On Mon, 22 Apr 2013 17:27:05 +0200, Robert Baer <rb...@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 ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
