Identifying a set of key paradata indicators in web surveys based on the relationship with response quality, respondent characteristics and survey estimatesVehovar, Vasja (Avtor) Berzelak, Jernej (Avtor) Čehovin, Gregor (Avtor) web surveysparadatasmartphonesresponse qualitydata qualitysurvey estimatesrespondent characteristicsbig fiveWeb survey paradata refer to the digital traces left by respondents, which can provide valuable insights into the response process. An exhaustive literature review revealed that web survey paradata have predominantly been studied in relation to response quality and sometimes also in relation to respondent characteristics and survey estimates. A broad range of paradata indicators was already employed for these purposes in the literature. This paper aimed to identify a minimal set of paradata indicators that can be used as general characteristics of respondents, similar to sociodemographic variables. In the empirical part of the paper, a comprehensive set of raw paradata for a typical web survey was collected (n = 3,458). Based on the literature, an initial set of 112 paradata indicators was identified and further reduced through subsequent steps. Finally, the potential paradata indicators were examined for their statistically significant relationship with 9 response quality indicators, 8 respondent characteristics (including the Big Five personality dimensions), and 13 survey estimates related to computers and Internet use. The result of this process was a set of 12 key paradata indicators that could serve as a starting point for establishing a standardised set of paradata indicators, which could potentially augment the web survey response data.20242024-12-23 10:06:30Članek v reviji166179sl