Measurement bias refers to any systematic or non-random error that occurs in the collection of data in a study. Another broad term for this type of bias is “detection bias”.
In some cases, the differential in observations might be because of an unseen confounder. More commonly, measurement bias arises from a lack of blinding.
There are a number of different types of measurement bias:
- Recall bias
- Observer bias
- Attention bias (Hawthorn effect)
- Expectation bias
- Verification or workup bias
- Insensitive measurement bias
- Lead time bias
- Response bias
This post is part of a series of posts on bias in medical research. You can find the whole bias catalogue here.