Thank you very much
Andrew
Andrew Zelin | Director - Operations Sampling | Ipsos MORI | Tel +44 (0)
208 515 3422 / 207 347 3193 | E-mail: [log in to unmask]
-----Original Message-----
From: A UK-based worldwide e-mail broadcast system mailing list
[mailto:[log in to unmask]] On Behalf Of allstat automatic digest
system
Sent: 18 April 2006 00:00
To: [log in to unmask]
Subject: allstat Digest - 15 Apr 2006 to 17 Apr 2006 (#2006-94)
There are 4 messages totalling 216 lines in this issue.
Topics of the day:
1. Sampling question/references
2. question
3. query: HIV incidence/prevalence by age and sex (2)
----------------------------------------------------------------------
Date: Sun, 16 Apr 2006 19:55:49 -0700
From: Mary Swinson <[log in to unmask]>
Subject: Sampling question/references
Hi All,
I have the following sampling question that came about
after a discussion with a colleague who is a computer
scientist specialising in data bases.
I have 2 tables in a data base and can do either of
the following:
1. Join them based on a single column and then take a
random sample from the joined table.
2. Take a random sample from each table and then
perform the same join on the 2 samples.
I am interested in the implications of both 1. and 2.
in terms of which is the better sampling stategy, and
are they equivalent in some sense?
Any references to papers that may have addressed this
question would be appreciated.
In SQL parlance, I am interested in this in the
context of aggregated queries where the output is a
scalar for example
select sum(c1) from A, B where A.c2 = B.c3
sum() may be replaced by count(), average(), stdev()
etc...
So from a statistical standpoint is it better to
sample from A and B and then join, or join A and B and
then sample?
It seems to me that there willl be less variance if
one takes a single sample from the joined table rather
than 2 samples and then join them.
From a database standpoint the sample then join
strategy is highly desirable from an efficiency
standpoint.
Any thoughts or pointers on this problem would be most appreciated
Best regards,
Mary
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
------------------------------
Date: Mon, 17 Apr 2006 12:53:58 +0300
From: Evie Delicha <[log in to unmask]>
Subject: question
Dear All,
I m not so familiar with bayesian inference and some issues have arise
in my mind. Let's suppose, we want to conduct a double blind,
randomised, placebo control study. The sample size calculation I
performed indicated 95 patents per arm (bayesian approach). Is it
possible to adopt a sequential Bayesian desing for this study? My major
concern is the unblinding each time the stoping rules shoule be tested
in interim analysis. Any suggestions or references are more than
wellcome. Regards, Evie Delicha
------------------------------
Date: Mon, 17 Apr 2006 20:21:54 +0200
From: "[log in to unmask]" <[log in to unmask]>
Subject: query: HIV incidence/prevalence by age and sex
Dear All,
I am looking for HIV incidence and prevalence data by age and sex.
I am mainly interested in HIV/AIDS most affected countries.
I know that DHS is a major source of information (on prevalence).
However, I was wondering whether you could indicate to me recent
articles= on the subject matter, from which I could derive age-sex
patterns (5 yea= rs age group).
Thank you in advance
Alessandra
------------------------------
Date: Mon, 17 Apr 2006 15:52:39 -0400
From: Darryl Bertolucci <[log in to unmask]>
Subject: Re: query: HIV incidence/prevalence by age and sex
Alexandra,
Others my have completely different standpoints....but
In a former career is was a statistician/epidemiologist working at the
local level in HIV/AIDS. I also got involved somewhat on the
international level. However, I'm not up to speed on current
international databases. Hopefully you will get some answers. I would
greatly caution you......and you probably already know these things:
1. the accurate collection of data varies greatly by jurisdiction with
the U.S.....let alone internationally. Take away: be very careful in
using any data....attempt to verify the information with one or more
other sources. 2. the accuracy of data among HIV incidence/prevalence
and AIDS incidence/prevalence is, IMO, a four-celled matrix with each
cell having greatly different dynamics. I can explain that in more
detail but it would take a few pages. 3. the date of the "estimates"
from some countries is very important depending on when/if anti-viral
drugs and/or prevention efforts were made available. Medications
fortunately have allowed people with AIDS to live longer and healthier
lives and prevented people with HIV from getting full-blown AIDS.
However, statistically both incidence and prevalence of AIDS can be
greatly affected. Prevention efforts have hopefully kept many people
from contracting HIV in the first place. 4. one must ask: do the various
countries have registries? if so how accurate are the registries? OR
are the data survey-driven? How accurately do people answer such
surveys? Is the answer to this, in part at least, culture-driven? etc.
etc. 5. how reluctant/non-reluctant are various countries to report
their data in any way shape or form? 6. I could probably add many more
points.....but you're interested in getting data.
Please don't take this as discouraging. The state-of-the-art may have
improved dramatically over the last 4 years for one thing. For another,
I don't know what use you wish to make of this information...for
example, what your tolerance for "inaccuracy" is. For another, Bayesian
and other methods can be used be "help" you with the data you do
receive......etc. etc.
BTW: Forgive me for the many "etcs", ....this, as I'm sure you know, is
a very large and varied area.
Darryl
"alegarbero@liber
o.it"
<alegarbero@LIBER
To
O.IT> [log in to unmask]
cc
Sent by: A
UK-based
Subject
worldwide e-mail query: HIV incidence/prevalence
by
broadcast system age and sex
mailing list
<allstat@JISCMAIL
.AC.UK>
04/17/2006 02:21
PM
Please respond to
"alegarbero@liber
o.it"
<alegarbero@LIBER
O.IT>
Dear All,
I am looking for HIV incidence and prevalence data by age and sex.
I am mainly interested in HIV/AIDS most affected countries.
I know that DHS is a major source of information (on prevalence).
However, I was wondering whether you could indicate to me recent
articles on the subject matter, from which I could derive age-sex
patterns (5 years age group).
Thank you in advance
Alessandra
------------------------------
End of allstat Digest - 15 Apr 2006 to 17 Apr 2006 (#2006-94)
*************************************************************
============================
This e-mail and all attachments it may contain is confidential and intended solely for the use of the individual to whom it is addressed. Any views or opinions presented are solely those of the author and do not necessarily represent those of Ipsos MORI and its associated companies. If you are not the intended recipient, be advised that you have received this e-mail in error and that any use, dissemination, printing, forwarding or copying of this e-mail is strictly prohibited. Please contact the sender if you have received this e-mail in error.
============================
