Hello, In a human-subjects experiment collaborators (A & B) communicated about how to categorize a number of multidimensional stimuli. Following their conversation, each collaborator sorted the stimuli into bins. This sort data was converted into square co-occurrence matrices, where 1 indicated that the row stimulus and column stimulus were placed in the same bin and 0 indicated that they did not co-occur. I would like to figure out how much information A transmitted to B and how much B transmitted to A; these transmissions are likely asymmetric. Is there any way, using R, to estimate asymmetric mutual information between the matrices? Should I be looking at some other metric entirely?
Thank you, John ______________________________________________ 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.
