Ascertainment Bias

In scientific research, ascertainment bias occurs when false results are produced by non-random sampling and conclusions made about an entire group are based on a distorted or nontypical sample. If this is not accounted for, results can be erroneously attributed to the phenomenon under study rather than to the method of sampling. It is one of the most common reasons that researchers in the medical, social, or biological sciences may discover an association or correlation that does not actually exist. Ascertainment bias may be easy to recognize or difficult to detect.

Examples

For example, to find the male/female ratio in a country it is not necessary to count everyone in the country, but selection of a statistical sample of the population will be adequate. The way the sample is selected can influence the result. For example, if the residents of a housing project for elderly persons was counted, the result could be biased in favor of females, who statistically live longer than males.

A simple classroom demonstration of ascertainment bias is to estimate the primary sex ratio (which we know to be 50:50) by asking all females students to report the ratio in their own families, and comparing the result with the same question asked of male students. The women will collectively report a higher ratio of women, since the survey method ensures that every family reported has at least one female child, and is biased by families with only a single, female child (themselves). The men will report a higher ratio of men, for the complementary reason.

Ascertainment bias is important in studying the genetics of medical conditions, since data are typically collected by physicians in a clinical setting. The results may be skewed because the sample is of patients who have seen a doctor, rather than a random sample of the population as a whole. Berkson's paradox illustrates this effect.

Often, proper design of experiments can minimize this effect. Another way to deal with this effect is to take the non-random sampling into account when analyzing results.

See Also

BiasDefinition

References