What Regression fallacy is
Regression fallacy is an error in reasoning where a person assumes that because something has returned to its original state after a period of change, the change that occurred must have been responsible for the current state. It is also known as regression to the mean.
Regression fallacy usually occurs when a researcher draws a causal inference from data that could have multiple explanations.
Steps for Regression Fallacy:
-
Identify the data or event that has changed over time.
-
Determine the underlying causes of the change.
-
Consider any other possible explanations for the change.
-
Examine the data closely to determine whether the change is due to the hypothesized cause or some other factor.
-
If the data suggests that the change is likely due to some other factor, then the regression fallacy is present.
Examples
- Assuming that a change in one variable is caused by a change in another variable without considering other potential factors.
- Assuming that a correlation between two variables implies causation.
- Assuming that because a regression line passes through the data points, the relationship between the two variables is causal.
- Assuming that the magnitude of the coefficient of determination (R2) is a measure of the strength of the relationship between two variables.