In the description of the statistical models that relate onevariable to the other we used terms that suggest a causalityrelation. One variable was called the "explanatory variable" andthe other was called the "response". One may get the impressionthat the explanatory variable is the cause for the statisticalbehavior of the response. In negation to this interpretation, somesay that all that statistics does is to examine the jointdistribution of the variables, but casuality cannot be inferredfrom the fact that two variables are statistically related.
What do you think? Can statistical reasoning be used inthe determination of causality?
As part of your answer in may be useful to consider a specificsituation where the determination of casuality is required. Can anyof the tools that were discussed in the book be used in ameaningful way to aid in the process of such determination?
