Global Positioning System (GPS) collars have revolutionized the field of spatial ecology, but to date, few primate studies have used them. We fitted a free-ranging, semi-habituated, juvenile male chacma baboon (Papio hamadryas ursinus) with an automatic self-releasing GPS collar and tracked his movements for 359 days. The collar captured 4254 fixes out of 5719 programmed opportunities, a 74.4 % acquisition rate, suggesting that the collar effectively tracked this baboon in a variety of habitat types. Of the data points captured, 73.7 % were three-dimensional fixes, and of these fixes, 66.9 % were highly accurate, having a dilution of precision of less than four. We calculated home range using three protocols with three estimation methods: minimum convex polygon, fixed kernel-density estimation (KDE), and fixed r local convex hull. Using all data points and the 95 % contour, these methods created home range estimations ranging from 10.8 to 23.1 km(2) for this baboon troop. Our results indicate that the KDE output using all data locations most accurately represented our data set, as it created a continuous home range boundary that excluded unused areas and outlying, potentially exploratory data points while including all seven sleeping sites and a movement corridor. However, home range estimations generated from KDE varied from 15.4 to 18.8 km(2) depending on the smoothing parameter used. Our results demonstrated that the ad hoc smoothing parameter selection technique was a better method for our data set than either the least squares cross-validation or biased cross-validation techniques. Our results demonstrate the need for primatologists to develop a standardized reporting method which documents the tool, screening protocol, and smoothing parameter used in the creation of home range estimations in order to make comparisons that are meaningful.