Hot spots have an irregular distribution over the earth's surface. Part of this irregularity is obviously due to the finite number (40-100) of hot spots, but the distribution does not appear to be completely random. In this paper, statistical analyses are compared for two published hot spot data sets, one minimal set of 42 and another larger catalog of 117. Three approaches are taken :(1) chi-square tests of equal area boxes, (2) cumulative distributions about principal axes, and (3) construction of a density function. These methods all indicate that hot spots have a nonuniform distribution, even when statistical fluctuations are considered. To the first order, hot spots are concentrated on one half of the surface area of the earth; within that portion, the distribution is consistent with a uniform distribution. A prediction of hot spot density is made based on an empirical model relating number of hot spots to plate speed. Comparison of this predicted density function to the constructed hot spot density functions for the two data sets yields some similarities; however, the observed hot spot densities for neither data set are explained solely by plate speed.