Mail surveys of small business owners have notoriously low response rates, creating the potential for substantial error in surveys of this population and diminishing the credibility of research conducted on small firms. The author recently carried out an experiment as part of a larger project involving 16,000 small business owner/members of the National Federation of Independent Business (NFIB). The experiment's purpose was to ascertain survey treatments that might enhance mail survey response among small business owners. Results showed that none of the six treatments examined improved response rates enough to warrant its routine use over the alternative, nor did any combinations of treatments help. The implication is that commonly used treatments, for example prenotification, often are unproductive.
Surveys, particularly mail surveys, have been a staple in quantitative research on small business and entrepreneurship (Aldrich and Baker 1997; Aldrich 1992; Churchill and Lewis 1986; Wortman 1986). While research techniques and data collection methods have evolved over the years, surveys still dominate (Aldrich and Baker 1997). The author's count of five small business oriented journals covering calendar years 1998 and 1999 concludes that about one-third of all refereed articles, including a majority in this journal, relied on mail surveys as their principal data source. Moreover, at least some educated opinion feels that self-administered surveys, including mail, largely will replace telephone and personal interview methods in the future (Dillman 1999). While changes driving the use of self-administered surveys often are not as relevant in a business as in a household setting due to influences such as telephone answering machines, a strong likelihood exists that mail surveys will continue to be an important tool in research on small business owners and entrepreneurs. Methodological issues regarding the conduct of mail surveys among small business owners, therefore, should be of considerable interest and of consequence for researchers investigating this population.
Response Rates in Mail Surveys
One of the most important methodological issues concerning small business and mail surveys is response rate. Mail surveys of small business owners and entrepreneurs produce notoriously low response rates, though reviews directly on point are largely absent. Most focus on business response rates and customarily fail to distinguish between large and small business respondents, mail and other survey forms (though most are mail), conventional and captive or proxy samples such as students in a classroom, etc. Still, the evidence is discouraging. The author's previously referenced examination of articles in five small business- or entrepreneurship-oriented journals shows that the average response rate hovers around 30 percent. Aldrich and Baker (1997) found that the almost three in four articles appearing in selected small firm-oriented journals between 1991 and 1995 with samples of entrepreneurs had response rates lower than 50 percent; nearly one-third had rates lower than 25 percent. (2) Paxson, Dillman, and Tar nai (1995), reviewing 180 studies with business respondents in the academic and trade literature during the early 1990s, calculated their average response rate to be 21 percent. However, it is not clear whether their search included surveys of small business owner populations, business populations, or some combination of the two.
Not all reviews find response rates as poor. Baruch (1999) showed the average response rate of the studies he examined to be 56 percent, though studies conducted by private businesses were generally much lower. But of the 175 studies included in Baruch's review, only two focused on small firms. (3) Roth and BeVier (1998) calculated response rates at the 50th percentile to be 51 percent and at the 20th percentile to be 31 percent across a sample of articles published in six human resource management and organizational behavior (HRM/OB) journals during the early 1990s. …