U.S. flag

An official website of the United States government

Department of Labor Logo United States Department of Labor
Dot gov

The .gov means it's official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you're on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Bureau of Labor Statistics > Office of Survey Methods Research > Publications > Browse Research Papers

The Effects Of Advance Letters And Reminder/Thank You Letters On Reducing Nonresponse In An Establishment Survey: An Experimental Study

Young I. Chun and Kenneth W. Robertson

Abstract

An increased nonresponse rate is a major problem not only in household surveys in the U.S. and abroad but also in establishment surveys (Christianson and Tortora, 1995) and economic censuses (Ambler and Mesenbourg, 1992). An increasing nonresponse rate in establishment surveys has been of primary concern to government bureaus collecting data from businesses or firms, as a high response rate is considered an important component of data quality, and the effort to reduce nonresponse mounts the survey cost. It is important for survey researchers to reduce as much nonresponse as possible, because nonresponse affects the reliability of statistical estimates by introducing bias. This paper reports the findings from a recent field experiment conducted by the Bureau of Labor Statistics (BLS) that was designed to evaluate a set of nonresponse-reducing techniques for an establishment mail survey. The nonresponse reducers investigated are advance letters and reminder/thank you letters. Among various design techniques (e.g., personalization, stamped return envelope, first outgoing postage, sponsorship, financial incentives, questionnaire color, and etc.), the combined use of advance and reminder/thank you letters have been found most effective in reducing nonresponse rates for voluntary household surveys and censuses (Dillman et al., 1993), but have not been tested yet for establishment surveys.