SAS

Pharm and Oracle Clinical
Hi Dan, For a basic introduction to OC I found the following to be quite good: http://www2.sas.com/proceedings/forum2008/396-2008.pdf (there are lots of more advanced papers to be found as well) With regards to getting the date of the DCMs, try the following code: proc sql; connect to oracle(path=�...�); c... 18 Feb 2010 11:41

Getting Base Observation values
On Feb 18, 12:28 pm, procconte...(a)GMAIL.COM (SAS_learner) wrote:  Hello all, I am trying to separate Base lesion measurements  from main dataset and trying to merge it back to get base measurements next to remaining ones. In the Base data set I have 86 and Remaining dataset has 110 but when merging ba... 18 Feb 2010 09:26

Intergrating SAS and R via the SAS Universal ODBC Driver(UODBC)
Hi SAS-Lers, Below is an R script the creates a R dataframe called x from a SAS dataset called DMDEATH. The advanage of the UODBC s that you do not need to have the SAS ODBC server process running simultaneously and you can programatically open and close the ODBC connection from R. Also you do not even ne... 18 Feb 2010 05:02

Getting Base Observation values
Hello all, I am trying to separate Base lesion measurements from main dataset and trying to merge it back to get base measurements next to remaining ones. In the Base data set I have 86 and Remaining dataset has 110 but when merging back I am getting 93 obs. I tried Left and Right join but did not get what I a... 18 Feb 2010 03:57

PDO
Hi Can someone derive or explain the formula for PDO, points to double odds ? As per my understanding : ln(p/1-p) = y p/(1-p) = exp(y).---(1) Now say, this should be doubled ln(p/1-p) = y'' such that 2( p/(1-p) ) = exp(y''). --- (2) Dividing (2) by (1) 2 = exp(y'') /exp(y) ln(2) = y''-y I have ... 18 Feb 2010 03:57

PROC REPORT Question
Here is my code so far: data bob; input aa $ dqc $; datalines; 1 F 1 T 1 F 1 F 2 T 2 T 2 F ; run; proc sort data=bob; by aa; run; data bob2(rename =(n=fail)); set bob; by aa; n=0; if dqc = 'F' then n = 1; m=1; run; proc print data=bob2; run; proc report data = bob2 nowindows missing ... 18 Feb 2010 10:34

Has anyone used DBCS configuration
Hi Greg, Conversion from latin1 to others should be quite easy. You can declare the encoding in SAS datastep at the set statement. There should be a sascommunity tip on this as well. ------Original Message------ From: Greg Woolridge Sender: SAS(r) Discussion To: SAS-L(a)LISTSERV.UGA.EDU ReplyTo: Greg Woolridge ... 17 Feb 2010 20:11

Interesting post about SAS and the Pharmaceutical Industry on R-help
Hi All, http://n4.nabble.com/Use-of-R-in-clinical-trials-td1559402.html#a1559402 http://tiny.cc/EY0tK Regards ... 17 Feb 2010 19:03

dumping memory
Hi all, Is there any SAS function or procedure that cleans up memory space other than proc datasteps can be used to delete all temporary files in work library ? I'm using proc glm to go through more than 1000 variables to do stepwise selection but as it goes through all the variables, the real and cpu time in... 17 Feb 2010 20:11

means in long format
data have; input SUBJID $ TEST $ VALUE1 VALUE2; datalines; A1 ONE 3 1 A1 TWO 2 2 A1 THREE 6 5 A2 ONE 4 3 A2 TWO 5 4 A2 THREE 8 9 ;;;; run; data want(keep=subjid value1 value2 test); do _n_ = 1 by 1 until (... 18 Feb 2010 10:34