Past Quantitative Brown Bag Sessions
Retrieving Data and Making Maps Using MPIP's MetroPhilaMapper
Researchers studying communities in the Philadelphia Metropolitan Statistical Area now have online access to comprehensive administrative data on a municipality by municipality basis. This presentation demonstrated easy ways to both access the data and create maps and graphs that illustrate findings in an engaging and intuitive manner. This unique tool aggregates data into useful geographic units, providing a new, user-friendly entry point to data that has previously been unavailable or very difficult to access.
Housed here at Temple, MPIP brings together on one Web site (http://mpip.temple.edu) a wealth of social, economic, and environmental data on the Philadelphia metropolitan area. MPIP research assistant Jason Martin will introduced us to one of the Web site’s most useful features, PhilaMetroMapper.
Using only a web interface, researchers can interactively investigate and portray regional data using maps, charts, tables, and statistics. PhilaMetroMapper lets you describe spatial patterns, display growth, reveal trends, and compare indicators. All of the information from the past five MPIP annual reports as well as hundreds of new indicators at a variety of geographic levels are accessible via MPIP's interactive map-making application.
Structural Equation Modelling
On Monday, March 2nd, we discussed two projects using Structural Equation Modeling (SEM). Psychology Professor Isabelle Chang and Education graduate student Nita Guzman presented their work. Professor Mark F Schmitz, of Social Administration, mentored the session. Session Notes.
Geographically Weighted Regression
On Tuesday, February 3rd 2009, our first session of the semester was about Geographically Weighted Regression. Graduate student Laura Chisholm, and her mentor, Dr. Jeremy Mennis from the Geography and Urban Studies Department presented.
Research Question: How places may differ in their causes of juvenile drug recidivism
Project Description: This study maps the results of geographically weighted regression (GWR), a statistical tool used to determine spatial nonstationarity, in order to investigate the causes of juvenile delinquency recidivism. Specifically, the study investigates how the influence of individual and socioeconomic characteristics on juvenile drug-crime recidivism varies across neighborhoods in Philadelphia, Pennsylvania. Home addresses of 7,323 juvenile delinquents were geocoded and integrated with both individual- and neighborhood-level data. Results of conventional forward-stepwise logistic regression suggest that juveniles' age, race, poverty and the prevalence of delinquency and recidivism in their neighborhoods influence the likelihood of recidivism with a drug crime. These same variables are being entered into a geographically weighted logistic regression and the results will be mapped for visual analysis of spatial nonstationarity.
Session Notes