Web Survey Bibliography
Web questionnaires have been placed on thousands of Web sites and Internet survey panels now include millions of Internet users. In addition, technology continues to improve all aspects of doing Web surveys: standardized software, user-friendly interface, attractive multimedia, merger of technologies (Web, TV, phone, VCR), high speed of transmission, and low access costs. During the next years, increased Internet penetration, massive Web usage, and technological improve-ments will further expand the application of Web surveys. However, nonresponse to such surveys is a serious problem. Our purpose in this chapter is to discuss the nonresponse process, factors that contribute to its occurrence, and its consequences. The Web survey mode is based on computer-assisted self-administered questionnaires answered without the presence of the interviewer. The questionnaires are based on HTML forms usually presented in standard Web browsers, while the responses are immediately transferred through electronic networks, usually the Internet. We further limit our discussion to the basic Web survey mode, where respondents record their answers manually (with a keyboard or a mouse), written questions are the core layout on the screen, there is no on-line interaction (help) with the interviewer, and multimedia is restricted only to illustrate the survey questions. Our discussion of web surveys draws on an extensive on-line literature base we have compiled (http://surveys.over.net/method). In addition, data are reported from the national project RIS - Research on Internet in Slovenia (RIS, 1996-2000), conducted at the Faculty of Social Sciences, University of Ljubljana since 1996. In particular, we refer to RIS Web surveys in which participants were invited via e-mail solicitation (with two follow-ups) through addresses from the public directory. In 1998, one tenth (n=6,500) of the active Slovenian Internet users participated in the RIS Web survey. Due to a small population (2 million) and moderate Internet penetration (15%) a large post-Web telephone survey (n=10,000 households) enabled a study to be done of the units that were aware of the Web survey but did not participate.
Homepage - book (Table of contents)