0:00You can see here I have Stratified switched
0:03on and it's actually working on the default
0:04column in my data set.
0:06Essentially the default column describes
0:07how many people have defaulted on payments.
0:10So if I actually go back to clean step
0:12number one and I go to the default column
0:14you'll see that I have an equal
0:16representative split of my data.
0:18Which means in Tabulate Prep when I'm
0:19working on this I can keep the sampling
0:21behavior on but still have everything
0:23performant and easy.
0:25Well what does it look like if I disable
0:27Stratified Sampling? Let me show you. Here
0:30I have 50 records from each and the default
0:31payments.
0:32Now if I go to the credit data and I go to
0:34data sample and then I switch off Strat
0:36ified Sampling and go back to Quick Select
0:40which is the default method.
0:41Now I still have 100 rows coming in but if
0:43I go back to clean one you can see there's
0:44100 rows there.
0:46But over here on the left hand side the
0:48default percentage is now split. It's gone
0:50back to represent what was originally in
0:52the data set.
0:53And so this allows you to work more easily
0:55and quickly in Tabulate Prep.