A study of otitis media is described which requires a special method for treatment comparision because of the lack of a gold standard for disease assessment. In this paper, we investigate the use of two diagnostic procedures to estimate and to test the treatment difference; a byproduct of this maximum likelihood-based procedure is the estimates of sensitivity and specificity of each diagnostic procedure involved. We also investigate, by simulation, the power of the proposed procedure.
Howie, V. M. and Schwartz R. H., (1983), Acute otitis media: One year in general pediatric practice, American Journal of Diseases in Children, 137, 155–158.Google Scholar
Teele, D. W., Klein, J. O., Rosner, B. et al., (1989), Epidemiology of otitis media during the first seven years of life in children in Greater Boston: A prospective cohort study, Journal of Infectious Diseases, 160, 89–94.CrossRefGoogle Scholar
Giebink, G. S., Batalden, P. B., Le, C. T., et al., (1990), A controlled trial comparing three treatments for chronic otitis media with effusion, Journal of Pediatric Infectious Diseases, 9, 33–40.CrossRefGoogle Scholar
Daly, K. A., Giebink, G. S., Anderson, R. S., et al., (1991), Resolution of otitis media with effusion with the use of a stepped treatment regimen of trimethoprim-sulfamethoæazole and prednisone, Journal of Pediatric Infectioud Diseases, 10, 500–506.CrossRefGoogle Scholar
Le, C. T., Daly, K. A., Margolis, R. H., et al., (1992), A clinical profile of otitis media, Archives of Otolaryngology, 118, 1225–1228.CrossRefGoogle Scholar