A brief, practical overview of "design effects" (DEFFs) is presented for users of the results of sample surveys. The overview is intended to help such users to determine how and when to use DEFFs and to compute them correctly. DEFFs are needed only for inferential statistics, not for descriptive statistics. When the selections for surveys are not simple random selections, DEFFs are needed for pooling or averaging sampling errors. In addition to internal uses of sampling errors, four external uses and four cases for which DEFFs are not sufficient are discussed. Finally, DEFFs for weighted means and the relationship of DEFFs to differences distinguishing the average cluster size from the average homogeneity of elements with primary clusters are addressed. DEFFs and ratios of homogeneity serve researchers' needs for: averaging for greater precision; economizing on computations or presentation; or borrowing from other survey samples. (TJH)