This paper describes the uncertainty analysis applied to comparisons between satellite monthly rainfall estimates and twenty 2.5¿¿2.5¿ box rainfall estimates constructed from Pacific atoll-sited rain gauge sites. This work was done in conjunction with NASA's WETNET Precipitation Intercomparison Project 3 (PIP 3), and was conducted by personnel at the Environmental Verification and Analysis Center (EVAC) at the University of Oklahoma. Motivation for this work stemmed from the need to supply surface areal rainfall estimates of known accuracy for comparison with satellite rainfall estimates and the need to use these estimates to quantify the uncertainty of the comparisons. This allowed for the discrimination of the value of various statistics associated with regression analysis, using different satellite algorithms, and for the quantification of the regression statistics computed by accounting for rain gauge uncertainty. To our knowledge this type of work has not been performed for previous satellite rainfall intercomparison programs. ¿ 1998 American Geophysical Union