Hi Everyone,   I'm doing some ARIMA forecasting and am finding the need to take the first difference of my variable of interest so I can get a stationary series.  My variable of interest is hospital admissions. I have two questions:   1) If I have a numeric covariate, that is also time related, such as membership over time, do I need to take the first difference of that covariate?   2) If the answer to #1 is yes, how do I accomplish that in a PROC ARIMA statement?   Thank you!     proc arima data=arima_input3 plots=all; identify var=admit_count (1) crosscorr=(memberships) nlag=53; estimate q=2 input=(memberships); forecast lead=106 interval=week id=admit_date out=results; run; ... View more

Hi,   I'm new to use Enterprise Miner, and Predictive Modeling in general, but have a stats background.  I have a dataset with about 100 inputs and a target variable with a discrete Poisson distribution.  I'd like to know:   1) Can I use a decision tree model in EM to help me narrow down inputs for a Poisson Model?   2) Can EM model a Poisson distribution, without using the "Rate Making" node (I don't have this node)?   Please let me know what additional information you need to help me answer my questions.   Thank you! ... View more

Hi, I have a SAS data set with one column in character format that looks like this: ID 239438233 485574323 048573493 495840312 I need to export it to a .txt file, and have it look the same as above when opening the text file.  Unfortunately when I export it and open it in notepad I can't get each ID on its own line. When I export the file I get: 239438233485574323048573493495840312 The 4 IDs come out as on long string.  Here's the code I'm using: PROC EXPORT DATA=USER_IDS;       OUTFILE= "&MYLOCATION/IDS.TXT"      REPLACE;      PUTNAMES=NO; RUN; Any ideas on modifications I can make to this block of code to get the desired output? Thank you! ... View more

I have this code below which user PGStats provided me in an answer to a different question a few weeks ago.  It worked great for helping me learn how to calculate a moving sum.  Now I'm wondering, how would I adjust the code below to do a moving sum that, instead of a three month moving average, was a year to date average based on the year_month field below. For example if YR_Month=201402 for the given record, it would give me the moving sum of the Value field through the first two months of the year.  Basically my transformout=(movsum n) would have to have a dynamic "n" based on the month in the year_month field.  Anybody have an idea on how I can use a dynamic for my movesum?  Thank you!!! data have; input Year_Month State $ Value; datalines; 201401 CA 11 201402 CA 12 201403 CA 11 201404 CA 12 201405 CA 14 201401 TX 12 201402 TX 14 201403 TX 10 201404 TX 11 201405 TX 16 ; proc expand data=have out=want; by state; id  year_month; convert Value=Rolling3 / transformout=(movsum 3 trimleft 2); run; ... View more