The Importance of Selection Bias in Internet Surveys

Abstract

Nowadays, internet-based surveys are increasingly used for data collection, because their usage is simple and cheap. Also they give fast access to a large group of respondents. There are many factors affecting internet surveys, such as measurement, survey design and sampling selection bias. The sampling has an important place in selection bias in internet survey. In terms of sample selection, the type of access to internet surveys has several limitations. There are internet surveys based on restricted access and on voluntary participation, and these are characterized by their implementation according to the type of survey. It can be used probability and non-probability sampling, both of which may lead to biased estimates. There are different ways to correct for selection biases; poststratification or weighting class adjustments, raking or rim weighting, generalized regression modeling and propensity score adjustments. This paper aims to describe methodological problems about selection bias issues and to give a review in internet surveys. Also the objective of this study is to show the effect of various correction techniques for reducing selection bias.

Identifying important health system factors that influence primary care practitioners’ referrals for cancer suspicion: a European cross-sectional survey

“…Most samples were taken from each local lead’s own locality, and these may not have been representative of their nations as a whole. 36 While this makes it difficult to generalise the findings to each country, the variation between countries is relevant and valid. The recruitment method used in this study resulted in variable response rates, leading to a risk of non-response bias and loss of power.…”

Do people prefer natural landscapes? An empirical study in Chile

“…Although internet surveys have become very popular, they are prone to well-known survey errors of non-observation or selection bias (Greenacre 2016). The population of "internet users" is dynamic and difficult to define, therefore a sampling method is challenging.…”

“…Usually, landscape assessment focuses on certain groups of people, which may be due to the increasing difficulty of the dataset, when a variation both in landscape attributes and features of respondents is to be included in the models (Sevenant and Antrop 2010). In this sense, internet-based surveys are increasingly used for data collection, because application is simple and cheap and also they allow instant access to a large group of respondents (Greenacre 2016). A landscape evaluation can be defined as the comparative relationships between two or more landscapes in terms of assessment of visual quality (Laurie 1975).…”

A pilot study of Australian pet owners who engage in social media and their use, experience and views of online pet health information

“…For example, over 90% of individuals in Australia between 12 and 54 years of age use social networking sites compared with only 61% of those 55 years of age and over . Furthermore, online surveys are also subject to self‐selection bias . This study's sample was predominately female; an issue that has been witnessed in other online pet owners surveys.…”