| Hand, D.J. (1998). "Data mining: statistics and more?". The American Statistician, 52, 112--119. |
....sets create new problems for statistical analysis, because none of the usual textbook hypothesis are expected to be true. We expect clustering of outliers and masking, nonstationarity, dependency among observations, selection bias, errors in variables, as well as other measurement problems (see Hand, 1998 for an excellent description of these problems) A consequence of this is that different models are supposed to hold in different regions of the parameter space and also at each point we have several different models which can generate the data. The Bayesian paradigm is a flexible tool in order ....
Hand, D.J. (1998). "Data mining: statistics and more?". The American Statistician, 52, 112--119.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC