Apps

🧪 This platform is in early beta. Features may change and you might encounter bugs. We appreciate your patience!

Information Bias

Also Known As: Measurement bias Observation bias Misclassification bias
Statistical Error ID: information_bias

Definition

Information bias is a systematic error arising from how data is obtained, recorded, or classified in a study. Unlike random measurement error, information bias distorts results in a consistent direction. It encompasses a family of biases including recall bias, observer bias, and misclassification, all of which compromise the validity of study findings by systematically distorting the relationship between variables.

Examples

In a case-control study of childhood leukemia, parents of sick children recall and report household chemical exposures more thoroughly than parents of healthy children, systematically inflating the apparent association between chemical exposure and disease.

In a study on the link between diet and colon cancer, patients diagnosed with cancer are interviewed extensively about their past eating habits, while healthy controls fill out a brief self-administered food frequency questionnaire. The asymmetry in data collection depth means dietary risks are more thoroughly captured for cases, exaggerating the apparent diet-cancer association.

A workplace injury study collects data from accident reports filed by supervisors. Minor injuries in high-visibility departments are carefully documented, while similar injuries in remote field sites are often not formally reported. The resulting data makes office environments appear comparatively safer, not because they are, but because reporting practices differ.

Verification Steps
Verification Steps
Binary yes/no questions that an AI must answer to detect a reasoning pattern in a text.
Each of the 452 aspects has verification steps — simple yes/no questions designed to systematically detect whether a pattern appears in a text. For ad hominem: "Does the argument attack a person rather than their claim?" For false dichotomy: "Are only two options presented when more exist?" This ensures consistent, reproducible analysis.

Binary (yes/no) questions an LLM must answer to identify this aspect:

  1. 1

    Is there a systematic flaw in how the data was collected or recorded?

    Type: binary
  2. 2

    Could the measurement method differ systematically between comparison groups?

    Type: binary
  3. 3

    Is there potential for misclassification of exposure or outcome status?

    Type: binary
  4. 4

    Could the data collection process itself have introduced distortion into the results?

    Type: binary
Deep Dive
The expandable detail section on each aspect page with examples, psychology, and counter-strategies.
The Deep Dive section provides in-depth information about each aspect: a real-world example showing the pattern in action, an explanation of why it works psychologically, practical advice on how to counter it, alternative names, and links to related aspects.

Hierarchical Context