Political Science Now

Incorporating Space in Multimethod Research: Combining Spatial Analysis with Case-Study Research

The map shown in figure 2 encompasses all 94 subnational units (i.e., the first subnational administrative level) across seven Central American countries, graphing the clustering of homicide rates in the region.6

Incorporating Space in Multimethod Research: Combining Spatial Analysis with Case-Study Research

by Imke HarbersUniversity of Amsterdam and Matthew C. IngramUniversity at Albany, SUNY

Most outcomes that social scientists care about are not distributed randomly across geographic space. Similar units are often located near one another so that phenomena of interest tend to cluster. This clustering is no accident and should matter in how scholars understand and explain these outcomes. Nevertheless, the spatial dimensions of political data rarely receive explicit attention in how multimethod scholars design research. This article outlines why integrating insights from spatial analysis and multimethod research can lead to stronger conclusions than using either approach in isolation. Specifically, we argue that (1) without integrating insights from spatial analysis, multimethod designs can be self-defeating because one method may undermine the logic of another; and (2) without integrating insights from multimethod research, spatial statistics and econometrics can fall short by assuming rather than demonstrating both (a) the mechanisms underlying key spatial processes and (b) the proper unit or level of analysis. Incorporating the spatial nature of data can enrich multimethod research by providing a new set of geographic tools to analyze data. This article shows how basic, exploratory, univariate diagnostics of spatial autocorrelation can help scholars to (1) understand the boundedness of phenomena, and (2) select interesting cases for further analysis.

Read the full article.

PS: Political Science & Politics, Volume 50Issue 4 / October 2017, pp. 1032-1037