The data used to make the calculations are the FBI's Uniform Crime Reports and the U.S. Bureau of the Census. Some of the problems associated with using arrest data to determine the number and types of crime are discussed, along with problems with counting populations. The author concludes that the 1990 U.S. census provided better estimates of the Native American population than had been available. The argument that the latest Uniform Crime Reports are more valid than earlier versions is a little more tenuous, according to the author. Sections of this paper discuss all reported crime, violence, and property crime among Native Americans; drunkenness, driving while intoxicated, and liquor violations; drugs; and homicide. Based on the data analysis, this study concludes that Native American criminality, as measured by arrest rates, is nowhere near as high as it has been portrayed in the criminological literature and popular press. Based on 1990 census data, arrest rates for Native Americans are often similar to those for white Americans. The error in the earlier research occurred because the denominator (Native American population) in the equations used to calculate rates was incorrect. The author explains why this is so. 2 tables, 8 figures, and 12 notes