Mail Surveys and Response Rates: A Literature Review

Abstract

Market researchers have long recognized the obvious advantages of mail questionnaire surveys. They are relatively low in cost, geographically flexible, and can reach a widely dispersed sample simultaneously without the attendant problems of interviewer access or the possible distortions of time lag. Difficult to reach respondents, such as farmers, soldiers, or busy executives, can be surveyed with relative ease [82], Businessmen and academic researchers favor mail surveys for reasons of expediency, since data can be procured more quickly, more abundantly, and more cheaply than when a personal interview is employed [46],Mail questionnaires are free from the costs and time consumption of interviewer bias or variability [7, 8, 9,17,31,41,44,70], Their relative or promised anonymity encourages respondents to freely divulge private or embarrassing or socially undesirable information [50,56,60,84], Finally, mail questionnaires tend to be more valid than either telephone or personal interviews because they enable respondents to check information by verifying their records or consulting' with other members of the family [59], and because they permit leisurely and thoughtful reply. Leslie Kanuk is Assistant Professor of Marketing and ConradBerenson is Professor of Marketing, Baruch College, City University of New York, The major disadvantages of mail surveys are generally believed to be their low response rates, with the attendant problems of response bias and nonresponse bias [1,5, 10,20,21,23,32,42,69, 78,81]. Efforts to increase the response rates to mail questionnaires are periodically reported in the literature, yet the most recent literature review appeared in a British journal back in 1961 [71], Various research reports published both before and since that time indicate that, contrary to general belief, some very high mail questionnaire response rates have been achieved.Empirical studies designed to improve the validity and reliability of mail surveys can be divided into two categories: those designed to increase response rates and those designed to reduce biases caused by nonresponse or special interest response. The reasons for this two-pronged effort are obvious. The greater the response, the more accurately it will estimate parameters in the population sampled. However, findings are representative of the population only if those people who do not respond to the questionnaire do not differ in significant ways from those who do respond. If they do differ, the kind and degree of such differences must be carefully estimated so that the findings may be properly weighted to reflect more accurately the population under study, INCREASING THE RESPONSE RATEEfforts to increase the response rate have variously been classified by timing(i.e., preliminary, concurrent, and followup efforts) and by technique (i.e., questionnaire length, size, survey sponsorship, return envelope and stamps, personalization of letter, method of reproduction, format, layout, color, anonymity, premiums or rewards, and deadline date). Methods clas...

The factors constraining innovation performance of SMEs in Croatia

“…In order to increase a response rate, follow-ups, i.e., e-mail and telephone prompts were used. In the literature, the follow-ups are considered as the most effective technique for obtaining a high response rate (Kanuk & Berenson, 1975). E-mail and telephone prompts resulted in a 12.5% response rate; that is 94 received filled questionnaires.…”

Innovation in family firms: an empirical analysis linking organizational and managerial innovation to corporate success

“…For a non-response bias, examinations were conducted to determine the differences between early and late respondents. No statistical differences were discovered between the two groups (Kanuk and Berenson 1975;Armstrong and Overton 1977;Newby et al 2003).…”

Endings and Visions of New Beginnings: The Effects of Source of Unemployment and Duration of Unemployment on Entrepreneurial Intent

“…There were also 23 respondents recruited by links from the agency website. To be sure that the different recruitment methods were not inducing a response bias (Kanuk and Berenson 1975), we compared respondents' age, education, and work experience across the different recruitment methods. The results of a one-way ANOVA revealed no significant differences between the recruitment methods regarding respondent age (F(3,115) = 0.59, p > 0.05), education (F(3,115) = 1.25, p > 0.05), or work experience (F(3,115) = 0.83, p > 0.05).…”