An Alternate Approach to Assessing Misclassification in JAS

• Activity Number: 116
• Type: Topic Contributed
• Date/Time: Monday, August 2, 2010 : 8:30 AM to 10:20 AM
• Sponsor: Section on Survey Research Methods
• Author(s): Pam Arroway*+
• Companies: North Carolina State University
• Keywords: NASS ; dual frame ; misclassification ; census ; JAS ; farms

Abstract

Each year, the National Agricultural Statistics Service (NASS) obtains an estimate of the number of farms in the United States (US) based on the June Area Survey (JAS). In 2007, the JAS estimate of the number of farms was much lower than that from the quinquennial Census of Agriculture. The discrepancy was more than could be accounted for by sampling error. The JAS uses an area frame that is, by design, a complete frame of the population. Estimates incorporate sampling weights appropriate to the sample design and so are unbiased unless misclassification is present. In 2009, NASS conducted the Farm Numbers Research Project (FNRP) to study misclassification of farms and non-farms in JAS. An annual (modified) version of FNRP called the Annual Land Use Survey (ALUS) is proposed to adjust the JAS estimate of the number of farms.