4,781
edits
Changes
Jump to navigation
Jump to search
Line 3:
Line 3: − +
no one ever finished writing the "in other words..."
:a statistical relation between two or more variables such that systematic changes in the value of one variable are accompanied by systematic changes in the other [http://256.com/gray/thoughts/2004/20040511.html]
:a statistical relation between two or more variables such that systematic changes in the value of one variable are accompanied by systematic changes in the other [http://256.com/gray/thoughts/2004/20040511.html]
In other words, if you are studying two
In other words, if you are studying two variables and both change at the same time (consistently, veritably, and repeatedly), then you still cannot conclude one causes the other. Instead all you can say is that there is a link between the two, but the directionality of that link still needs to be established by negative testing. The design of the system must also be reexamined to assure that the design is not causing a systematic connection between the two variables, by implicit means.
==Correlation and causation==
==Correlation and causation==