Contextual data and the study of elections and voting behavior: connecting individuals to environments

Studies of contextual processes have always involved the possibility that if individuals' aggregation into geographic units is not exogenous to their values on the dependent variable, then what appear to be 'contextual processes' may be solely due to selection effects. We propose a method to test whether observed contextual effects are real or phantom. The integration of individuals in their neighborhoods is measured by response latency on questions about the neighborhood; if contextual effects are based on what happens to people in their neighborhoods (that is, the apparent effects are not solely because of selection effects), they should be more pronounced among those who are most integrated into their neighborhood. An empirical example illustrates the technique. We propose instrumentation by which electoral studies can test for true contextual effects. The availability of this test should encourage greater emphasis in electoral studies on the search for contextual processes. (C) 2002 Elsevier Science Ltd. All rights reserved.