Benito,

I have done similar modeling exercises at the census tract level and have found that spatial error and/or spatial lag models can improve the fit over using demographic information alone.

I would suggest that first you conduct the modeling exercise at the county level. The data is easier to get, and you can test out various hypothesis, and there will be less "noise" in the data. Once you've got a good model at the county level, then you can explore going to smaller levels of geography such as the census tract or the block group.

Mr. Louis Merlin, AICP

Doctoral Student

UNC CH Department of City and Regional Planning

From: Nancy Reger [Nreger@morpc.org]
Sent: Thursday, May 10, 2012 12:30 PM
To: ctpp-news@chrispy.net
Subject: Re: [CTPP] Analyzing historical geospatial Census data to assist in forecasting TAZ socioeconomic data

Benito-

I’m more than likely preaching to the choir, but my conscience is making me say to be careful. Sometimes looking back doesn’t help with looking forward. I guess I’m just suggesting you don’t assume history will trend forward, there might be other variables at play that were blips in the decades and may not be repeated. Also, the evolution of recent events regarding aging, international migration, fluctuations in employment, foreclosures may be excluded.

Nancy

From: ctpp-news-bounces@chrispy.net [mailto:ctpp-news-bounces@chrispy.net] On Behalf Of Benito Perez
Sent: Thursday, May 10, 2012 10:27 AM
To: ctpp-news@ryoko.chrispy.net
Subject: [CTPP] Analyzing historical geospatial Census data to assist in forecasting TAZ socioeconomic data

All,

Good morning. Wanted to solicit ideas, tools, resources that others may be aware of in analyzing historical census data to develop growth trends that can be used in forecasting socioeconomic data for our travel demand model’s traffic analysis zones (TAZs). Thoughts? At this point I have gathered Census tract geospatial data for our region (Hampton Roads) as far back as 1960, Census Block Group geospatial data from 1990 onwards, and Census Block geospatial data from 2000 onwards. The hope is to do a geospatial analysis with these data sets to geospatially identify growth patterns across our region. Thanks for your time in your thoughts on this. I’ll be cross-posting this on the TMIP listserv as well.

Benito O. Pérez, AICP

Transportation Engineer

Hampton Roads Transportation Planning Organization

The Regional Building 723 Woodlake Drive Chesapeake Virginia 23320

bperez@hrpdcva.gov| http://www.hrtpo.org| Phone: 757.420.8300 | Fax: 757.523.4881

All email correspondence to and from this address is subject to the Virginia Freedom of Information Act

and to the Virginia Public Records Act, which may result in monitoring and disclosure to third parties, including law enforcement.