Date:         Tue, 24 Oct 2006 05:43:22 -0400
Reply-To:     Peter Flom <flom@NDRI.ORG>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Peter Flom <flom@NDRI.ORG>
Subject:      Re: Basic stat question
Comments: To: aknas_a@YAHOO.COM
Content-Type: text/plain; charset=UTF-8

>>> Aknas Dii <aknas_a@YAHOO.COM> 10/23/06 9:26 PM >>> wrote
<<<
Is there a way that statistically you can determine the cut-off point.
Ex. I have a large data set looks like this ( millions of records):

Code            total_sub           Total                   percent
GGGG         10                 20                      50%
YYYY              1                  10                      10%
KKKK             15                  20                      75%
PPPP             44                  300                     15%
HHHH              9                  9                       100%
FFFF              123                123                     100%
BBBB              22                 234                     9%
…..

The extract: I want remove my observation the record’s, that doesn’t
have
enough data available based on total_one.

For instance if assign the cut-off ( total_sub >10) point, then I will
only have a these record’s in my analysis.

Code         total_sub            Total                   percent
KKKK      15                20                     75%
PPPP             44                300                    15%
FFFF             123               123                    100%
BBBB             22                234                    9%

Here is my question. Is there is a way to determine the cut-off point
statistically?
>>>

That doesn't have enought data for what purpose?
What are you trying to do?

What is the data, and how did you get it?
What do the variables mean?

Please write back to SAS-L with a description of what you are trying to
do, and someone may be able to help.  Maybe even me.

Peter