[R] Scatterplot and Causality

Lorenzo Isella lorenzo.isella at gmail.com
Mon Apr 22 22:15:58 CEST 2013


On Mon, 22 Apr 2013 17:27:05 +0200, Robert Baer <rbaer at atsu.edu> wrote:


> It strikes me that this is not a particularly productive approach to  
> causality, particularly in an observational setting.  You would need to  
> design an experiment where you had a known manipulation of an  
> explanatory variable and studied the change in a response variable, and  
> then, you came back with the roles  reversed.  I don't think R or indeed  
> any statistical package can help you here.
>

I certainly agree, but here we are not planning an experiment: we have  
some data sets that were collected having something totally different in  
mind and we wonder if we can extract any info about causality from them.
Cheers

Lorenzo



More information about the R-help mailing list