I desperately need your help!! I have a huge dataset of 10+ million patient data entries and I have no idea how to start working with all that data.
The first problem is this: the data is in a SAS7BDAT format. I originally downloaded it off the CD's in a ASCII format, basically. I have no idea how to write a program in the editor that uses the variables/data from this SAS7BDat format. I want to start doing something simple - like, say, calculating the average birth weight of all the patients in the records, before moving on to something bigger.
I'm a total beginner to SAS and would appreciate some help!
1) get a copy of "The Little SAS Book" by Slaughter & Delwiche
2) the extension SAS7BDAT is a sas data set. You need to know a bit about it. Let us assume that it has a name like xxxx.sas7bdat
libname mydat "pathtoyourdata";
proc contents data=mydat.xxxx;
here xxxx is the name of your data set.
PROC CONTENTS will tell you about the data set. Read about variable names and how to use them in the little book.
3) PROC MEANS and PROC SUMMARY will give you a good start on calculations.
4) read about the obs=1000 option to limit data size during testing.