Specification Issues in Proximity Models of Candidate Evaluation (with Issue Importance)

Bryce E. Corrigan Department of Political Science, University of Michigan, 5700 Haven Hall, 505 S. State Street, Ann Arbor, MI 48109-1045 e-mail: becorrig{at}umich.edu e-mail: grynaviski{at}uchicago.edu (corresponding author) The use of the proximity model to represent the relationshipbetween citizens' policy attitudes and the positions of candidateson the issues of the day has considerable appeal because itoffers a bridge between theoretical models of political behaviorand empirical work. However, there is little consensus amongapplied researchers about the appropriate representation ofvoter behavior with respect to the measurement of issue distance,candidate location, or whether to allow heterogeneity in theweight that each individual places on particular issues. Eachof these choices suggests a different, and reasonably complicated,nonlinear relationship between voter utility and candidate andvoter issue positions which may have a meaningful influenceon the substantive conclusions drawn by the researcher. Yet,little attention has been given to the best way to representthe proximity model in applied work. The purpose of this paperis to identify which forms of the proximity model work best,with particular consideration given to the identification offunctional forms that are invariant to the choice of scale forthe independent variables.     

Violence in the city: Empirical bases for a collective working image

Many police patrol officers in Newark, New Jersey, articulate a working image of violence in the city that is similar to Louis Wirth's classical model of the effects of urban social disorganization on deviant behavior. In Newark, however, the working theory posits the 1967 civil disorders as a cataclysmic disorganizing event that generated ominously unique patterns of violence in the post-disorder years, compared to earlier times. Using data on violent crimes reported to the Newark police between 1940 and 1980, this article attempts to test the adequacy of that working theory as an explanation of reality. Regression techniques similar to those used by Friesma (1979) to assess natural disaster impacts are applied to three transformations of these crime data. The analysis demonstrates that the police working version of the disorganization model is more accurate as an inference from the pattern of violence that characterizes their workload than it is one from the patterns of absolute incidence of violent crime or of the risk of violent victimization incurred by residents of Newark. The article closes with a discussion of the implications of these findings for the larger problem of police-citizen distance.     

The Statistical Properties and Empirical Performance of Double Regression

Voting rights litigation requires ecological inference to estimatethe voting preferences of minority and nonminority groups withinthe electorate. Double regression has been the procedure mostcommonly employed for this purpose. This article presents thefirst formal examination of this procedure. The underlying structuralmodel reveals that double regression estimators are neitherunbiased nor consistent estimators of true within-group votepreferences or polarization. Simulations demonstrate that theycan substantially exaggerate the differences between minorityand nonminority vote choices when none are present, and dramaticallyunderstate them when differences exist. In sum, double regressioncannot meet conventional statistical standards for reliability.Consequently, it should be abandoned.     

Sentencing Using Statistical Treatment Rules: What We Don’t Know Can Hurt Us

The existing literature seriously misinterprets the available evidence on the predictability of high rate criminal offending and thus the potential value of statistical treatment rules that impose stiffer punishments on offenders with higher predicted risk of recidivism. The misinterpretation results from the failure to take account of the fact that the data used in existing risk assessment exercises come from environments characterized by informal (and sometimes formal) attempts by judges and other actors to base penal treatments on expected recidivism. Findings of little or no predictive power for baseline covariates may simply indicate the efficient use of the available information. We lay out the problem in detail, provide examples from several literatures and then consider general solutions to the problem.

Social disorganization, Latinos and juvenile crime in the Texas borderlands

Purpose

Using a time-series cross-sectional design, we estimated the effects of social disorganization on juvenile property crime rates in a predominately Latino, Texas-Mexico border region.

Methods

Eighteen years of data from seven independent sources (Bureau of Economic Analysis, Bureau of Labor Statistics, Census Bureau, Texas State Demographer, Internal Revenue Service, Department of Agriculture Economic Research Service, and Uniform Crime Reports) were examined. Counties were utilized as the unit of analysis, and time-series cross-sectional regression models were estimated.

Results

The analysis showed that per capita income was negatively related to juvenile crime in both rural and urban counties. Ethnic heterogeneity was positively related to the outcome in rural, but not urban, counties; while percent foreign-born was negatively related to juvenile crime in urban, but not rural, counties.

Conclusions

The Latino experience, both native- and foreign-born, is important for improving our understanding how economic and social conditions relate to crime. Comparative analyses between distinct geographical environments, such as rural and urban counties, can yield insight how the local context interacts with social disorganization processes.