Sampling in epidemiological research: issues, hazards and pitfalls
- PMID: 27087985
- PMCID: PMC4817645
- DOI: 10.1192/pb.bp.114.050203
Sampling in epidemiological research: issues, hazards and pitfalls
Abstract
Surveys of people's opinions are fraught with difficulties. It is easier to obtain information from those who respond to text messages or to emails than to attempt to obtain a representative sample. Samples of the population that are selected non-randomly in this way are termed convenience samples as they are easy to recruit. This introduces a sampling bias. Such non-probability samples have merit in many situations, but an epidemiological enquiry is of little value unless a random sample is obtained. If a sufficient number of those selected actually complete a survey, the results are likely to be representative of the population. This editorial describes probability and non-probability sampling methods and illustrates the difficulties and suggested solutions in performing accurate epidemiological research.
Conflict of interest statement
References
-
- The Straits Times. Scotland decides: economic risks drove voters to reject independence, poll shows. 20 September, 2014.
-
- Williams M. Full indyref survey reveals young voters voted no and only 25-39 age group said yes. Herald Scotland; 24 September 2014.
-
- Spitzer RL, Endicott J, Fleiss JL, Cohen J. The Psychiatric Status Schedule: a technique for evaluating psychopathology and impairment in role functioning. Arch Gen Psychiatry 1970; 23: 41-5. - PubMed
-
- Harper D, Barry D. Estimated prevalence of psychiatric disorder in a prison population. Abstr Crim Sociol 1979; 19: 237-42.
-
- Fazel S, Seewald K. Severe mental illness in 33 588 prisoners worldwide: systematic review and meta-regression analysis. Br J Psychiatry 2012; 200: 364-73. - PubMed
LinkOut - more resources
Full Text Sources
Other Literature Sources