@MarissaMarais wrote:   I have a feeling that the apps on our PCs are completely locked down for editing ... Let's not jump to conclusions here.   To edit a copy (not the original) of your config file, that you have placed in a folder that you have write access to: Open an editor, such as Notepad or Notepad++ (but not Microsoft Word) and then use the File->Open menu command and select the config file. ... View more

Many people here refuse to download file attachments.   Please paste whatever text you want us to see into your reply. ... View more

@Shailesh_R_T wrote: Hey @PaigeMiller i am beginner, currently learning SAS basics. Even i don't have solution for this, i tried with proc print it worked out but still don't know if its the right way, if anyone came across solution for this please approach or discuss I asked to see the log. If there are errors in the log, SHOW US the log! Even if you are a beginner, you can explain better and provide us with more information (which we have specifically requested). ... View more

@Tom wrote: If you are changing the COMMAND you run there is no need to modify the CONFIG file since you can add the -altlog option to the COMMAND. True and the reason I do it the other way is that there is a limit on the number of characters you can enter into the Properties field, and so if you want a lot of characters in the -ALTLOG file name you may hit that limit, and have to then modify the CONFIG file. Plus, this allows a lot of other additions to the CONFIG file if desired, which also might cause the command to exceed the character limit. ... View more

Step 1. Copy the CONFIG file to a folder where you have write access, let's say the folder name is C:\users\Paige\SAS_Startup Step 2. Edit the CONFIG file and add the proper -ALTLOG command into this CONFIG file, and save the file Step 3. Copy the shortcut that launches SAS to the same folder as the new CONFIG file Step 4. Right click on the shortcut, select properties, edit the properties to change the part after -CONFIG to "C:\users\Paige\SAS_Startup\sasv9.cfg" (or whatever folder and file name you used in Step 1). Click on OK Step 5. Double-click on this new shortcut (do not use the old shortcut if you want this ALTLOG to work) to launch SAS ... View more

Yes, IT can and will lock down these files.   I made a copy of the CONFIG file and a copy of the shortcut that launches SAS, and placed these copies in a place where I can make changes to them. The copy shortcut properties needs to point to the copy of the CONFIG file you have made with the ALTLOG command included. ... View more

/* UNTESTED CODE */ data want;     set have;     person=personA;     personcode=personAcode;     output;   person=personB;     personcode=personBcode;     output;     person=personC;     personcode=personCcode;     output;     keep lockerid locations person personcode; run;     Please from now on provide data as working SAS data step code (examples and instructions). Also, I'm sure you know this, but SAS data sets cannot have variables with spaces in the variable name. ... View more

I think we need to hear from @Shailesh_R_T about what the problem is, in much more detail. Everyone guessing different things isn't really a good approach. ... View more

Please do not type in ALL CAPITAL LETTERS.   When you get errors in the log, then please show us the entire log. In fact, please do that for this problem and all future problems. Do not paraphrase error messages.    When I run your code, I get no errors at all.     ... View more

@David_M wrote: Ok, thanks for the clarification. So will PLS also generate regression coefficients that will map my 35 variables to the Y response in its model? Yes ... View more

@SASPreK wrote: I have tried Price sql; Create table want as Select* From have Group by id Having dt=max(dt); Quit; But it does not give the output based on my specific requirements. PRICE SQL ??? That won't work.   Also, you didn't tell SQL to do this for each year. How about this?   proc sql; create table want as select * from have group by id,year having dt=max(dt); quit;     ... View more

@David_M wrote: My original goal (which I hope I clearly stated and apologies if I didn't) was to reduce the number of highly correlated 35 mixed type variables to a lesser number that are not or much less correlated with each other. Won't the PROC CORR function with the /corrb option show correlation coefficients that could be used to target high correlation variables for elimination? Maybe, maybe not. You could, for example, remove one of the two variables which have coefficients highly correlated with each other. You may remove the best predictor of the two, which would not be good. But multicollinearity takes other forms, such as a linear combination of three or more variables produces an almost constant result. In that case, maybe the correlation of the coefficients won't show that because it is looking at pairwise correlations, but this multicollinearity cannot be seen pairwise, it can be seen if you look at the three or more variables. This type of multicollinearity will impact the quality of the model fit, but may not be seen from pairwise correlations.   Won't the PLS procedure you suggested do something similar?   No, that's not what PLS does. PLS leaves all the variables in the model, and fits the model in such a way that it is robust to the effects of multicollinearity. In the paper by Tobias, he has 1,000 predictor variables, and the PLS model uses all 1,000 variables, and Tobias decides that the model is useful.     ... View more

@David_M wrote:   Are they saying (fingers crossed) that I can define all variable types (binary, categorical and continuous) in this statement and all is golden? I see "Sex" as binary, "Race" and possibly "Treatment" as nominal. Not sure what type of variables Group and Replication might be. SAS has only two types of variables, character and numeric. SAS modeling PROCs have either categorical or continuous variables.   Are they saying (fingers crossed) that I can define all variable types (binary, categorical and continuous) in this statement and all is golden?   You can interpret the variables as binary, categorical or continuous as you wish. At a certain point, PLS is no longer optimal (if it ever was optimal) and you may want to consider other modelling methods, as all is not golden in some situations. Which is true of any modeling approach. ... View more

So will the PROC logistic example you've shown accomplish the same goal of eventually producing a set of de-correlated variables for my model?   PROC LOGISTIC does not produce de-correlated variables. The variables remain correlated. (You can choose to remove certain variables from the model with the goal of having the multicollinearity have less effect on the model fit, but the ones that remain will still be correlated)   That's really to goal of this thread, as I have understood it. We want to find estimation methods that are less affected by collinearity, not the removal of collinearity which isn't possible. ... View more

I don't know what handling categorical values with missing values has to do with this thread.   Clearly, PLS has been modified to include categorical predictors, as SAS has been able to do it for at least 20 years now. I don't know if SAS gets the credit for this invention, or if it had been published previously elsewhere. ... View more