OBJECTIVE: Older adults may require additional support to comprehend written information due to inadequate health literacy, which involves components of cognitive function including reaction time. This study tested the acceptability of web-based reaction time testing in the UK Women's Cohort Study and possible sources of bias. Additionally, it assessed the association between health literacy and reaction time. DESIGN: A cross-sectional analysis was conducted using data from the UK Women's Cohort Study, a prospective cohort study. PARTICIPANTS: The study involved women aged 48-85 without cancer registration who participated in the 2010/2011 follow-up (n=768). SETTING: Postal questionnaires and web-based cognitive function tests were administered in participants' homes. METHODS AND ANALYSIS: Logistic regression identified predictors of volunteering for reaction time testing, used to calculate inverse probability weights for the primary analysis. Associations between health literacy and reaction time were estimated with linear regression models, adjusting for volunteer effects. Poisson regression models assessed associations between health literacy and choice reaction time errors. PRIMARY AND SECONDARY OUTCOME MEASURES: The primary outcome was acceptability of web-based testing (response rate, task distress, task difficulty). Secondary outcomes were sources of volunteer bias and the association between health literacy and reaction time. RESULTS: Web-based testing of cognitive function was attempted by 67% of women (maximum age 80), with little distress or difficulty reported. There was substantive volunteer bias. Women providing data on cognitive function were younger, had higher educational attainment and were higher in self-rated intelligence. Inadequate health literacy was associated with making fewer choice reaction time errors among those providing valid data but was also associated with not providing valid data. Health literacy was not associated with other aspects of reaction time (speed, variability). Additionally, selection bias may have restricted range on study variables, given that 2010/2011 volunteers were younger and more educated compared with those at recruitment in 1995/1998. CONCLUSION: Brief web-based measures of cognitive function in the home are acceptable to women aged 48-80, but there are substantive selection effects and volunteer biases. Additionally, there are potentially vulnerable subgroups who provide poorer quality data.