Notice: the WebSM website has not been updated since the beginning of 2018.

Web Survey Bibliography

Title Assessing Potential Bias in Respondent-driven Incident Based Data from a Web Survey of College Students
Year 2016
Access date 06.06.2016
Abstract
Incident-level data collection is a useful approach when measuring events that can occur multiple times within a survey’s reference period. Incident-based data allow survey researchers to analyze not just characteristics of persons but also characteristics of incidents (e.g. to assess the proportion of victimizations reported to authorities). However, asking respondents to complete detailed incident reports for all incidents experienced within the reference period may be too burdensome for persons who experienced several incidents. Therefore, survey practitioners often cap the number of
incident reports required for each respondent. If reported incidents differ from those not covered in the survey instrument, then bias potentially exists because limiting the number of incidents seemingly excluded incidents with certain characteristics. The Campus Climate Survey Validation Study (CCSVS), sponsored by the Bureau of Justice Statistics and the Office of Violence Against Women, was a web-based survey administered at nine colleges that collected prevalence and incident-based information onunwanted sexual contact. The CCSVS capped the number of incident reports at three and allowed respondents to determine the order in which incident reports were completed. To assess the potential for bias, we determine whether respondents systematically ordered the reported incidents. Bias could be introduced if the incidents that do not have a completed incident report are fundamentally different (e.g., occur later in the year or are less severe) than those that were reported. We consider incident ordering based on the chronological order and severity of incidents. In addition, we assess whether respondents who were unsure of the month in which one of their incidents occurred reported those incidents in a systematic way. Our analysis found that respondents do appear to systematically order their incidents both in terms of chronological order and severity. We quantify the potential impact of this biased ordering on key victimization estimates.
 
 
Year of publication2016
Bibliographic typeConferences, workshops, tutorials, presentations
Print