Surveys allow convenient and inexpensive research. Surveys include mail-out questionnaires, email questionnaires, telephone interviews, and personal interviews. Despite a widespread perception that surveys are easy to conduct, good surveys need rigorous design, implementation and analysis. This requires substantial planning, time and effort. The most important step in designing a survey is to clearly define the question(s) the survey aims to answer The target population, measured variables and types of associations being investigated should be specific and unambiguous. Investigators should concentrate on what they 'need to know' rather than what would be 'nice to know'. During development surveys should be piloted to identify problems. The main goal when implementing a survey is to maximize the response rate to avoid misleading results. Evidence-based strategies, including brief personalized surveys with stamped return envelopes, can be used to maximize the response rate. A poorly conducted survey can lead to misleading or invalid conclusions and may undermine participation in subsequent surveys by the target population.