Initial  data  analysis  and  model  fitting  were  conducted using  the  first  2 years  of  data  (January  1,  2005,  to December 31, 2006), here after referred to as the training set. Daily patient counts for each facility for the period January 1, 2007, to March 31, 2007, were held out of  the  modeling  process  to  empirically  evaluate  the post sample  forecast  accuracy,  here after  referred  to  as the  validation  set.  Forecast accuracy was assessed at horizons ranging from 1 to 30 days in advance.  Data from each facility were treated as individual time series and analyzed and evaluated separately.