Web-based experiments and questionnaires are essential methods of epidemiology that provide important information about public health and disease. They are a typical method of gathering data that is usually less expensive and time-consuming than face-toface interviews, mail-in questionnaires or automated menus for telephone systems. Questionnaires and Web tests are not free of limitations, which should be addressed to obtain valid and reliable results.
A questionnaire may be affected by response bias. This is the tendency for respondents to answer questions based on their own opinions and not on research goals. Moreover, questionnaire design can influence responses in different ways. For example the wording of the question can affect whether respondents are able to comprehend and interpret the question in the same manner (reliable), measure the topic you’re interested in (valid), or can answer with accuracy (credible).
Lack of engagement with the questionnaire can also make respondents less likely to give honest answers. A lack of incentive or compensation might hinder respondents from filling out a questionnaire.
Online questionnaires also pose a challenge for some experimental designs, for example, positioning or reaction time studies. The wide range of settings for browsers screens, sizes, and operating systems makes it challenging to control and measure the same variables across all participants.
Additionally, surveys conducted on the Web are only accessible to those who are keyboard and Internet proficient, which currently excludes a significant portion of the population. It is also difficult for Web researchers debriefing participants after the experiment window has ended.