Introduction: In the field of Agricultural Estimates there is at the present time 2-way cooperation either with the State Departments of Agriculture and/or the Land Grant Colleges in 29 of the Field Offices representing 33 States. This cooperation is a natural outgrowth of the fact that the Federal Government is primarily interested in National Statistics with a breakdown by regions aha States, whereas State Agencies are primarily interested in State Statistics with a breakdown by areas and counties within the State. The Federal Census provides agricultural statistics for both purposes every 5 years, whereas the BAE provides current, up-to-the-minute agricultural statistics. Actually in the field of agricultural statistics we have "3-way cooperation"— The BAE, the Census Bureau, and the States Agencies. This cooperation could well be extended, not only in the field of current agricultural statistics, but also in providing the data needed for the agricultural economic and marketing research described by Dr. Elliott this morning. (The soundness of the conclusions reached in economic investigations depends in part on the reliability and the representativeness of the statistics and data utilized by the research worker.) Much of the data required for economic analysis relate to the operation and business activity of some 6,000,000 individual farms and/or to thousands of buyers and processors of agricultural products. Frequent enumerations of so large a population are not practical because of their high cost and lack of timeliness. Sampling in one form or another is the only alternative to complete enumeration. Since we cannot escape sampling, we should know more about it and how to use it effectively.