JMIR Publications

ABSTRACT

Background:

The widespread availability and cost-effectiveness of new-wave, software-based Audience Response Systems (ARSs) has expanded the possibilities of collecting health data from hard-to-reach populations, including youth. However, with all survey methods, biases in the data may exist because of participant nonresponse.

Objective:

Our goals were to: (1) examine the extent to which an ARS could be used to gather health information from youth within a large-group school setting, and (2) examine individual- and survey-level response biases stemming from this web-based data collection method.

Methods:

We used an ARS to delivered mental health survey to 3,418 youth at four high schools in the Midwestern U.S. The survey contained demographic questions, depression, anxiety, and suicidality screeners, and questions about their use of offline resources (e.g., parents, peers, and counselors) and online resources (i.e., telemental health technologies) when they faced stressful life situations. We then examined the response rates for each survey item, focusing on the individual- and survey-level characteristics that related to nonresponse.

Results:

Overall 80% of the youth participants answered more than half of the 38 survey questions; however, missingness analyses showed that there were some survey structure factors that led to higher rates of nonresponse (e.g., questions at end of survey, sensitive questions, and questions for which precise answers were difficult to provide), and there were also some personal characteristics that were associated with nonresponse (e.g., not identifying as either male or female, non-White ethnicity, and higher levels of depression). Specifically, a multivariate model showed that male students and students reporting “other” gender had significantly higher numbers of missed items compared to female students (B = .30 and B = .47, respectively, ps < .001). Similarly, non-White race (B = .39, p < .0001) and higher depression scores (B = .39, p < .0001) were positively related to the number of missing survey responses.

Conclusions:

Although our study showed that it is possible to gather sensitive mental health data from youth in large groups using ARSs, we also suggest that these nonresponse patterns need to be considered and controlled for when using ARSs for gathering population health data.