Bias Assessment in Progression-Free Survival Analysis Using Interval-Censored Methods - Interval-Censored-Time-to-Event Data: Methods and Applications - page 302

through the collaborative efforts of the PhRMA PFS Working Group. They
would also like to thank Beat Neuenschwander and Emmanuel Zuber at No-
vartis Pharmaceuticals for their review and comments.
Appendix: SAS Programs
An SAS macro ( %ICSTEST ) for the generalized logrank test proposed by Sun
et al. (2005) can be downloaded at http://support.sas.com/kb/24980 , where
one can find detailed instructions for using %ICSTEST and some additional SAS
macros for interval-censoring analysis. One can call the SAS macro %ICSTEST
using the following syntax:
%ICSTEST(version,data=_last_,left=,right=,group=,freq=,errortype=1,
rateconv=1e-7,mRS=50,seed=8375,rho=0,gamma=0);
The following arguments may be listed within parentheses in any order,
and separated by commas:
DATA=SASdatasettobeanalyzed.DefaultisDATA=_last_.
LEFT=Anumericvariablerepresentingtheleftendpointof
thetimeinterval.
Left-censoredobservationshaveamissingvalueoravalueof0.
RIGHT=Anumericvariablerepresentingtherightendpointof
thetimeinterval.
Right-censoredobservationshaveamissingvalue.
FREQ=Asinglenumericvariablewhosevaluesrepresentthefrequencyof
occurrenceoftheobservations.
GROUP=Avariableidentifyingdifferenttreatmentgroups.
ERRORTYPE=Convergencecriteriontobeused.
1--Themaximumoftheclosenessofconsecutiveestimates,
2--Theclosenessoftheloglikelihoodfunction,
3--Thegradientoftheloglikelihoodfunction,