This Article  • Full text  • PDF  • Reply to article  • Send to a friend  • Save in My Folder  • Save to citation manager  • Permissions  Citing Articles  • Citing articles on ISI (5)  • Contact me when this article is cited  Related Content  • Similar articles in this journal

	Since this article does not have an abstract, we have provided the first 150 words of the full text and any section headings.

In my opinion, the Age-Related Eye Disease Study (AREDS) investigators promoted a nonsignificant result into a conclusive recommendation.¹ Here is how they did it.

The primary study outcomes for AREDS are explicitly stated in the "Participants and Methods" section of the article: (1) progression to advanced age-related macular degeneration (AMD) and (2) a 15-letter decrease in visual acuity. These outcomes were to be evaluated in all patients by independent tests of significance of the 2 primary treatments. This carefully specified primary analysis led to 4 tests, none of which was statistically significant. One, testing the effect of zinc on progression to advanced AMD, achieved a level of significance defined by the investigators as suggestive.

Despite these negative results, the investigators recommend combined treatment with antioxidants and zinc based on their secondary analysis. Two analytic approaches provided them with significant results. First, the authors restricted the analysis to a subgroup. The . . . [Full Text of this Article]