estimate for complete count data measures the variation 

 associated with the sample-based adjustment for whole 

 farm nonresponse. The percent relative standard error of 

 the estimate for sample items measures both the sampling 

 error due to the nonresponse sample estimation procedure 

 and the census sample selection and estimation proce- 

 dure. The reliability of State estimates may vary substan- 

 tially from State to State. Generally, State estimates for a 

 given data item are less reliable than the corresponding 

 U.S. estimate. 



Table D presents the standard error (not relative stand- 

 ard error) for percent change in U.S. totals from 1982 to 

 1987. The general purpose of the percent change estimate 

 is to provide a relative measure of the difference in a 

 characteristic between censuses. The relative change for 

 a given characteristic is defined as the ratio of the differ- 

 ence of the 1 987 and the 1 982 estimate for that charac- 

 teristic to the 1982 estimate. This ratio is multiplied by 100 

 to obtain the percent change. The percent standard error 

 of a percent change estimate, then, is the standard error of 

 the ratio multiplied by 100. 



Table E presents the relative standard error for U.S. and 

 State totals for 10 major complete count items and 7 

 sample items. The relative standard error of the estimate 

 (percent) for the same item differs among States. Reasons 

 for this are differences among States in (1) the total 

 number of farms, (2) the number of large farms included 

 with certainty, (3) the size classifications of the farms 

 sampled, (4) the amount of nonresponse, (5) the general 

 agricultural characteristics, and (6) the specific character- 

 istic being measured. 



CENSUS NONSAMPLING ERROR 



The accuracy of the census counts are affected by the 

 joint effects of the sampling errors described in the previ- 

 ous section and nonsampling errors. Extensive efforts 

 were made to compile a complete and accurate mail list for 

 the census, to design an understandable report form and 

 instructions, and to minimize processing errors through the 

 use of quality control, verification, and check measures on 

 specific operations. Nonsampling errors arise from incom- 

 pleteness of the census mail list, duplication in the mail list, 

 incorrect data reporting, errors in editing of reported data, 

 and errors in imputation for missing data. These specific 

 nonsampling errors are further discussed in this section. 

 Evaluation studies will be conducted to measure the extent 

 of certain nonsampling errors such as coverage error, 

 classification error, and item imputation. 



Census Coverage 



The main objective of the census of agriculture is to 

 obtain a complete and accurate enumeration of U.S. farms 

 with accurate data on all aspects of the agricultural oper- 

 ation. However, the cost and availability of resources for 



this enumeration place restrictions on operationally feasi- 

 ble data collection methodologies. The past five agricul- 

 ture censuses have been conducted by mail enumeration 

 with telephone contact for selected nonrespondents. The 

 completeness of such an enumeration thus depends to a ^ 

 large extent on the coverage of farm operations by the , 

 census mail list. 



Historically, the census of agriculture has included , 

 approximately 90 percent of the farms in the United States 

 and over 96 percent of the agricultural production. Com- 

 plete enumeration of agricultural operations satisfying the 

 farm definition of $1,000 or more in agricultural sales is 

 complicated by fluctuations in agricultural operations qual- 

 ifying for enumeration, the variety of arrangements under 

 which farms are operated, the multiplicity of names used 

 by an operation, the number of operations in which an 

 operator participates, the accuracy of data reporting, etc. A 

 new mail list is compiled for each census because no 

 current single list of agricultural operations is comprehen- 

 sive. 



An evaluation of census coverage has been conducted 

 for each census of agriculture since 1 945. The evaluation 

 provides estimates of the completeness of census farm 

 count and major census data items. In addition, the 

 evaluation helps to identify problems in the census enu- 

 meration and provide information that can form the basis 

 for improvements. The results of the 1987 Coverage 

 Evaluation program will be published in volume 2, part 2. 



The evaluation of coverage conducted in 1987 was 

 designed to measure errors in the census mail list and in 

 farm classification. Mail list error includes a measurement 

 of farms not on the census mail list (undercount), and a 

 measurement of farms enumerated more than once in the 

 census (overcount). Classification error includes a mea- 

 surement of farms classified as nonfarms in the census 

 (undercount) and of nonfarms classified as farms in the 

 census (overcount). Classification error arises from report- 

 ing and processing errors. Mail list undercount dominates 

 all coverage errors. Net coverage error is defined as the 

 difference of undercounted and overcounted farms. Mea- 

 surements of these errors, as well as a description of the 

 complete coverage program, will be available in the Cov- 

 erage Evaluation report. 



Mail List Coverage 



A major problem with the use of a mail list for the census 

 of agriculture enumeration is the difficulties that are encoun- 

 tered in compiling a complete list. The percentage of farms 

 on the census mail list varies considerably by State. 

 Several reasons have contributed to farm operators' names 

 not being included on the census mail list— the operation 

 may have been started after the mail list was developed, 

 the operation may be so small as not to appear in 

 agricultural related source lists used in compiling the 

 census list, or the operation may have been falsely clas- 

 sified as a nonfarm prior to mailout. A large proportion of 

 the farms not included on the mail list were small in both 

 acres and sales of agricultural products. 



C-4 APPENDIX C 



1987 CENSUS OF AGRICULTURE 



