Confounding
- unaccounted confounding variable - treatment and the control group differ in some third variable which influences the response that is being studied
- e.g. a hospital may select healthier subjects for surgery
Data Collection Bias
When we conduct a experiment or survey, there are many possible sources of possible bias. For example:
- sampling bias - sample is collected in such a way that some members of the intended population have a lower or higher sampling probability than others
- observer bias - when the participants or investigators are aware of the identity of the 2 groups, and so we can get bias in either the responses or evaluations
Bias of an Estimator
The bias of an estimator is the difference between an estimator’s expected value and the true value of the parameter being estimated.
Interpretation
- correlation implies causation
- ecological fallacy - the interpretation of statistical data that occurs when inferences about the nature of individuals are deduced from inferences about the group to which those individuals belong
- reporting bias - selective revealing or suppression of information
Probability Biases
- Gambler’s fallacy
- base rate bias
- also called prosecutor’s Fallacy, can be viewed as confusion of the probability
with the probability
- also called prosecutor’s Fallacy, can be viewed as confusion of the probability
- Texas sharpshooter fallacy and clustering illusion
- multiple comparisons problem