Spatial Regression Models for the Social Sciences shows researchers and students how to work with spatial data without the need for advanced mathematical statistics. Focusing on the methods that are commonly used by social scientists, Guangqing Chi and Jun Zhu explain what each method is and when and how to apply it by connecting it to social science research topics. Throughout the book they use the same social science example to demonstrate applications of each method and what the results can tell us.

Advanced Spatial Regression Models

Learning Objectives

  • Understand how to fit a spatio-temporal regression model, interpret the spatial and/or temporal lag effects, and use appropriate diagnostics to assess the model.
  • Understand how to use spatio-temporal regression models for forecasting purposes.
  • Understand how to use geographically weighted regression models for forecasting purposes.

Previous chapters focus on the spatial aspects of a research problem and deal with data that have spatial information. What if the data are both geographically referenced and longitudinal? Such rich information could be considered in more advanced models. Could we use the spatial and longitudinal nature of the data for forecasting?

In this chapter we first introduce spatio-temporal regression models that consider both spatial and temporal dependence exhibited in the data (Section 7.1). Second, we transform spatial regression ...

  • Loading...
locked icon

Sign in to access this content

Get a 30 day FREE TRIAL

  • Watch videos from a variety of sources bringing classroom topics to life
  • Read modern, diverse business cases
  • Explore hundreds of books and reference titles