Objective: To evaluate the impact on the general public of England's Time to Change program to reduce mental health-related stigma and discrimination using newly developed measures of knowledge and intended behaviour regarding people with mental health problems, and an established attitudes scale, and to investigate whether social desirability affects responses to the new measures and test whether this varies according to data collection method. Method: The Mental Health Knowledge Schedule (MAKS) and Reported and Intended Behaviour Scale (RIBS) were administered together with the 13-item version of the Marlowe-Crowne Social Desirability Scale to 2 samples (each n = 196) drawn from the Time to Change mass media campaign target group; one group was interviewed face to face, while the other completed the measures as an online survey. Results: After controlling for other covariates, interaction terms between collection method and social desirability were positive for each instrument. The social desirability score was associated with the RIBS score in the face-to-face group only (β = 0.35, 95% CI 0.14 to 0.57), but not with the MAKS score in either group; however, MAKS scores were more likely to be positive when data were collected face to face (β = 1.53, 95% CI 0.74 to 2.32). Conclusions: Behavioural intentions toward people with mental health problems may be better assessed using online self-complete methods than in-person interviews. The effect of face-to-face interviewing on knowledge requires further investigation.