Stephen J.LurieMD, PhD, Senior EditorIndividualAuthorJody W.ZylkeMD, Contributing EditorIndividualAuthor
To the Editor: In their article on the association between cigarette smoking and anxiety disorders, Dr Johnson and colleagues1 wrote, "A power analysis indicated that there was sufficient statistical power to detect an association of modest effect size." It would have been very helpful if the size of this effect had been offered in quantitative terms. One person's "modest" is the next one's "trivial." Johnson et al reported that their study demonstrated increased risk of 3 different anxiety disorders in early adulthood for those subjects who smoked heavily during adolescence. This may be the case. However, the woefully small numbers in each cell of the table accompanying their article and the extremely wide confidence intervals (CIs) for the odds ratios (ORs) for agoraphobia, generalized anxiety disorder, and panic disorder suggest their estimates are characterized by a considerable lack of precision.
MacCorquodale DW. Cigarette Smoking and Anxiety Disorders. JAMA. 2001;285(6):732-733. doi:10-1001/pubs.JAMA-ISSN-0098-7484-285-6-jlt0214