Rejoinder

Food insecurity and mental health among young adult college students in the United States

“…At each university, a random sample of 8,000 students was invited by e-mail to participate, except at smaller universities (<8,000 students) where all students were invited to participate. The response rate was 14%, which is comparable to other response rates from online surveys using convenience samples and panels (Baker et al, 2013;Craig et al, 2013). We restricted the sample by age (18-34) to isolate young adults (18,013 observations excluded) and excluded individuals who were missing data on any of the variables of interest; we used complete-case analysis (23557 observations excluded listwise), resulting in a final analytic sample of 96379.…”

“…People may have been reluctant to disclose mental health conditions or being food insecure due to stigma. Third, the response rate was 14%, which is expected of online surveys of this nature (Baker et al, 2013;Craig et al, 2013). We attempted to address this by using survey weights that account for non-response, but sampling bias remains a concern.…”

Using Facebook Advertising to Recruit Representative Samples: Feasibility Assessment of a Cross-Sectional Survey

“…It could be especially effective in comparison with other nonprobabilistic sampling methods; other research has noted that Facebook may be able to obtain more representative samples than other types of nonprobabilistic methods [19]. Moreover, probabilistic sampling does not inherently result in representative inferences, so although some may criticize nonprobabilistic sampling, it can yield valid inferences with proper weighting and adjustment [26].…”