Todd Graham makes all the right points. CTPP is statistically very thin (and IMO not usable at any fine granularity such as CT, let alone TAZ).<br><br>Keith<br><br><div class="gmail_quote">On Wed, Apr 15, 2009 at 1:16 PM, <span dir="ltr"><<a href="mailto:ctpp-news-request@chrispy.net">ctpp-news-request@chrispy.net</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">Send ctpp-news mailing list submissions to<br>
<a href="mailto:ctpp-news@chrispy.net">ctpp-news@chrispy.net</a><br>
<br>
To subscribe or unsubscribe via the World Wide Web, visit<br>
<a href="http://www.chrispy.net/mailman/listinfo/ctpp-news" target="_blank">http://www.chrispy.net/mailman/listinfo/ctpp-news</a><br>
or, via email, send a message with subject or body 'help' to<br>
<a href="mailto:ctpp-news-request@chrispy.net">ctpp-news-request@chrispy.net</a><br>
<br>
You can reach the person managing the list at<br>
<a href="mailto:ctpp-news-owner@chrispy.net">ctpp-news-owner@chrispy.net</a><br>
<br>
When replying, please edit your Subject line so it is more specific<br>
than "Re: Contents of ctpp-news digest..."<br>
<br>
<br>
Today's Topics:<br>
<br>
1. RE: RE: Census Bureau Federal Register Notice on New<br>
DataDisclosure Restrictions (Michael Moan)<br>
2. remove (Brian Raimondo)<br>
<br>
<br>
----------------------------------------------------------------------<br>
<br>
Message: 1<br>
Date: Wed, 15 Apr 2009 14:42:30 -0400<br>
From: "Michael Moan" <<a href="mailto:MMoan@doa.ri.gov">MMoan@doa.ri.gov</a>><br>
Subject: RE: [CTPP] RE: Census Bureau Federal Register Notice on New<br>
DataDisclosure Restrictions<br>
To: <<a href="mailto:ctpp-news@chrispy.net">ctpp-news@chrispy.net</a>><br>
Message-ID: <<a href="mailto:s9e5f27d.037@ri.gov">s9e5f27d.037@ri.gov</a>><br>
Content-Type: text/plain; charset=US-ASCII<br>
<br>
Yes this is too much and one of the reasons I opted out last time.<br>
<br>
<br>
>>> <a href="mailto:JSabula@rideuta.com">JSabula@rideuta.com</a> 4/15/2009 1:38 PM >>><br>
Is there a way to reply just to the person you are conversing with? I<br>
would rather access these messages on the discussion board if I'm<br>
interested than empty my inbox once an hour.<br>
<br>
Julianne Sabula<br>
Utah Transit Authority<br>
<br>
<br>
-----Original Message-----<br>
From: <a href="mailto:ctpp-news-bounces@chrispy.net">ctpp-news-bounces@chrispy.net</a><br>
[mailto:<a href="mailto:ctpp-news-bounces@chrispy.net">ctpp-news-bounces@chrispy.net</a>] On Behalf Of Agnello, Paul<br>
Sent: Wednesday, April 15, 2009 10:22 AM<br>
To: Ed Christopher; Graham, Todd; Penny Weinberger;<br>
<a href="mailto:ctpp-news@chrispy.net">ctpp-news@chrispy.net</a><br>
Cc: Memmott, Jeff <RITA>; <a href="mailto:kcooper@dot.state.nv.us">kcooper@dot.state.nv.us</a>; <a href="mailto:amy.thomas@ky.gov">amy.thomas@ky.gov</a>;<br>
<a href="mailto:robbins@wsdot.wa.gov">robbins@wsdot.wa.gov</a>; Murakami,Elaine; <a href="mailto:ayalew.adamu@dot.ca.gov">ayalew.adamu@dot.ca.gov</a>;<br>
<a href="mailto:sandy.beaupre@dot.state.wi.us">sandy.beaupre@dot.state.wi.us</a>; <a href="mailto:willimasjs@dot.state.al.us">willimasjs@dot.state.al.us</a>;<br>
<a href="mailto:bobbi.retzlaff@dot.state.wi.us">bobbi.retzlaff@dot.state.wi.us</a>; <a href="mailto:dhardy@ampo.org">dhardy@ampo.org</a>;<br>
<a href="mailto:nerlbaum@dot.state.ny.us">nerlbaum@dot.state.ny.us</a>; <a href="mailto:donna.weaver@po.state.ct.us">donna.weaver@po.state.ct.us</a>;<br>
<a href="mailto:pleasantmd@scdot.org">pleasantmd@scdot.org</a>; <a href="mailto:huiwei.shen@dot.state.fl.us">huiwei.shen@dot.state.fl.us</a>; <a href="mailto:kmiller@njtpa.org">kmiller@njtpa.org</a>;<br>
<a href="mailto:rdenbow@ampo.org">rdenbow@ampo.org</a>; <a href="mailto:Ron.fields@arkansashighways.com">Ron.fields@arkansashighways.com</a>;<br>
<a href="mailto:jonette.kreideweis@dot.state.mn.us">jonette.kreideweis@dot.state.mn.us</a>; <a href="mailto:nsrinivasan@nas.edu">nsrinivasan@nas.edu</a>;<br>
<a href="mailto:phil.mescher@dot.state.ia.us">phil.mescher@dot.state.ia.us</a>; Curling,Samuel F.; Weiner,Ed <OST>;<br>
Pickard, Andy,P.E.; <a href="mailto:virginia.porta@arkansashighways.com">virginia.porta@arkansashighways.com</a>; Tambellini,<br>
Rick L.; Fred@NARC.org<br>
Subject: [CTPP] RE: Census Bureau Federal Register Notice on New<br>
DataDisclosure Restrictions<br>
<br>
>From a state planning perspective, I think it is very disappointing<br>
(whether it is due to new tighter disclosure rules or the statistical<br>
reliability issue) that it appears that states and MPOs will not have<br>
the same quality of CTPP data available in 2010 as in 2000 and previous<br>
census cycles. Particularly since states are paying considerably more<br>
for the next CTPP than for 2000. Virginia's share more than tripled in<br>
cost from 2000 to 2010. I agree with the earlier point that if states<br>
are paying for the special tabulations, there should not be these new<br>
disclosure restrictions governing the release of the data. I am not<br>
clear on why the disclosure restrictions are even an issue since I am<br>
not aware of any past disclosure issues with the 2000 or prior CTPP and<br>
mining CTPP data would not appear to be a particularly effective way for<br>
someone to try to find out personal info. about someone else. If this is<br>
such an issue, why was it not a problem in the past?<br>
<br>
While it may be too late to fix the problems associated with data<br>
quality/content for the next CTPP, I'm wondering if there are ways that<br>
the ACS sample could be increased with additional federal and/or state<br>
support in the future so that this statistical reliability issue could<br>
be addressed, perhaps in a process similar to the way NHTS is done, or<br>
perhaps CTPP data needs to come from a different source long term if the<br>
ACS data is not reliable enough to meet state and metropolitan planning<br>
needs.<br>
<br>
Decision makers increasingly want to see more robust technical tools<br>
and analysis which to support planning analysis which requires more<br>
detailed data at the small area from sources such as ACS, CTPP, NHTS,<br>
etc., and major conferences, e.g., TRB, and federal agencies have<br>
supported better data for transportation planning for years. Therefore,<br>
from a state perspective, the Census Bureau's proposed policy change run<br>
counter, not only to prevailing trends, but to the policies from other<br>
federal transportation agencies.<br>
<br>
<br>
-------------------------------------------<br>
Paul T. Agnello<br>
Travel Demand Modeling Manager<br>
Virginia Department of Transportation<br>
Transportation & Mobility Planning Division<br>
1401 East Broad Street Telephone (804) 786-2531<br>
Richmond, Virginia 23219-2000 Fax (804) 225-4785<br>
E-mail: mailto:<a href="mailto:paul.agnello@VDOT.Virginia.gov">paul.agnello@VDOT.Virginia.gov</a><br>
Website: <a href="http://www.virginiadot.org/" target="_blank">http://www.virginiadot.org/</a><br>
* CONFIDENTIALITY/PRIVACY NOTICE - The documents included in this<br>
transmission may contain information that is confidential and/or legally<br>
privileged. If you are not the intended recipient, or the employee or<br>
agent responsible for delivering the information to the intended<br>
recipient, you are hereby notified that any disclosure, copying,<br>
distribution, or action taken in reliance on the contents of these<br>
documents is strictly prohibited. If you have received this document in<br>
error, please notify the sender immediately to arrange for return or<br>
destruction of these documents.<br>
<br>
<br>
-----Original Message-----<br>
From: Ed Christopher [mailto:<a href="mailto:edc@berwyned.com">edc@berwyned.com</a>]<br>
Sent: Wednesday, April 15, 2009 12:07 AM<br>
To: Graham, Todd; Penny Weinberger<br>
Cc: Murakami, Elaine; Agnello, Paul; <a href="mailto:banningag@michigan.gov">banningag@michigan.gov</a>;<br>
<a href="mailto:sandy.beaupre@dot.state.wi.us">sandy.beaupre@dot.state.wi.us</a>; <a href="mailto:kcooper@dot.state.nv.us">kcooper@dot.state.nv.us</a>;<br>
<a href="mailto:jonette.kreideweis@dot.state.mn.us">jonette.kreideweis@dot.state.mn.us</a>; <a href="mailto:phil.mescher@dot.state.ia.us">phil.mescher@dot.state.ia.us</a>;<br>
<a href="mailto:ayalew.adamu@dot.ca.gov">ayalew.adamu@dot.ca.gov</a>; <a href="mailto:pleasantmd@scdot.org">pleasantmd@scdot.org</a>;<br>
<a href="mailto:virginia.porta@arkansashighways.com">virginia.porta@arkansashighways.com</a>; <a href="mailto:bobbi.retzlaff@dot.state.wi.us">bobbi.retzlaff@dot.state.wi.us</a>;<br>
<a href="mailto:robbins@wsdot.wa.gov">robbins@wsdot.wa.gov</a>; <a href="mailto:huiwei.shen@dot.state.fl.us">huiwei.shen@dot.state.fl.us</a>; <a href="mailto:amy.thomas@ky.gov">amy.thomas@ky.gov</a>;<br>
<a href="mailto:donna.weaver@po.state.ct.us">donna.weaver@po.state.ct.us</a>; <a href="mailto:willimasjs@dot.state.al.us">willimasjs@dot.state.al.us</a>;<br>
<a href="mailto:sharon.ju@h-gac.com">sharon.ju@h-gac.com</a>; <a href="mailto:kmiller@njtpa.org">kmiller@njtpa.org</a>; Pickard, Andy, P.E.;<br>
<a href="mailto:creschovsky@mwcog.org">creschovsky@mwcog.org</a>; <a href="mailto:grousseau@atlantaregional.com">grousseau@atlantaregional.com</a>; Fred@NARC.org;<br>
<a href="mailto:rdenbow@ampo.org">rdenbow@ampo.org</a>; <a href="mailto:dhardy@ampo.org">dhardy@ampo.org</a>; <a href="mailto:rmccready@aashto.org">rmccready@aashto.org</a>; Memmott,<br>
Jeff <RITA>; <a href="mailto:nsrinivasan@nas.edu">nsrinivasan@nas.edu</a>; Weiner, Ed <OST>;<br>
<a href="mailto:Ron.fields@arkansashighways.com">Ron.fields@arkansashighways.com</a>; <a href="mailto:nerlbaum@dot.state.ny.us">nerlbaum@dot.state.ny.us</a><br>
Subject: Re: Census Bureau Federal Register Notice on New Data<br>
Disclosure Restrictions<br>
<br>
Todd--You should have posted to the full CTPP listserve. You make all<br>
<br>
good points that people need to think about. One point of<br>
clarification<br>
is that the AASHTO CTPP Oversight Board has sent a new proposal of<br>
tables over to the CB for 3-year data and in fact the mode to work<br>
questions are rolled up. I believe the largest roll-up is 3 modes:<br>
auto, other and total. I took on the task of posting the new tables to<br>
<br>
the Listserve but haven't done so yet. The tables are still fresh off<br>
<br>
the press and I will not be able to get to it till Thursday.<br>
<br>
One point that is missed in all of this is that with the 3-year data we<br>
<br>
are talking about a zone system with 20,000 people per zone. That is<br>
the size of 7 or so tracts. Pretty big when you are talking about<br>
planning within a region. Even though you are right about the<br>
statistical quality of the data the CB is not telling us there is a<br>
statistical reason for suppressing the data. They are basing it solely<br>
<br>
on disclosure requirements. Disclosure requirements and arguments that<br>
<br>
can not be proven. Another point that is missed is that the old long<br>
<br>
form data suffered from the same relative thinness at the tract, block<br>
<br>
group and TAZ level. At those levels of geography many of the same<br>
tables that are not passing the disclosure rules now would not have<br>
passed then. Yes, the data today is a little thinner but that has<br>
never<br>
been the issue.<br>
<br>
One last point is that CTPP has always been a special tabulation and if<br>
<br>
you push the issue far enough logic should dictate that someone<br>
purchasing a special tabulation should be allowed to buy whatever data<br>
<br>
they want no matter how crappy it is. In 1980 the CB used to sell us<br>
the data with a "caveat emptor" sticker on it.<br>
<br>
Putting all the cards on the table does point to why synthetic data for<br>
<br>
small area analysis is so important. Unfortunately there are not only<br>
<br>
statistical issues of methodology to deal with but also practical<br>
issues<br>
of political acceptance within the community.<br>
<br>
Graham, Todd wrote:<br>
> State and MPO colleagues--<br>
><br>
> Discussions about Census data disclosure have been making the rounds.<br>
I wanted to share a few thoughts with the SCOP Census Data Work<br>
Group...<br>
><br>
> Re: protecting the individual confidentiality of respondents. True,<br>
the Bureau itself is standing this up as their decision basis (it's a<br>
legally powerful position). But I think the larger, latent, real concern<br>
among the Bureau statisticians is statistical reliability.<br>
><br>
> We know ACS sampling is thin (1 in 8 households surveyed, 60-65%<br>
response rates?) and temporally spread out... And we know there will be<br>
large numbers of individual data cells in the planned CTPP-from-ACS<br>
tabs where estimates would be based on just 1 or 2 respondents. As a<br>
statistician, I really don't like this. Resulting estimates are not<br>
robust. (There's great uncertainty around whether the 1 or 2 survey<br>
respondents should represent 10-20 other people - or perhaps, by freak<br>
luck, the 1 or 2 persons are unique. There is real probability of 1 or 2<br>
respondents being *not* representative.) This is particularly true in<br>
the most highly-detailed crosstabs. Hundreds of cells in a table *will*<br>
result in many cells with small numbers.<br>
><br>
> I know some members of SCOP have been drafting comments in response<br>
to the Fed Register Notice. Some of these comments will make emphatic<br>
proposals that we must have fully populated CTPP tables. I worry that<br>
this line of reasoning won't have much traction at Census Bureau...<br>
And really, do we believe that any numbers (regardless of statistical<br>
reliability) are better than no numbers?<br>
><br>
> As a statistician, I disagree - and I think there are creative<br>
alternatives that are viable: (1) SCOP and Census Data Workgroup have<br>
discussed data synthesis techniques to simulate or synthesize the<br>
desired details. Or (2), a more conventional solution, more highly<br>
aggregated ("rolled up") categorization in the CTPP-from-ACS tabs. What<br>
SCOP requested in 2007 looks a lot like CTPP 2000 -- even though we knew<br>
that ACS Survey sampling is thinner than Census 2000.<br>
><br>
> Sorry to bring this up, but here goes: AASHTO SCOP should revisit<br>
the CTPP-from-ACS design, reopen it for discussion, go back to the<br>
drawing board, and consider more highly aggregated ("rolled up")<br>
categorizations in the CTPP-from-ACS tabs. Do we really need 10 (or 17)<br>
categories of mode of travel (can we live with fewer)? Do we really<br>
need 25 categories of household income (can we live with fewer)? Do we<br>
really need tabs with travel-start-time expressed in 15-minute<br>
intervals??<br>
><br>
> I know there are sunken costs already. Still, my candid advice:<br>
AASHTO SCOP and other funding partners in the CTPP need to take a deep<br>
breath... and consider revising the special tabs requests. And Census<br>
Bureau should cooperate and enable such a new plan.<br>
><br>
> I understand that people are up-at-arms about this. (Census Bureau,<br>
for their part, waited until 2008 to clearly signal that there would be<br>
a tighter data disclosure regime than experienced in CTPP 2000...) But<br>
the realpolitic is: Census Bureau statisticians have already decided<br>
this matter -- isn't the Fed Register notice just a formality? -- and<br>
from the standpoint of good statistical science, their decision is<br>
right.<br>
><br>
> -- Todd Graham<br>
><br>
><br>
><br>
> ________________________<br>
><br>
> Todd Graham<br>
> Principal Forecaster<br>
> Metropolitan Council<br>
> 390 Robert Street North<br>
> Saint Paul, MN 55101<br>
><br>
> phone 651/602-1322<br>
> email <a href="mailto:todd.graham@metc.state.mn.us">todd.graham@metc.state.mn.us</a><br>
> web <a href="http://www.metrocouncil.org" target="_blank">www.metrocouncil.org</a><br>
> <a href="http://www.metrocouncil.org/metroarea/stats.htm" target="_blank">www.metrocouncil.org/metroarea/stats.htm</a><br>
> ________________________<br>
><br>
><br>
><br>
<br>
--<br>
Ed Christopher<br>
708-283-3534 (V)<br>
708-574-8131 (cell)<br>
<br>
FHWA RC-TST-PLN<br>
19900 Governors Dr<br>
Olympia Fields, IL 60461<br>
<br>
<br>
_______________________________________________<br>
ctpp-news mailing list<br>
<a href="mailto:ctpp-news@chrispy.net">ctpp-news@chrispy.net</a><br>
<a href="http://www.chrispy.net/mailman/listinfo/ctpp-news" target="_blank">http://www.chrispy.net/mailman/listinfo/ctpp-news</a><br>
<br>
_______________________________________________<br>
ctpp-news mailing list<br>
<a href="mailto:ctpp-news@chrispy.net">ctpp-news@chrispy.net</a><br>
<a href="http://www.chrispy.net/mailman/listinfo/ctpp-news" target="_blank">http://www.chrispy.net/mailman/listinfo/ctpp-news</a><br>
<br>
<br>
------------------------------<br>
<br>
Message: 2<br>
Date: Wed, 15 Apr 2009 15:41:36 -0400<br>
From: "Brian Raimondo" <<a href="mailto:braimondo@swfrpc.org">braimondo@swfrpc.org</a>><br>
Subject: [CTPP] remove<br>
To: <<a href="mailto:ctpp-news@chrispy.net">ctpp-news@chrispy.net</a>><br>
Message-ID:<br>
<<a href="mailto:51C7115D89DD7F4FA0D991DBE96511837493D9@exchange.corp.swfrpc.org">51C7115D89DD7F4FA0D991DBE96511837493D9@exchange.corp.swfrpc.org</a>><br>
Content-Type: text/plain; charset="us-ascii"<br>
<br>
Please remove me from all the mailing lists.<br>
-------------- next part --------------<br>
An HTML attachment was scrubbed...<br>
URL: <a href="http://www.chrispy.net/pipermail/ctpp-news/attachments/20090415/391eef2c/attachment.html" target="_blank">http://www.chrispy.net/pipermail/ctpp-news/attachments/20090415/391eef2c/attachment.html</a><br>
<br>
------------------------------<br>
<br>
_______________________________________________<br>
ctpp-news mailing list<br>
<a href="mailto:ctpp-news@chrispy.net">ctpp-news@chrispy.net</a><br>
<a href="http://www.chrispy.net/mailman/listinfo/ctpp-news" target="_blank">http://www.chrispy.net/mailman/listinfo/ctpp-news</a><br>
<br>
<br>
End of ctpp-news Digest, Vol 62, Issue 9<br>
****************************************<br>
</blockquote></div><br><br clear="all"><br>-- <br>Keith Lawton<br>503 538 6509<br>503 453 7630 (mobile)<br>