The author addresses two methodological aspects of the Diary Survey conducted as part of the 1972–73 Consumer Expenditures Program by the U.S. Bureau of the Census for the U.S. Bureau of Labor Statistics. The Diary Survey was a record-keeping survey in which sample households were asked to record all their expenditures for a 14-day period. The survey was conducted over a two-year period from July 1972 to June 1974. Part I of the article describes the actions taken during the course of the survey to improve response rates, which were considerably below expectations during the initial weeks of the survey. Part II describes and presents results of an experiment undertaken to determine the effects on response rates of offering a modest cash incentive to sample households for maintaining a record of their expenses for two weeks.

No abstract