TY - JOUR AU - Schnell, Rainer AU - Noack, Marcel AU - Torregroza, Sabrina PY - 2017/08/07 Y2 - 2024/03/28 TI - Differences in General Health of Internet Users and Non-users and Implications for the Use of Web Surveys JF - Survey Research Methods JA - SRM VL - 11 IS - 2 SE - Articles DO - 10.18148/srm/2017.v11i2.6803 UR - https://ojs.ub.uni-konstanz.de/srm/article/view/6803 SP - 105-123 AB - Web surveys have become popular in many fields of research. Tocompensate persisting undercoverage and nonresponse problems ofweb surveys, weighting strategies are used. However, the underlyingassumptions of weighting are rarely tested. If the probability of missingdata depends on the missing data itself (missing not at random,MNAR), no standard weighting method will correct for nonresponseor undercoverage bias. We postulate a MNAR selection effect due tohealth conditions. Using real data from large scale non-internet surveysin different countries (European Social Survey (ESS), n 55; 000,Behavioral Risk Factor Surveillance System (BRFSS), n 492; 000),large differences in general subjective health between Internet usersand non-users can be observed. Weighting by calibration on age, gender, ethnic background, urban residence, education and household income does not eliminate the observed health differences. Therefore,the underlying missing data mechanism might be considered as an example of MNAR. If this holds, no weighting strategy will be able toeliminate health bias in web surveys. ER -