I am working on a paper with some colleagues. Trouble is that the data in the paper are very soft. Is there anything wrong with that? Is it wrong to publish data that are difficult to interpret and the suggest how e might interpret the data?
I wish I knew the answer. Trouble here is that the arguments are very statistical. If one does not reject the Null Hypothesis, does that mean that there is no difference between the data sets even if I, based on my judgment alone, feel that thee is a difference?
Imagine where the world would be if we insisted on such proofs for political decisions or worse made quarterbacks prove that their evlauations were correct?
Sunday, September 18, 2005
span.fullpost {display:inline;}
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment