In The Lancet Psychiatry, Matthias Pierce and colleagues1,2 identify the importance of sampling in studying mental health effects of COVID-19. We found that a mental health survey3 using a commercial panel (of approximately 20000 people) overrepresented mentally unhealthy respondents by approximately 2·5 times. This overrepresentation occurred despite multiple measures to ensure representativeness: prespecified demographic and geographical sampling quotas; post-collection checks on the distribution of socioeconomic parameters; and adjustments for mismatches between clinical psychological scores and use of health-care services. Further random subsampling, before analysis, was required to correct for this sampling bias.