LAE

Note: This was originally posted by an inactive account. Content was preserved by moving under an admin account.

Originally posted by: tessam

Hi All,

Today I was asked to create a random sample for a survey that my department will be providing. I have used the sample node before and when I compared it to the sample feature in SPSS, they are within .01% of each other, regarding distribution based on a particular account attribute.

My supervisor was wondering what the logic behind the sample node was; we'd like to have a better understanding of the sample node and I wasn't able to immediately find the code.

Thanks!

Note: This was originally posted by an inactive account. Content was preserved by moving under an admin account.

Originally posted by: ryeh

Hi, Tessa. I'm not sure how much detail you're looking for, but we rely on a random number generator. So let's say you have ten records and you want a sample size of three. Each record is scored from 0-9 (0 through n-1, where 'n' is the number of records). The score is then sorted, and the top three records are returned. Did you want to know how the random number generator works?

By the way, you could actually open up the 'Sample' node by opening 'core.brg'. Go to Graph -> Edit Base Libraries -> select 'core' -> Open.