Online surveys generally have very heavy response bias. This is caused by a range of factors that can include

- poor response rates

- poor completion rates

- lack of access to the internet

- lack of ease with the internet especially when responding on sensitive subjects

The bias will operate in different ways but will often include under-participation by older people, people in rural communities, socially excluded groups, very busy people (e.g. professionals), people from ethnic minorities. Often these factors can make online surveys virtually useless, but it depends on the objectives of the research. They work well with audiences where all email addresses are held and where there is high motivation (e.g. staff surveys). However, this does not seem to apply here.

One way forward is to help people complete a survey say on a tablet by meeting with them face to face. Other methods are postal, face to face and telephone surveys. Of course these are all more expensive so it depends on budget. I would suggest perhaps a mixed methodology so that if you do decide to use online you supplement this with work with groups that are not responding or that you have good reason to think may not be accessing it. If you want to minimise response bias however there remains no substitute for old fashioned methods which is why the US and UK both still use postal surveys for definitive health and social survey work.

Online surveys generally have very heavy response bias. This is caused by a range of factors that can include

- poor response rates

- poor completion rates

- lack of access to the internet

- lack of ease with the internet especially when responding on sensitive subjects

The bias will operate in different ways but will often include under-participation by older people, people in rural communities, socially excluded groups, very busy people (e.g. professionals), people from ethnic minorities. Often these factors can make online surveys virtually useless, but it depends on the objectives of the research. They work well with audiences where all email addresses are held and where there is high motivation (e.g. staff surveys). However, this does not seem to apply here.

One way forward is to help people complete a survey say on a tablet by meeting with them face to face. Other methods are postal, face to face and telephone surveys. Of course these are all more expensive so it depends on budget. I would suggest perhaps a mixed methodology so that if you do decide to use online you supplement this with work with groups that are not responding or that you have good reason to think may not be accessing it. If you want to minimise response bias however there remains no substitute for old fashioned methods which is why the US and UK both still use postal surveys for definitive health and social survey work.

You can find systematic recommendations about how to improve online response rates in Dillman et al., Internet, Mail, and Mixed-Mode Surveys: The Tailored Design Method 3rd Edition.

Being effective to overtake the old and rural population bias can be to contact them by more common means, like telefone.

Good luck

Usually snowball sampling method with recommendations are helpful to improve response rate in online surveys.

The following sources should be helpful, particularly the Internet survey process/recruitment/online coverage problems, where mixed-mode surveys can be considered, please refer to de Leeuw et al (2008). 

• Birnbaum, M. H. (2004). Human research and data collection via the Internet. Annual review of psychology, 55, 1, pp. 803-832.
• de Leeuw, E. D., Hox, J. J. and Dillman, D. A. (2008). International Handbook of Survey Methodology, New York, Psychology Press.
• Ilieva, J., Baron, S. and Healey, N., M. (2002). Online surveys in marketing research: Pros and cons. International Journal of Market Research, 44, 3, pp. 361-381. 

Try creating an online survey which is anonymised.  You do not know the responders name or contact details but with careful wording of biographic detail you can generate a considerable data set depending on what variables you are looking for.  Several online survey software programs allow for the creation of a link to your survey which can be posted on, for example, FB pages appropriate to your target population.  See as one example EasyQuest.  This is an alternative to collating a database and inviting individuals to participate.

In order to increase the response rate in the survey,,,try to include incentives for participants.

What are the best methods to recruit more participants using online surveys?

Assuming online survey is deployed, perhaps following approach can be considered to increase online respondents' response rate:

These links may help you

https://support.optimalworkshop.com/hc/en-us/articles/202456124-How-to-source-participants-for-your-surveys-

https://www.callforparticipants.com/researcher

https://www.apa.org/education/ce/facebook-research.pdf

Article Recruitment of mental health survey participants using Inter...

Article Using Online Social Media for Recruitment of Human Immunodef...

Article The effectiveness of recruitment strategies on general pract...

Article Recruiting for health, medical or psychosocial research usin...

Article The Use of Facebook in Recruiting Participants for Health Re...