inferences about all hyperlipoproteinemia cases on the basis of those observed in the sample. Thus, if one wishes to know whether there
Schor S. Hyperlipoproteinemia— A Difference of Opinion. JAMA. 1968;206(2):375-376. doi:10.1001/jama.1968.03150020091028