Sample size calculations for ophthalmologic studies
W. J. Gauderman and W. E. Barlow
Department of Preventive Medicine, University of Southern California School of Medicine, Los Angeles 90033.
Sample size calculations are shown for some common ophthalmologic study
designs in which two treatments are to be compared. Included are the
following three designs: 1, only one eye per subject; 2, both eyes, with
each eye assigned to a different treatment; and 3, both eyes undergoing a
common treatment. Continuous and binary outcomes are considered. The
correlation between eyes is accounted for in the computations using a
simple correction factor. For design 3, the formulas allow for a mixture of
single-eye and double-eye eligible subjects. A computer program that
performs the calculations is available.
