Ensure accurate data collection and risk factor ascertainment. If not possible, $\textit{select}$ features keeping in mind the biasing factor(s).

Prevention of Ascertainment Bias

Ascertainment Bias : Image

Incomplete ascertainment of risk factor in control group leads to underrepresentation of the factor, and an inaccurate study.

University of Michigan - Ann Arbor

The paper focusses on case control studies done in a clinical setting. Thus it expands on types of biases generated in this environment. 
The types elucidated are : 
1. Referral Bias
2. Ascertainment Bias
3. Berkson Bias
4. Hospital Control Bias

Types of Bias outlined in paper

Sutton-Tyrrell, K. (1991). Assessing bias in case-control studies. *AHA Journals*. 22(7),  938-939 from [www.ahajournals.org/doi/pdf/10.1161/01.STR.22.7.938 .](https://www.ahajournals.org/doi/pdf/10.1161/01.STR.22.7.938 .) 

Assessing bias in case-control studies.

Occurs when referral patterns within a community causes the hospital population to be a misrepresentation (either overrepresentation or underrepresentation) of the general population.

Referral Bias

Ascertainment Bias

Also called admission-rate bias, refers to the fact that people with more than one conditions are more likely to be admitted than people with just one condition. This increases the likelihood of the chosen risk factor to be present - which causes an overrepresentation in the hospital sample.

Berkson Bias

If the cause of admission to the hospital and the risk factor are related, this could skew the study and cause an overrepresentation of exposed factors. 

Learn Before

Related

Learn After