Ecometrics: New Directions for Multilevel Spatial Analysis in the Social Sciences
Investigators: Stephen W. Raudenbush, Jeffrey Morenoff
New Directions for Multilevel Spatial Analysis in the Social Sciences Stephen Raudenbush University of Michigan Research has long documented that risks and opportunities vary systematically over space and time. Just as poverty, residential instability, and home ownership are concentrated in certain sections of cities, so too are social disorder, crime, and violence as well as infant mortality, low birth weight, and accidents. Rates of crime and other outcomes surge and decline with time, and some neighborhoods are more strongly affected by these changes than are other neighborhoods. To examine how neighborhoods affect a variety of outcomes and how these effects change over time, this study will develop a method of statistical analysis that combines multilevel and spatial models. Four aims organize the proposed work: 1) to incorporate a spatial auto-regressive process into the now-standard two-level hierarchical linear model; 2) to elaborate this model to include repeated measures on participants; 3) to incorporate repeated measures at the neighborhood level; and 4) to exploit spatial dependence in order to improve the reliability and validity of measures of neighborhood social process. Predictive validity will be assessed using data from thc Project on Human Development in Chicago Neighborhoods (PHDCN), which conducted a citywide neighborhood study in 1995 and will complete a replication of' this study in 2002. Methods will also be illustrated with PHDCN data on 6000 young people growing up in those neighborhoods between 1995 and 2002. Software to implement the proposed methods will be tested through simulation studies before being distributed publicly. The multilevel aspect of the model expresses the notion that urban space is divided into uniquely defined, more or less contiguous, self-contained "neighborhoods," often bounded by railroad tracks, major arteries, parks, or industrial districts. The spatial aspect of the model reflects theory and empirical evidence suggesting that neighborhoods, while somewhat distinct, are not independent. Rather, neighborhood social processes "spill over" into surrounding neighborhoods. The model thus represents the view that neighborhoods are socially meaningful units that are linked spatially. Using the proposed methods, it will be possible to study not only how the social composition and processes in each neighborhood are related to human development but also how the composition and processes in surrounding neighborhoods affect the development of persons within a given neighborhood.
| Funding: | National Science Foundation |
Funding Period: 08/01/2002 to 07/31/2006
PSC Research Themes:Analysis and Modeling (Methodology)
Contextual Effects (Group Disparities)
PSC blog
Recent resources, events, news
New Publications
Bingenheimer & Geronimus, "Behavior & HIV"
Wildeman, "Imprisonment & Infant Mortality," PSC Research Report
Next Brown Bag
Tues, Dec 1
Arland Thornton & Barb Koremenos
Mobilizing for Human Rights
For live stream
LINK HERE
W A R N I N G
If you are reading this, it may be that you are using rather old web browsing software that does not support modern international Web technology standards. For a better experience of the Web and this site in particular, please upgrade your web browser software today. The following are good choices: Firefox 2; Opera 9; Safari 3.