Hi, I am still new to R and have, in spite of searching all over, found no "understandable" documentation for how to join two (or more) frequency tables. Why would I want to do that and what do I mean by "joining" ? Let me try to explain:
I have a diagnosis form that allows registration of up to three diagnosis codes on animals with birth defects, like this: father.id diagnosis diagnosis2 diagnosis3 a 100 200 300 b 200 100 340 .... and so on. As you can see the same diagnosis can show up in either field (1, 2 or 3). I am interested in how many times each diagnosis shows up for offspring from the same father (looking at inheritance) The best I have come up with so far is table(father.id, diagnosis) table(father.id, diagnosis2) table(father.id, diagnosis3) which gives me the frequency counts for each combination of father.id and diagnosis code and then I manually join these tables together by cutting and pasting (in Excel!!). Oh the horror! The resulting table looks like this though and gives me what I want: father.id 100 200 300 340 a 1 1 1 0 b 1 1 0 1 ..... This is incredibly cumbersome and therefore I want to find a way of doing this completely in R script so that I have the code ready when I need it again. So far I have tried with several varieties of merge() and xtabs() but have given up. I can not afford to spend more time on this and as a last resort I'm hoping anyone here could pass me a tip. I use R for modelling but I am so far finding it hard to wrap my head around it when it comes to the pre-analysis data manipulation like this as I am not proficient enough (i.e. do not quite understand) in the language and data structure intricacies. Regards, Jan [[alternative HTML version deleted]] ______________________________________________ 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.