01/18/2012:  Version 0.9.9

   o Added coxphERR to calculate Heller's explained relative risk.
   o Fixed NaN bug in toxbdry when priority="alt" is used.

09/13/2011:  Version 0.9.8

   o fixed bug in print.gsdesign for binomial case (p1,p2 instead of pC,pE)
   o ROC functions now check that there are at least one each of status=0,1

04/27/2011:  Version 0.9.7

   o fixed fortran code to address gfortran-4.6 warnings
   o added ktau a faster implementation of cor(x, y, method="k").
     not in NAMESPACE. Should be called using clinfun:::ktau

04/25/2011:  Version 0.9.7

   o bug fix: roc.area.test integer overflow for large nn*nd.
   o use sort function to speed up roc curve and area estimation.

03/24/2011:  Version 0.9.6

   o bug fix: roc.area.test gave NaN as the statistic and p-value when
     the markers are identical. Changed it to 0.

03/09/2011:  Version 0.9.5

   o bug fix: gsdesign funtions not returning the sample size / # events.

02/24/2011:  Version 0.9.4

   o twostage.inference for umvue, p-value and CI for 2 stage design.

12/06/2010:  Version 0.9.3

   o ph2simon was testing whether dim is null for feasible solution.
     Replaced with nrow == 0 since it is now possible to have 0 rows.

11/05/2010:  Version 0.9.2

   o Added functions to compute and plot the empirical ROC curve.

11/03/2010:  Version 0.9.1

   o Added functions for the area and permutation tests to compare ROC.
   o Checks that min.diff is greater than 0 in pselect.

11/01/2010:  Version 0.9.0

   o Added a non-binding futility boundary to gsdesign

04/16/2010:  Version 0.8.10

   o variable names for returned data.frame in coxphQuantile
   o examples in coxphQuantile & coxphCPE use status==2

04/09/2010:  Version 0.8.9

   o check Rversion so that coxphCPE works for any version (see 0.8.9)

04/07/2010:  Version 0.8.8

   o Change coxphCPE to reflect the fact that model.matrix.coxph doesn't 
     have an intercept term.

02/25/2010:  Version 0.8.8

   o Added the function or2pcase

11/20/2009:  Version 0.8.7

   o Fixed the 0/0 bug in the revised pselect

11/17/2009:  Version 0.8.6

   o Changed Venkat's affiliation to MSKCC.
   o Fixed pselect to calculate the selection probability correctly when
     only one treatment exceeds the min.resp threshold.

07/10/2009:  Version 0.8.5

   o Changed the Jonckheere-Terpstra statistic such that large value is 
     indicative of increasing group locations and small for decreasing.
     Function warns that p-value is based on approximation for tied data.

12/02/2008:  Version 0.8.4

   o Added functionality to pselect.  It can do unequal sample size for 
     the case of two treatments.  min.diff can be specified as a rate 
     instead of number of responses.  Output element names changed to be
     more descriptive.

11/18/2008:  Version 0.8.3

   o Fixed the bug CPS.ssize. call inside used fixed alpha, power & r.

09/18/2008

   o Fixed the bug in the approximate one-sided p-value of Jonckheere 
     test. wrong tail was used. 

06/20/2008:  Version 0.8.2

   o toxbdry allows the error threshold to prioritize when the sample 
     size is too small to have both satisfied.

06/17/2008:  Version 0.8.1

   o Fixed gsdesign to allow for fixed sample designs.  Help file fixed.

05/23/2008:  Version 0.8.0

   o New version with one new function power.lehmann.design