References

Appendix

In this brief appendix, readers can find additional guides that informed this project and a brief overview of the political science literature that is using spatial regression methods.

For more resources that guided this project:

An Overview of How Spatial Modeling is Applied in Political Science

Advancements in spatial modeling have improved measurements for research questions whose theoretical arguments are dependent upon accounting for space and time. In political science and spatial econometrics, models have progressed our understanding of topics such as political geography, political identity, and political opinions. Modeling relationships without accounting for space has led to inaccurate predictions and other estimation errors (Darmofal, 2006). Experts in the field have advocated for moving away from non-spatial OLS regressions to models that account for the ways in which space can impact bias, accuracy in standard errors, and efficiency of estimation (Franzese and Hays, 2017). Lin et al. (2006) used spatial modeling techniques to determine how Taiwanese national identity was shaped through neighborhood influence. Mourao et al. (2020) incorporated spatial models into their analysis to better understand how providing citizens with local budgetary transparency can facilitate legislative transparency and better accountability. These relevant examples highlight the importance of correct model specification and its applications, but spatial methods are not yet popular in political science. One goal of this project, is to increase the usage of spatial regression by political scientists.