Ratio Estimation and Approximate Optimum Stratification in Electric Poher Surveys

= Some of the history of a monthly sales and revenue survey, and the current status of that survey and others, are given as background to changes now being implemented. Sampling will now take place at the State level, instead of the national level; more complete use will be made of auxiliary information; work has been done to control cv's for several variables simultaneously; and a test originally designed to consider degrees of homogeneity between several similar populations with limited sampling, has been used to investigate the effectiveness of this design at an aggregated (Census division) level. I. INTRODUCTION= A relatively small number of utilities sell most of the retail electricity in the United States. The Energy Information Administration (EIA) Form EIA-826, "Monthly Electric Utility Sales and Revenue Report Nith State Distributions," collects data from these large utilities and a stratified random sample of the smaller utilities. The universe is from another survey, begun in Ig8q, which is a census, performed on an annual basis. Until 1986, the predecessors to Form EIA-826 gathered data from only a select group of large privately owned utilities. Stratified random sampling has been used with good results since that time. A "certainty" stratum has been used to let the largest utilities represent only themselves, and this design