In October-November 2004, the Afrobarometer surveyed a nationally representative random, stratified probability sample of 2,400 South Africans. Face-to-face interviews were conducted by AC Nielsen/South Africa in all eleven official languages across all nine provinces. The sample was drawn by taking the smallest geographic units, census Enumeration Areas (EA’s) and stratifying all EA’s across the country into separate lists according to province, race, and urban/ rural status. 600 EA’s were then randomly selected from these lists with the probability proportionate to its size in the overall population as represented in the 2001 census. This ensures that every eligible adult had an equal and know chance of being selected. Four interviews were then randomly conducted within each EA, and a respondent 18 years of age or older was randomly selected from each household. A gender quota ensured that every other interview must be with a female. This generated an overall sample size of 2,400 which is sufficient to yield a margin of error of plus or minus 2 percent at a confidence level of 95 percent.