Hierarchical Bayesian analysis of arrest rates

Jacqueline Cohen, Daniel Nagin, Garrick Wallstrom, Larry Wasserman

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

A Bayesian hierarchical model provides the basis for calibrating the crimes avoided by incarceration of individuals convicted of drug offenses compared to those convicted of nondrug offenses. Two methods for constructing reference priors for hierarchical models both lead to the same prior in the final model. We use Markov chain Monte Carlo methods to fit the model to data from a random sample of past arrest records of all felons convicted of drug trafficking, drug possession, robbery, or burglary in Los Angeles County in 1986 and 1990. The value of this formal analysis, as opposed to a simpler analysis that does not use the formal machinery of a Bayesian hierarchical model, is to provide interval estimates that account for the uncertainty due to the random effects.

Original languageEnglish (US)
Pages (from-to)1260-1270
Number of pages11
JournalJournal of the American Statistical Association
Volume93
Issue number444
StatePublished - Dec 1998
Externally publishedYes

Fingerprint

Bayesian Analysis
Bayesian Hierarchical Model
Drugs
Reference Prior
Formal Analysis
Markov Chain Monte Carlo Methods
Hierarchical Model
Random Effects
Uncertainty
Interval
Model
Estimate
Bayesian analysis
Bayesian hierarchical model

Keywords

  • Crime data: Hierarchical models
  • Markov chain Monte Carlo

ASJC Scopus subject areas

  • Mathematics(all)
  • Statistics and Probability

Cite this

Cohen, J., Nagin, D., Wallstrom, G., & Wasserman, L. (1998). Hierarchical Bayesian analysis of arrest rates. Journal of the American Statistical Association, 93(444), 1260-1270.

Hierarchical Bayesian analysis of arrest rates. / Cohen, Jacqueline; Nagin, Daniel; Wallstrom, Garrick; Wasserman, Larry.

In: Journal of the American Statistical Association, Vol. 93, No. 444, 12.1998, p. 1260-1270.

Research output: Contribution to journalArticle

Cohen, J, Nagin, D, Wallstrom, G & Wasserman, L 1998, 'Hierarchical Bayesian analysis of arrest rates', Journal of the American Statistical Association, vol. 93, no. 444, pp. 1260-1270.
Cohen J, Nagin D, Wallstrom G, Wasserman L. Hierarchical Bayesian analysis of arrest rates. Journal of the American Statistical Association. 1998 Dec;93(444):1260-1270.
Cohen, Jacqueline ; Nagin, Daniel ; Wallstrom, Garrick ; Wasserman, Larry. / Hierarchical Bayesian analysis of arrest rates. In: Journal of the American Statistical Association. 1998 ; Vol. 93, No. 444. pp. 1260-1270.
@article{01714d1a5c4b402a924b2757d73f248d,
title = "Hierarchical Bayesian analysis of arrest rates",
abstract = "A Bayesian hierarchical model provides the basis for calibrating the crimes avoided by incarceration of individuals convicted of drug offenses compared to those convicted of nondrug offenses. Two methods for constructing reference priors for hierarchical models both lead to the same prior in the final model. We use Markov chain Monte Carlo methods to fit the model to data from a random sample of past arrest records of all felons convicted of drug trafficking, drug possession, robbery, or burglary in Los Angeles County in 1986 and 1990. The value of this formal analysis, as opposed to a simpler analysis that does not use the formal machinery of a Bayesian hierarchical model, is to provide interval estimates that account for the uncertainty due to the random effects.",
keywords = "Crime data: Hierarchical models, Markov chain Monte Carlo",
author = "Jacqueline Cohen and Daniel Nagin and Garrick Wallstrom and Larry Wasserman",
year = "1998",
month = "12",
language = "English (US)",
volume = "93",
pages = "1260--1270",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",
number = "444",

}

TY - JOUR

T1 - Hierarchical Bayesian analysis of arrest rates

AU - Cohen, Jacqueline

AU - Nagin, Daniel

AU - Wallstrom, Garrick

AU - Wasserman, Larry

PY - 1998/12

Y1 - 1998/12

N2 - A Bayesian hierarchical model provides the basis for calibrating the crimes avoided by incarceration of individuals convicted of drug offenses compared to those convicted of nondrug offenses. Two methods for constructing reference priors for hierarchical models both lead to the same prior in the final model. We use Markov chain Monte Carlo methods to fit the model to data from a random sample of past arrest records of all felons convicted of drug trafficking, drug possession, robbery, or burglary in Los Angeles County in 1986 and 1990. The value of this formal analysis, as opposed to a simpler analysis that does not use the formal machinery of a Bayesian hierarchical model, is to provide interval estimates that account for the uncertainty due to the random effects.

AB - A Bayesian hierarchical model provides the basis for calibrating the crimes avoided by incarceration of individuals convicted of drug offenses compared to those convicted of nondrug offenses. Two methods for constructing reference priors for hierarchical models both lead to the same prior in the final model. We use Markov chain Monte Carlo methods to fit the model to data from a random sample of past arrest records of all felons convicted of drug trafficking, drug possession, robbery, or burglary in Los Angeles County in 1986 and 1990. The value of this formal analysis, as opposed to a simpler analysis that does not use the formal machinery of a Bayesian hierarchical model, is to provide interval estimates that account for the uncertainty due to the random effects.

KW - Crime data: Hierarchical models

KW - Markov chain Monte Carlo

UR - http://www.scopus.com/inward/record.url?scp=0032260516&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032260516&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0032260516

VL - 93

SP - 1260

EP - 1270

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 444

ER -