[Openspace] Multi-Level Modeling

[Rudy Banerjee]

Guangqing and Jason,

There is software that does hierarchical regression. For example,
WinBUGS(TM) uses Bayesian statistics (involving networks and
hierarchies) to model a variety of problems including space and time
networks. One can also write programs in C++ etc to implement these
Bayes methods. The problem is that convergence is based on algorithms
using Markov Chains methods and are very time consuming. Good Luck.

Rudy B.
Scientist,
Prevention Research Center,
Berkeley, CA

>>> GUANGQING CHI <guangqingchi at wisc.edu> 4/28/2006 4:00 PM >>>
Jason,

As far as I know, no existing software can do spatial hierarchical 
regression. You have to conduct the analysis by two stages as 
demonstrated in the following paper. 

Sampson, Robert J., Jeffrey D. Morenoff & Felton Earls. 1999. "Beyond 
Social Capital: Spatial Dynamics of Collective Efficacy for Children."

American Sociological Review 64(5):633-660.


Guangqing


----- Original Message -----
From: Jason McDaniel <jmcdanie at usc.edu>
Date: Friday, April 28, 2006 5:00 pm
Subject: [Openspace] Multi-Level Modeling
To: openspace at sal.uiuc.edu 

> I am wondering about the best ways to combine spatial regression 
> with  
> opinion survey data.  I have been thinking about the possibilities 
> of  
> using a multi-level hierarchical model that combines spatially  
> located data of Los Angeles Mayoral elections and demographics  
> aggregated at the census tract level with exit polling.  Does 
> anyone  
> know of any efforts to develop multi-level models using spatial  
> regression?
> 
> Thank you.
> 
> Jason McDaniel
> Department of Political Science
> University of Southern California
> jmcdanie at usc.edu 
> 
> 
> _______________________________________________
> Openspace mailing list
> Openspace at sal.uiuc.edu 
> http://sal.uiuc.edu/mailman/listinfo/openspace 
> 
_______________________________________________
Openspace mailing list
Openspace at sal.uiuc.edu 
http://sal.uiuc.edu/mailman/listinfo/openspace