Date:         Wed, 19 Apr 2006 09:09:56 +0100
Reply-To:     Jim Groeneveld <jim2stat@YAHOO.CO.UK>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Jim Groeneveld <jim2stat@YAHOO.CO.UK>
Subject:      Re: Looking for advise
Comments: To: David Fickbohm <davefickbohm@yahoo.com>
In-Reply-To:  <20060418193253.10310.qmail@web82314.mail.mud.yahoo.com>
Content-Type: text/plain; charset=iso-8859-1

Hi Dave,

  No you do not need equal sample sizes. And dependent on your hypothesis (difference from 0) and the expected membership duration in the samples (mean and sd) you might calculate minimum sample sizes. I don't know what you could expect, but it might well be that a sample of 18 is too small to show a significant difference. I would use both groups as they are (you don't have anything else) and perform the t-test to see if there is a significant difference in membership duration.

  Regards - Jim.
  --
Jim Groeneveld, Netherlands
Statistician, SAS consultant
home.hccnet.nl/jim.groeneveld


David Fickbohm <davefickbohm@yahoo.com> wrote:
    Jim,
  I have found the records that fit the criteria for both groups  There are 18 records in the group that subscribed and a 187 records in the other group.
I think I am correct in saying I need to pull a random sample of 18 from the larger non-subscriber group so the two groups are the same size.  Yes?
  Thanks
Dave

Jim Groeneveld <jim2stat@yahoo.co.uk> wrote:
    Hi David,

  Draw justified samples from both groups of people and determine the time how long subscribers stayed (e.g. in days). Then perform a T-test between both (independent) samples. Your test will be one-sided, only considering "better" for the group having got the offer.

  Regards - Jim.
  --
Jim Groeneveld, Netherlands
Statistician, SAS consultant
home.hccnet.nl/jim.groeneveld

David Fickbohm <davefickbohm@yahoo.com> wrote:
    Jim,
  Thanks for your questions.
  I must have not stated my situation well.
  I have data about people who accepted the offer
  I have data about people who were not given the offer.
  I am not sure how big each group is at this point.
  My goal is to determine if the people who accepted the offer remain members longer than those people who were not presented the offer.
  Thanks
  Dave

Jim Groeneveld <jim2stat@YAHOO.CO.UK> wrote:
  Hi Dave,

Questions, questions and more questions [;-). Briefly:
1. Why only a sample from the group not offered a discount?
2. How large are the groups you have?
3. What is your goal? Compare both groups? What expectation / hypothesis?
4. N of months stayed all right for presentation.
5. N, Mean, stddev, etc. good for hypothesis testing.
6. Right direction depends on what you want to do with the data.

Regards - Jim.
--
Jim Groeneveld, Netherlands
Statistician, SAS consultant
home.hccnet.nl/jim.groeneveld


On Mon, 17 Apr 2006 14:08:11 -0700, David Fickbohm
wrote:

>People,
> I have a group of people who were offered and accepted a subscription
discount. I also have a group of people who subscribed at the same time
but were not offered the discount.
>
> I think I want to take a random sample from those who subscribed but
were not offered the discount.
>
> The figure out how long subscribers stayed. Then summarize this so that
I have how many subscribers stayed 1 month, 2 months, etc. for both groups.
>
> Then I can do min, max, mode, mean, variance, stddev.
>
> Am I heading in the right direction ? I can code this. I am NOT
looking for code. I am hoping someone can say "yes you are heading in the
right direction' or 'no, you are not'
>
> Thanks
> Dave
>
>
>Dave Fickbohm
>
>Use Technology to the Fullest
>1250 45th st suite 200
>Emeryville, CA, 94608
>510 594 4151 voice


---------------------------------
How much free photo storage do you get? Store your holiday snaps for FREE with Yahoo! Photos. Get Yahoo! Photos