Survey Research Unit (SRU) - Sampling and Non-response

Centre for Research on Inner City Health - Keenan Research Centre

To help secure coverage and recruitment, the SRU draws upon a variety of sampling strategies that include probability samples such as:

  • simple random sampling
  • systematic sampling
  • stratified sampling
  • quota sampling
  • cluster sampling

and non-probability samples such as:

  • purposive sampling
  • convenience sampling
  • snowball sampling
  • expert sampling
  • heterogeneity sampling
  • time-location sampling

Non-response error occurs when people who choose to respond to your survey are different from the ones that choose not to respond. The SRU can help you minimize the resulting bias, using a variety of recruitment strategies.

To encourage participant response, the SRU can facilitate the distribution of small incentives to participants, and boosts response rates by taking into account the social and psychological elements of survey participation. These social and psychological elements include: scarcity of opportunity, consistency with previous behaviour, desire to reciprocate, enjoyment of task, and social proof (Groves et al. 1992). Recruitment letters, phone scripts, and email invites are all drafted with your study population and applicable ‘social behaviour rules of survey participation’ in mind.

The SRU has a proven track record of delivering optimal recruitment rates. Although recruitment rates vary from project to project (depending on the target population and the project budget), our average recruitment rate is 80 per cent, and over 70 per cent when recruiting hard-to-reach populations. The SRU also offers low missing data rates - below five per cent for general questions, and below 20 per cent for sensitive information.