This paper explores capturing expenditure data from food-purchase receipts using optical character recognition (OCR). Point-of-sale receipts provide means to assess the accuracy of self-reported expenditures by providing a comprehensive record of the number of items purchased and their prices. However, comprehensively coding receipts can be cost prohibitive, particularly for large-scale surveys. The burden of capturing receipt data then becomes the largest impediment to survey researchers who are looking to reduce respondent burden and take full advantage of point-of-sale receipts as an external record of expenditures. This work examines the efficacy of employing open-source OCR software to interpret food-purchase receipts and …

Correctly recalling where someone lived as of a particular date is critical to the accuracy of the once-a-decade U.S. decennial census. The data collection period for the 2010 Census occurred over the course of a few months: February to August, with some evaluation operations occurring up to 7 months after that. The assumption was that respondents could accurately remember moves and move dates on and around April 1st up to 11 months afterwards. We show how statistical analyses can be used to investigate the validity of this assumption by comparing self-reports and proxy-reports of the month of a move in …