scholarly journals Three essays on crime policy and the Bayesian bootstrap

2021 ◽  
Author(s):  
◽  
Lonnie Hofmann
Keyword(s):  
Violent Crime ◽  
Coverage Probability ◽  
Crime Rates ◽  
Bayesian Bootstrap ◽  
Significance Level ◽  
Credible Intervals ◽  
Three Strikes ◽  
Frequentist Coverage ◽  
Pre Treatment

This dissertation consists of three chapters. In the first chapter, I analyze credible intervals for quantiles constructed using Bayesian bootstrap techniques and show that credible intervals constructed using the "continuity-corrected" Bayesian bootstrap (Banks, 1988) have frequentist coverage probability error of only O(n [superscript -1]). In addition, I show that these "continuity-corrected" Bayesian bootstrap credible intervals achieve the same frequentist coverage probability as the frequentist confidence intervals of Goldman and Kaplan (2017), up to some error term of magnitude O(n [superscript -1]). Furthermore, I demonstrate that credible intervals constructed using the "continuity-corrected" Bayesian bootstrap have less frequentist coverage probability error than those constructed using the Bayesian bootstrap (Rubin, 1981). In the second chapter, I investigate three strikes laws, which mandate sharply increased sentences for criminals who commit a specific number of felonies. Specifically, I analyze the effect of these laws on violent crime rates using municipal-level data from the FBI. I compare violent crime rates of border municipalities in states with differing treatment statuses using a difference-in-differences specification with a sample matched on pre-treatment outcomes. I find no statistical evidence that three strikes laws reduce violent crime rates. I rule out reductions in violent crime rates greater than 1.3 [percent] and reject the hypothesis that three strikes laws reduce violent crime rates at the 5 [percent] significance level. Additional analyses and robustness checks support my main findings. In the third chapter, I examine medical marijuana laws (MMLs), which legalize the use, possession, and cultivation of marijuana by individuals with qualifying medical conditions. Namely, I employ municipal-level data from the FBI to analyze the effect of MMLs on violent crime rates. I compare municipalities in border regions with different treatments statuses using a difference-in-differences specification with a sample matched on pre-treatment outcomes. I find a lack of evidence for MMLs increasing violent crime rates, but I cannot eliminate the possibility of small-to-medium positive effects. However, I rule out increases in violent crime rates greater than 9.9 [percent] and reject the hypothesis that MMLs increase violent crime at the 10 [percent] significance level.

Social capital and violent crime rates across U. S. Communities

2002 ◽  
Author(s):  
Steven F. Messner ◽  
Eric P. Baumer ◽  
Richard Rosenfeld
Keyword(s):  
Social Capital ◽  
Violent Crime ◽  
Crime Rates

Is a Decentralized Police Organization a Better Option in a Modern Democratic Society? A Case Study From South Korea

2021 ◽  
pp. 109861112110420
Author(s):  
Sungil Han ◽  
Jennifer LaPrade ◽  
EuiGab Hwang
Keyword(s):  
South Korea ◽  
Violent Crime ◽  
Fear Of Crime ◽  
Police Department ◽  
Property Crime ◽  
Interrupted Time Series ◽  
Crime Rates ◽  
Interrupted Time Series Analysis ◽  
Clearance Rates ◽  
Crime Clearance

While western countries have had a decentralized policing model for many years, some countries, such as South Korea, still employ a centralized, national police department. Responding to calls for reform, South Korea launched a pilot program and implemented a more decentralized policing structure in Jeju Island in 2006. This study adds to the policing literature by offering the empirical comparison of a region before and after decentralization of a police department. This study will examine the intervention effects of police decentralization in Jeju, specifically related to crime rates, crime clearance rates, victimization, trust in police, and fear of crime. Using propensity score matching and interrupted time series analysis, this study found that the decentralized policing intervention significantly reduced total crime, violent crime rates, and property crime rates that lasted throughout the intervention period, while improving crime clearance rates for violent crime, as well as reduced fear of crime among residents.

scholarly journals A call for comparative thinking: Crime, citizenship and security in the global South

2016 ◽  
Author(s):  
Vanessa Barolsky ◽  
Suren Pillay
Keyword(s):  
Latin America ◽  
Violent Crime ◽  
Crime Rates ◽  
Democratic Governance ◽  
Comparative Approach ◽  
Democratic Transitions ◽  
The World ◽  
Resource Poor ◽  
International Comparative ◽  
The Impact

This article argues for the importance of an international comparative perspective in terms of our analysis and response to violent crime. This is particularly important in the light of the fact that while an increasing number of countries in the global Southhave achieved formal democracy, they continue to be plagued by high levels of violent crime. In fact, transitions from authoritarian to democratic governance around the world, from Eastern Europe to Latin America and Africa, have been accompanied by escalating violent crime rates. In this context, we have much to learn from an international comparative approach in terms of understanding why democratic transitions are so often accompanied by increases in violence, what the impact of this violence is on the ability of these societies to deepen democracy, and what the most appropriate interventions are in relatively new and often resource poor democracies.

Club convergence of crime rates in the United States of America

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Kolawole Ogundari
Keyword(s):  
Violent Crime ◽  
Property Crime ◽  
The United States ◽  
Crime Rates ◽  
Community Level ◽  
Club Convergence ◽  
Content Type ◽  
Level Data ◽  
Convergence Club ◽  
Over Time

Purpose The cyclical behavior of US crime rates reflects the dynamics of crime in the country. This paper aims to investigate the US's club convergence of crime rates to provide insights into whether the crime rates increased or decreased over time. The paper also analyzes the factors influencing the probability of states converging to a particular convergence club of crime. Design/methodology/approach The analysis is based on balanced panel data from all 50 states and the district of Columbia on violent and property crime rates covering 1976–2019. This yields a cross-state panel of 2,244 observations with 55 time periods and 51 groups. In addition, the author used a club clustering procedure to investigate the convergence hypothesis in the study. Findings The empirical results support population convergence of violent crime rates. However, the evidence that supports population convergence of property crime rates in the study is not found. Further analysis using the club clustering procedure shows that property crime rates converge into three clubs. The existence of club convergence in property crime rates means that the variation in the property crime rates tends to narrow among the states within each of the clubs identified in the study. Analysis based on an ordered probit model identifies economic, geographic and human capital factors that significantly drive the state's convergence club membership. Practical implications The central policy insight from these results is that crime rates grow slowly over time, as evident by the convergence of violent crime and club convergence of property crime in the study. Moreover, the existence of club convergence of property crime is an indication that policies to mitigate property crime might need to target states within each club. This includes the efforts to use state rather than national crime-fighting policies. Social implications As crimes are committed at the local level, this study's primary limitation is the lack of community-level data on crime and other factors considered. Analysis based on community-level data might provide a better representation of crime dynamics. However, the author hopes to consider this as less aggregated data are available to use in future research. Originality/value The paper provides new insights into the convergence of crime rates using the club convergence procedure in the USA. This is considered an improvement to the methods used in the previous studies.

Abstract 076: Longitudinal Trajectories And Predictors Of County-level Cardiovascular Mortality In The United States (1980-2014)

Circulation ◽  
2021 ◽  
Vol 143 (Suppl_1) ◽  
Author(s):  
Shreya Rao ◽  
Amy E Hughes ◽  
Colby Ayers ◽  
Sandeep R Das ◽  
Ethan A Halm ◽  
...  
Keyword(s):  
Violent Crime ◽  
High Mortality ◽  
Multinomial Logistic Regression ◽  
The United States ◽  
Crime Rates ◽  
Social Characteristics ◽  
Mortality Data ◽  
County Level ◽  
Obesity And Diabetes ◽  
Health Factors

Introduction: CV mortality has declined over 4 decades in the U.S. However, whether declines have been uniformly experienced across U.S. counties, and predictors of CV mortality trajectory are not known. Methods: County-level mortality data from 1980-2014 was obtained from the National Center for Health Statistics. We used a ClustMix approach to identify 3 distinct county phenogroups based on mortality trajectory. Adjusted multinomial logistic regression models were constructed to evaluate the associations between county-level characteristics (demographic, social, and health status) and CV mortality trajectory-based phenogroups. Results: Among 3,133 counties, there were parallel declines in CV mortality in all groups (Fig.1A). High-mortality counties were located in the South and parts of the Ohio and Mississippi River valleys (Fig. 1B). County phenogroups varied significantly in social characteristics such as non-white proportion (low vs. high mortality: 12% vs. 27%), high-school education (11% vs. 20%), and violent crime rates (.01 vs. 0.3/100 population). Disparities in health factors were also observed with higher rates of smoking, obesity, and diabetes in the high (vs. low) mortality groups. A substantial collinearity was observed between social and health factors. In adjusted analysis, social, environmental, and health characteristics explained 56% variance in the county-level CV mortality trajectory. Education status (OR [95% CI]=12.4 [9.4-16.3]), violent crime rates (OR [95% CI] =1.6 [1.3-1.9]), and smoking (OR [95% CI] = 3.9 [3.1- 4.9]) were the strongest predictors of high mortality trajectory phenogroup membership (ref: low mortality). Conclusions: Despite a decline in CV mortality, disparities at the county-level have persisted over the past 4 decades largely driven by differences in social characteristics and smoking prevalence. This highlights the need for multi-domain interventions focusing on safety, education and public health to improve county-level disparities in CV health.

The legacy of military dictatorship: Explaining violent crime in democracies

2018 ◽  
Vol 40 (3) ◽  
pp. 404-418 ◽  
Author(s):  
Erica Frantz
Keyword(s):  
Law Enforcement ◽  
Civil Wars ◽  
Violent Crime ◽  
Statistical Tests ◽  
Crime Rates ◽  
Military Rule ◽  
Military Dictatorship ◽  
Homicide Rates ◽  
The Military ◽  
Cross National

Violent crime rates have increased dramatically in many parts of the world in recent decades, with homicides now outpacing deaths due to interstate or civil wars. Considerable variations exist across democracies in their violent crime rates, however: different autocratic experiences help explain why this is the case. Democracies emerging from military rule have higher homicide rates because they typically inherit militarized police forces. This creates a dilemma after democratization: allowing the military to remain in the police leads to law enforcement personnel trained in defense rather than policing, but extricating it marginalizes individuals trained in the use of violence. The results of cross-national statistical tests are shown to be consistent with this argument.

scholarly journals The Spatial and Social Patterning of Property and Violent Crime in Toronto Neighbourhoods: A Spatial-Quantitative Approach

2019 ◽  
Vol 8 (1) ◽  
pp. 51 ◽  
Author(s):  
Lu Wang ◽  
Gabby Lee ◽  
Ian Williams
Keyword(s):  
Violent Crime ◽  
Property Crime ◽  
Criminal Activity ◽  
Ordinary Least Squares ◽  
Crime Rates ◽  
Individual Characteristics ◽  
Suitable Model ◽  
Similar Distribution ◽  
Wide Range ◽  
The City

Criminal activities are often unevenly distributed over space. The literature shows that the occurrence of crime is frequently concentrated in particular neighbourhoods and is related to a variety of socioeconomic and crime opportunity factors. This study explores the broad patterning of property and violent crime among different socio-economic stratums and across space by examining the neighbourhood socioeconomic conditions and individual characteristics of offenders associated with crime in the city of Toronto, which consists of 140 neighbourhoods. Despite being the largest urban centre in Canada, with a fast-growing population, Toronto is under-studied in crime analysis from a spatial perspective. In this study, both property and violent crime data sets from the years 2014 to 2016 and census-based Ontario-Marginalisation index are analysed using spatial and quantitative methods. Spatial techniques such as Local Moran’s I are applied to analyse the spatial distribution of criminal activity while accounting for spatial autocorrelation. Distance-to-crime is measured to explore the spatial behaviour of criminal activity. Ordinary Least Squares (OLS) linear regression is conducted to explore the ways in which individual and neighbourhood demographic characteristics relate to crime rates at the neighbourhood level. Geographically Weighted Regression (GWR) is used to further our understanding of the spatially varying relationships between crime and the independent variables included in the OLS model. Property and violent crime across the three years of the study show a similar distribution of significant crime hot spots in the core, northwest, and east end of the city. The OLS model indicates offender-related demographics (i.e., age, marital status) to be a significant predictor of both types of crime, but in different ways. Neighbourhood contextual variables are measured by the four dimensions of the Ontario-Marginalisation Index. They are significantly associated with violent and property crime in different ways. The GWR is a more suitable model to explain the variations in observed property crime rates across different neighbourhoods. It also identifies spatial non-stationarity in relationships. The study provides implications for crime prevention and security through an enhanced understanding of crime patterns and factors. It points to the need for safe neighbourhoods, to be built not only by the law enforcement sector but by a wide range of social and economic sectors and services.

scholarly journals Calibrating general posterior credible regions

Biometrika ◽  
2018 ◽  
Vol 106 (2) ◽  
pp. 479-486 ◽  
Author(s):  
Nicholas Syring ◽  
Ryan Martin
Keyword(s):  
Monte Carlo ◽  
Posterior Distribution ◽  
Coverage Probability ◽  
Monte Carlo Algorithm ◽  
Tuning Parameter ◽  
Challenging Problem ◽  
Misspecified Models ◽  
Credible Region ◽  
Frequentist Coverage

Summary Calibration of credible regions derived from under- or misspecified models is an important and challenging problem. In this paper, we introduce a scalar tuning parameter that controls the posterior distribution spread, and develop a Monte Carlo algorithm that sets this parameter so that the corresponding credible region achieves the nominal frequentist coverage probability.

Sign in / Sign up

Export Citation Format

Share Document