Just Say "No" -- to Junk Science

The Wall Street Journal (September 18, 1996)

Last month, the U.S. Department of Health and Human Services reported that drug use among U.S. teenagers doubled between 1992 and 1995 to about 11 percent. And we've all seen this report morph into a presidential election issue. But what's the real story?

The sample size was about 4,600 boys and girls. Because many of the individual age groups did not have enough individuals to produce meaningful results, they were pooled with other individual age groups.

Only the group of 14-to-15- year-old white boys from the West and North Central states were large enough to have statistically significant results. The conclusion that teen drug use had doubled was primarily based on the results from this group -- hardly a group representative of all teens.

Although teen heroin use rose from 0.3 percent in 1994 to 0.7 percent in 1995, the actual number of surveyed teens using heroin rose from 14 to 32. Not good, but certainly not a sufficient sample size on which to conclude an increase of epidemic proportions.

Used since 1971, the survey was substantially rewritten in 1994 because it was determined to be too vague to accurately track drug use. Some questions were added, some deleted, and some modified. Questions on marijuana use, for example, were reduced from 12 to 6.

The consequence of this was to adjust the responses of teens in the pre-1994 surveys to what they "would have said" had they been answering questions from the new survey. As acknowledged by the tabulators, these adjustments are as much art as science.

These adjustments also lowered the 1992-1993 estimates of teen drug use -- estimates that were then compared against 1995 estimates to reach a conclusion that teen drug use has doubled.

Material presented on this home page constitutes opinion of the author.

Copyright © 1996 Steven J. Milloy. All rights reserved. Site developed and hosted by WestLake Solutions, Inc.