I am trying to convert a character variable to a numeric using the following code:   data mva_jasper4; set mva_jasper3; payorPrice_num = input(payorPrice, BEST32.); run; However I am getting multiple lines of this error: NOTE: Invalid argument to function INPUT at line 10580 column 22. MRN=4431155 name=Freda Snedden serv_date=10FEB2017 program=Auto Insurance Company - MVA site=Ottawa description=IE | Homesite Assessment Code=IXXAC intake_flag=0 intake_form=0 block1=0 block2=0 block3=0 dc=0 migext=0 monitor=0 payorPrice=1,448.50 supp=0 payorPrice_num=. _ERROR_=1 _N_=38 I tried googling this but I don't think I understand what is actually wrong or how to solve this.   Can any suggest how I can fix this? ... View more

I just completed a left join using proc sql, however I would like to see what did NOT merge.   here is the code I used:   proc sql; create table conc_merge as select* from conc_tx_base as x left join conc_dados as y on x.mrn=y.mrn; run; How can I see what didn't merge from Y (conc_dados)?   If it can be spit out in another dataset or table that would be awesome.   Thank you ... View more

I know this is a really stupid question. I've googled it but I'm havin trouble understanding what the by statement actually does in a data step!   I know that you need to proc sort first by the variable...   but what is it actually doing?   So for example in a data step like this:   data test; set test; by mrn program serv_date provider amount description; firstmrn = first.mrn; firstdesc = first.description; if firstdesc = 0 then delete; run; What is the by mrn program sev_date etc actually doing? How is it different from the proc sort?   please help! thank you! ... View more

I am trying to run fisher's exact test to see if there are any differences between two categorical variables.   var # 1-->Collection_Center=5 categories var # 2-->Education= 7 categories   B/c the frequencies in the cross tabs for these 2 variables were < 5, I decided to run a Fisher's exact est instead of a chi-square test for independence.    The following is the code I put into SAS to run fisher's exact test:     proc freq data=baseline_Characteristics; tables collection_center*ca_education/fisher; run; However, I received this warning from SAS:   WARNING: Computing exact p-values for this problem may require much time and memory. Press the system interrupt key to terminate exact computations. And sure enough it took so long that I had to stop it.   I have two questions regarding this situation:   1. Can anyone please confirm that I am indeed running the correct statistical test?  2. If I am running the correct test why is it taking so long in SAS and what can I do about it? Am I doing something wrong?   please help!   ... View more