This Article  • Full text  • PDF  • Send to a friend  • Save in My Folder  • Save to citation manager  • Permissions  Citing Articles  • Contact me when this article is cited  Related Content  • Related article  • Similar articles in JAMA

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

To the Editor: In the study by Dr Langman and colleagues,¹ data from several studies were pooled prospectively, and the results were interpreted to indicate that "rofecoxib was associated with a significantly lower incidence of PUBs [upper gastrointestinal tract perforations, symptomatic gastroduodenal ulcers, and upper gastrointestinal tract bleeding] than treatment with NSAIDs [nonsteroidal anti-inflammatory drugs]." The consistent use of this terminology throughout the manuscript implies that rofecoxib is not an NSAID (which it is) and that all of the drugs to which it was compared belong to a class that is dissimilar to rofecoxib. The latter conclusion cannot be supported from the data presented. The authors did certain analyses and concluded that "a common RR [relative risk for the comparators] was appropriate." The nonsignificant test for treatment by protocol interaction cannot be taken as proof of homogeneity because this test has very low power in the presence of so few . . . [Full Text of this Article]

RELATED ARTICLE

Adverse Upper Gastrointestinal Effects of Rofecoxib Compared With NSAIDs
Michael J. Langman, Dennis M. Jensen, Douglas J. Watson, Sean E. Harper, Peng-Liang Zhao, Hui Quan, James A. Bolognese, and Thomas J. Simon
JAMA. 1999;282(20):1929-1933.
ABSTRACT | FULL TEXT