Hi, i think the below code will help you to get those missing dates in the final dataset. proc sql;     create table ae_ as select a.*,b.visit from ae as a left join assigned as b on     a.subjid=b.subjid where ((start<=visit<=stop) or (visit>=stop)); quit; Thanks, Jag ... View more

proc sql; create table want as select ae.id, ae.adverse, d.visit from ae left join drug d ae.subjid=d.subjid and ae.adverse between d.start_date and d.stop_date; quit; ... View more

Hi, Can you try this below? proc sql noprint; create table new as (select distinct put(leg,3.) as leg,treattxt, count(distinct sid) as cnt from have group by leg,treattxt having phase='active'   union all   select  '',"total", count(distinct sid) from have where phase='active' );    quit;    ... View more

Think about what the p value is saying: if it is less than 0.05, then there is less than one chance in twenty that a difference as large as the one observed would come about due to chance variability if the null hypothesis of no difference were true.  If it is less than 0.01, then there is less than one chance in one hundred that a difference as large as the one observed would come about due to chance alone.  It indicates how much "risk" there is in rejecting the null hypothesis of no difference. OK, that's the standard.  Now comes the part that doesn't answer your questions, but is where I get out a soapbox and make a speech.  All of the p values depend on a very strong assumption--a null hypothesis of no difference.  But in the real world, this could never be true.  NEVER.  It might be closely approximated to the level of your measurement instrument, but the probability of two population means being exactly equal can be shown through some pretty rigorous math to be exactly zero.  So p values are approximate tools to begin with, and their interpretation should never come down to whether a hypothesis is true or false, but how likely the difference observed could be due to random variation. Steve Denham ... View more