Model Training & Adaptation
Confounding
Another factor affecting both a possible cause and its result, making their relationship easy to misread.
Example
An apparent link between a training course and performance also reflects who volunteered.
Why people use it
It helps explain why an apparent cause-and-effect relationship may be misleading.
What you'll hear
“Could a third factor explain both changes?”
What this means for you
Ask which alternative explanations the analysis has addressed.
Can you control it?
No
No direct control. This describes a wider issue, concept or result rather than something you can simply switch on or off in a tool.
Common questions
- Does a predictive AI system automatically resolve confounding?
- No. Predicting correctly does not establish which factor actually caused the result.
- Can a hidden factor affect the result?
- Yes. Important influences may be absent from the information collected.
- Does collecting more of the same information remove the problem?
- Not necessarily. More examples do not automatically reveal an unmeasured influence.