About dcruik

dcruik · ‎09-28-2015

The code below will do what PaigeMiller's code is doing, except this will give you the same value for Sort_tranx if the ID and Date are the same. Hope this helps! data have; input ID Date; format Date mmddyy10.; informat Date mmddyy10.; datalines; 34532 01/01/2015 34532 02/03/2015 34532 05/06/2015 34532 01/01/2015 36978 01/02/2015 21562 01/01/2015 21562 01/02/2015 21562 01/03/2015 21562 01/04/2015 21562 01/05/2015 ; run; proc sort data=have; by ID Date; run; data want; set have; by ID Date; Date_lag=lag(Date); If First.ID then Sort_tranx=1; Else If First.ID=0 AND Date=Date_lag then do; Sort_tranx=Sort_tranx; end; Else Sort_tranx+1; Drop Date_lag; run;

dcruik · ‎08-19-2015

There are a couple of ways to approach this. One way would be using the FREQ procedure on Age vs Food Options and test for associations (or on Active or Gender vs Food Options, etc... whatever you would be interested in). There are some key words to use in the options to test for associations between class variables. You could also just look visually by plotting the different Food Options vs the binary variables such as Age or Gender and determine if there is a change in any of the classes for any of the binary variables. Not an actual statistical test, but sometimes looking at plots visually will give you an idea of what could be significant and what to test for significance. Hope this helps and is what you were looking for. Good luck! /*Tests of Association: Gender vs Food*/ proc freq data=input; tables Gender*Food / expected chisq relrisk measures cl; run;

dcruik · ‎08-13-2015

You can try and subset the data set with a FIND() function and use the modifier that ignores case.

dcruik · ‎08-13-2015

Similar to PhilC's, although it's in a macro form:

dcruik · ‎08-13-2015

You can actually use the TRANSPOSE procedure and then merge the two data sets. May have to change the reorder the columns to get it the way you want, but this will set it up initially for you:

dcruik · ‎08-11-2015

Mark is correct, you would want to use the Nodup here, as I re-read the the post. I originally assumed (looking at the example data set) that the Number was the same for each individual Name; however, it sounds like that may not be the case. Instead of eliminating duplicate Names with the Nodupkey, the Nodup will eliminate duplicate rows that have the same values in both the Name and Number field. The same with select distinct *, instead of select distinct Name in the SQL procedure. In case there are multiple Numbers for individual Names, otherwise my code will give you the first Number of each Name, and not all possible combinations of Names and Numbers. Hope that makes sense!

dcruik · ‎08-11-2015

You can use the SORT procedure or the SQL procedure to do this. Try the following: proc sort data=have out=want nodupkey; by Name; run; proc sql; create table want as select distinct Name, Number from have order by Name; quit;

dcruik · ‎08-11-2015

I would recommend checking out this book by Paul Allison that discusses Logistic Regression using SAS. In Chapter 3.5, he discusses about Multicollinearity and checking the diagnostics using this proc reg with the vif option. There's an example that he uses that could help bring to light the purpose of what you're trying to do, and how to apply it with your data. Hope this can be a better reference. https://books.google.com/books?hl=en&lr=&id=NF9kwF1lOF4C&oi=fnd&pg=PR3&dq=paul+allison+multicollinearity+with+logistic+regression&ots=zxuYlu2I2B&sig=gOGzfB0d9Zibr_OofjHBiMBnPlI#v=onepage&q=paul%20allison%20multicollinearity%20with%20logistic%20regression&f=false

dcruik · ‎08-10-2015

You could convert your character variables to numeric with dummy variables, then take that data set and run a proc reg with a VIF options that will give you the multicollinearity diagnostics by providing you with variation inflation factors (vif). Any parameter estimate with high variation will tell you that you may have some confounding issues. Not sure if that's what you're looking for exactly, but just one idea.

dcruik · ‎07-29-2015

Not sure if you're looking to return history transaction data fields or fields from the input file data, but this would be something that you may want using SQL subquery. Haven't tested it though: proc sql; create table want as select a.* from history_transaction_data as a having a.customer# in (select distinct customer# from input_file_data as b where a.process_date between b.start_date and b.end_date); quit; Hope this helps or gives you an idea!

dcruik · ‎07-21-2015

Xia, I was hoping you could answer a quick question I've had with remerging summary statistics back with the original data set. Does this cause an increase in I/O due to reading the data more than once (first to max the weight within the by group and second to merge back against the have data set)? Obviously, with a small data set like this it doesn't matter, but if it was with large data would it have much effect? Just wondering for the future... Thanks!

dcruik · ‎07-21-2015

Try the following code using BY processing: data have; input obs group count; datalines; 1 1 10 2 1 15 3 2 5 ; run; data want; do until (last.group); set have; by group; sum_count=sum(count,sum_count); end; do until (last.group); set have; by group; output; end; run; The first do until sum's all counts within each by group and the last do until outputs all observations from the original data set with the sum_count field. Hope this helps!

dcruik · ‎07-20-2015

Try the code below, I believe it will give you what you want if I'm understanding your description correctly: data have; input raceA$ raceB$ raceP$ raceI$ raceW$; datalines; N N N N Y N N N Y N N N N Y Y N N Y N N N N Y N Y N Y N N N N Y N N Y N Y N Y Y Y N N N N Y N N N Y Y N Y N N Y Y N N N Y Y N N Y ; run; proc contents data=have noprint out=have_contents (keep=NAME); run; %macro race; data _NULL_; set have_contents end=lastobs; call symputx(cats('race',_n_),NAME); if lastobs then call symputx('n',_n_); run; data want; set have; combine=catx(',',raceA,raceB,raceP,raceI,raceW); If countc(combine,"Y")>1 then do; raceO="Y"; subgrp_race="raceO"; end; Else do; %do i=1 %to &n; If &&race&i="Y" then do; raceO="N"; subgrp_race="&&race&i"; end; %end; end; drop combine; run; %mend; %race Hope this helps!

dcruik · ‎07-20-2015

Here's a way to do it in two steps, but there may be a way to use by processing and do it in one. data have; input ID$ Weight; datalines; UI_1 121 UI_1 122 UI_1 125 UI_2 99 UI_2 95 UI_3 101 UI_3 102 UI_3 107 ; run; proc sql; create table max_weight as select ID, max(Weight) as max_weight from have group by ID; quit; proc sql; create table want as select a.ID, max_weight as Weight from have a left join max_weight b on (a.ID=b.ID); quit; Hope this helps!

dcruik · ‎07-16-2015

If you mean how to create a variable named total that equals the total sum, then try this: proc means data=yash123 sum nway noprint; var monthly_sales; output out=west (drop=_TYPE_ _FREQ_) sum=Total; run; This will give you a data set called west with a variable called Total that is equal to the sum of all monthly_sales. If you want to see the sum of monthly_sales by Month, like Mark Johnson laid out, add a class statement to the means procedure with Month as your class: proc means data=yash123 sum nway noprint; var monthly_sales; class month; output out=west (drop=_TYPE_ _FREQ_) sum=Total; run; Hope that helps!

Online Status	Offline
Date Last Visited	‎08-14-2018 10:38 AM

Re: Chi-square test of association

Chi-square test of association

Re: left join usage

Re: left join usage

Re: Creating a Rolling 12 Month Total

Re: please help simplify some codes

Re: please help simplify some codes

Re: Proc Means Var Statement

Re: Variables Using Count

Re: Saving Formatted Text to a Macro Variable

Re: Chi-square test of association

Re: dataset creation

ODS Graphics trick: Plotting a turkey with SGPLOT

Re: Formatting question

Re: Help with proc export

Re: Create timestamp variable in sas

Re: Reverse Substr

Re: Reverse Substr

Re: macro function to output yesterday's data and 3 days of data if th...

Re: Creating a Rolling 12 Month Total

Re: Sorting and flaging transactions.

Re: Help with Binary correlated data!

Re: Extracting specific text from observation value

Re: first and last day of a month

Re: Want to have only unique rows

Re: Filter data so only relevant rows remain

Re: Filter data so only relevant rows remain

Re: evidence for confounding in proc logistic

Re: evidence for confounding in proc logistic

Re: Help with look up customer data in transaction history file.

Re: Changing Value of Variable to Largest Value

Re: Sum by group while maintaining individual observations in dataset

Re: Coding Race Variables

Re: Changing Value of Variable to Largest Value

Re: creating new variables in sas