The Relationship between First Imprisonment and Criminal Career Development: A Matched Samples Comparison Paul Nieuwbeerta & Arjan Blokland NSCR Daniel.

Slides:



Advertisements
Similar presentations
Non-randomized Medical Device Clinical Studies: A Regulatory Perspective Sep. 16, 2005 Lilly Yue, Ph.D.* CDRH, FDA, Rockville MD * No official support.
Advertisements

When the inevitable happens— rising, not falling crime rates—What to do? DANIEL S. NAGIN CARNEGIE MELLON UNIVERSITY STOCKHOLM CRIMINOLOGY SYMPOSIUM JUNE.
The effectiveness of suspended sentences in reducing reoffending
1 Arlene Ash QMC - Third Tuesday September 21, 2010 (as amended, Sept 23) Analyzing Observational Data: Focus on Propensity Scores.
Oklahoma Department of Corrections DUI Offender Profile
Explaining Race Differences in Student Behavior: The Relative Contribution of Student, Peer, and School Characteristics Clara G. Muschkin* and Audrey N.
Residential Community Supervision Programs
" The Impact of Criminal Justice Policies and Practices on Minorities" 2009.
An Overview of Two Recent Advances in Trajectory Modeling Daniel S Nagin.
Drug Offender Sentencing Alternative (DOSA): Treatment and Supervision
Re-Entry and Recidivism
Observational Studies Based on Rosenbaum (2002) David Madigan Rosenbaum, P.R. (2002). Observational Studies (2 nd edition). Springer.
Incarceration and Fragile Families Bruce Western, Princeton University Leonard M. Lopoo, Syracuse University Sara McLanahan, Princeton University May 2004.
Justice Griffith 1 Juvenile Offending Trajectories A Queensland Study.
Group Risk Assessment Model Monitoring trends in re-offending among convicted offenders in adult and children’s court Fourth National Justice Modelling.
The Relationship between First Imprisonment and Criminal Career Development: A Matched Samples Comparison Presentation at the 2 nd Annual Workshop on Criminology.
Method Introduction Results Discussion Sex Offenders: How Treatment, Employment, and Level of Denial Relate to Education and IQ Caitlyn E. McNeil University.
The transition from juvenile to adult criminal careers Bureau of Crime Statistics and Research.
1 Psychological Symptoms among Young Maltreated Children: Do Services Make a Difference? The research for this presentation was funded by the Administration.
Incarceration and the Transition to Adulthood Gary Sweeten Arizona State University Robert Apel University at Albany June 4, Crime and Population.
Re-validation of the Nonviolent Offender Risk Assessment Instrument: Preliminary Findings.
“Once a sex offender, always a sex offender?” Claire Hargreaves – Professor Brian Francis – Department.
Evaluation of the Connecticut Judicial Branch’s Three Court-Mandated Family Violence Programs: FVEP, EXPLORE, and EVOLVE Stephen M. Cox, Ph.D, Professor.
Modeling Developmental Trajectories: A Group-based Approach
Incapacitation, Recidivism and Predicting Behavior Easha Anand Intro. To Data Mining April 24, 2007.
Chapter 8 Residential Intermediate Sanctions. Introduction Intermediate Sanctions are sentencing options between prison and probation that provide punishment.
Less Is More? An Application of Propensity Score Stratification to First-Grade Retention Mieke Goos, Jan Van Damme, Patrick Onghena and Katja Petry SREE.
Unpacking the Relationship Between Adolescent Employment and Antisocial Behavior: A Matched Samples Comparison Robert Apel, University at Albany Robert.
The Effects of Time in Prison on Male Felons’ Employment and Earnings Haeil Jung University of Chicago 2007 Crime and Population Dynamics Summer Workshop.
Propensity Score Matching and Variations on the Balancing Test Wang-Sheng Lee Melbourne Institute of Applied Economic and Social Research The University.
Modeling Developmental Trajectories: A Group-based Approach Daniel S. Nagin Carnegie Mellon University.
1 CRJS 4476 Lecture #2. 2 Sentencing key here is in understanding the difference key here is in understanding the difference between the conviction and.
Imprisonment and Crime: Can Both be Reduced? Daniel S. Nagin Carnegie Mellon University National Association of Sentencing Commissions August 7, 2012.
North Carolina TASC NC TASC Bridging Systems for Effective Offender Care Management.
Discussion of Hujer, R. and S. Thomsen (2006). “How Do Employment Effects of Job Creation Schemes Differ with Respect to the Foregoing Unemployment Duration?”
Overview of Split Sentencing Research October 25, 2006 Mark Rubin.
Article Review Cara Carty 09-Mar-06. “Confounding by indication in non-experimental evaluation of vaccine effectiveness: the example of prevention of.
Probation Effectiveness
Salient Factor Score CTSFS99. What it is How to use it.
The Price of Violence Long term effects of assault on labor force participation and health Petra Ornstein, Uppsala university.
Propensity Score Matching for Causal Inference: Possibilities, Limitations, and an Example sean f. reardon MAPSS colloquium March 6, 2007.
The Health Consequences of Incarceration Michael Massoglia Penn State University.
In Search of the Intermittent Offender: A Theoretical and Statistical Journey Megan C. Kurlychek, Ph.D. Assistant Professor Shawn Bushway, Ph.D. Associate.
Generalizing Observational Study Results Applying Propensity Score Methods to Complex Surveys Megan Schuler Eva DuGoff Elizabeth Stuart National Conference.
Can Mental Health Services Reduce Juvenile Justice Involvement? Non-Experimental Evidence E. Michael Foster School of Public Health, University of North.
Chapter 7 Prison Populations Size and Nature of Prison Populations Severity of legal sanctions General social-demographic trends –Aging of population.
NOT PROTECTIVELY MARKED Integrated Offender Management: A Multiagency Desistance Programme C/Supt Andy Williams MStBarak Ariel PhD.
Nora Wikoff August 19, Former prisoners face hurdles to gainful employment Recidivism rates are high among former prisoners Prison- and community-based.
Extending Group-Based Trajectory Modeling to Account for Subject Attrition (Sociological Methods & Research, 2011) Amelia Haviland Bobby Jones Daniel S.
Introduction Results Treatment Needs and Treatment Completion as Predictors of Return-to-Prison Following Community Treatment for Substance-Abusing Female.
A Claims Database Approach to Evaluating Cardiovascular Safety of ADHD Medications A. J. Allen, M.D., Ph.D. Child Psychiatrist, Pharmacologist Global Medical.
Using propensity score matching to understand what works in reducing re-offending GSS Methodology Symposium Sarah French & Aidan Mews, Ministry of Justice.
Using Propensity Score Matching in Observational Services Research Neal Wallace, Ph.D. Portland State University February
Are fines criminogenic? The impact of fines on re-offending in NSW local courts David Tait Justice Research Group University of Western Sydney With Alice.
Racial Disparities in Criminal Justice in Wisconsin Pamela Oliver.
Life course partnership status and biomarkers in mid-life: Evidence from the 1958 British birth cohort George B. Ploubidis, Richard J. Silverwood, Bianca.
Psychology 3.1 Imprisonment. Psychology Learning outcome: Planned behaviours once freed from jail (factors affecting recidivism, Gillis, C. A. and Nafekh,
The Relationship between First Imprisonment and Criminal Career Development: A Matched Samples Comparison Paul Nieuwbeerta & Arjan Blokland NSCR Daniel.
The Impact of Mandatory Supervised Release (MSR) Violators & Time Served on IDOC’s Population David E. Olson, Ph.D. & Donald Stemen, Ph.D. Department of.
Department of Sociology & Criminal Justice What is an appropriate punishment or response? What do you expect your response to do for the offender, potential.
Peter Conlong Justice Analytical Services Scottish Government
Creation of synthetic microdata in 2021 Census Transformation Programme (proof of concept) Robert Rendell.
Sec 9C – Logistic Regression and Propensity scores
Dutch terrorist suspects
1 Panel 2, Position 5 Jack D. Ripper.
Presenter: Wen-Ching Lan Date: 2018/03/28
The European Statistical Training Programme (ESTP)
Chapter: 9: Propensity scores
Recidivism Among DWI Offenders in New Mexico (Preliminary Results)
The Impact of incarceration on the risk of violent recidivism
Presentation transcript:

The Relationship between First Imprisonment and Criminal Career Development: A Matched Samples Comparison Paul Nieuwbeerta & Arjan Blokland NSCR Daniel Nagin Carnegie-Mellon University

Imprisonment in Europe and the USA (Circa 2005) Country Jail & Prison Population Prisoners per population USA European Union England & Wales Netherlands

Main Question What is the effect of imprisonment on the subsequent criminal career development of those actually imprisoned? Methodology builds upon work with Amelia Haviland (Rand) and Paul Rosenbaum (Penn) that combines propensity score matching and group-based trajectory modeling

Possible Effect of Imprisonment on Crime On the wider society—general deterrence On the criminality of the imprisoned individual – Incapacitation (-) – Specific Deterrence (-) – Rehabilitation (-) – Labeling/stigma (+) – School of crime (+)

Criminal Career and Life Course Study CCLS Data Sample: persons convicted in 1977 in the Netherlands – 4% random sample of all persons convicted in 1977 – 500 women (10%) – 20% non-Dutch (Surinam, Indonesia) – Mean age in 1977: 27 years; youngest: 12; oldest 79 – Data from year of birth until 2003: for most over 50 years.

CCLS Data Full criminal conviction histories (Rap sheets) – Timing, type of offense, type of sentence, imprisonment. Life course events (N=4,615): – Various types: marriage, divorce, children, moving, death (GBA & Central Bureau Heraldry) – incl. Exact timing. – Cause of death (CBS)

Outcome variable Number of convictions in three year period after year of first-time imprisonment

Outcome variable Number of convictions in three year period after year of first-time imprisonment First-time imprisonment effects measured by age from 18 to 39

Outcome variable Number of convictions in three year period after year of first-time imprisonment First-time imprisonment effects measured for ages 18 to 39 Limit analysis to persons with sentences of less than 1 year – 80% less than 6 months – 99% less than 1 year

Outcome variable Number of convictions in three year period after year of first-time imprisonment First-time imprisonment effects measured for ages 18 to 39 Limit analysis to persons with sentences of less than 1 year Correction for exposure-time / incarceration

Estimating the effect of imprisonment on the imprisoned: Some important contingencies and challenges Prior experience with imprisonment – Limit analysis to first-time imprisonment effects

Estimating the effect of imprisonment on the imprisoned: Some important contingencies and challenges Prior experience with imprisonment Age

Estimating the effect of imprisonment on the imprisoned: Some important contingencies and challenges Prior experience with imprisonment Age—exact matching on age

Estimating the effect of imprisonment on the imprisoned: Some important contingencies and challenges Prior experience with imprisonment Age Sex—Males only

Estimating the effect of imprisonment on the imprisoned: Some important contingencies and challenges Prior experience with imprisonment Age Sex Prior trajectory of offending – Estimate effects contingent on prior trajectory of offending

Estimating the effect of imprisonment on the imprisoned: Some important contingencies and challenges Prior experience with imprisonment Age Sex Prior trajectory of offending Selection—Imprisonment more likely for higher propensity offenders

Differences in prior records of those imprisoned at age and those convicted but not imprisoned

Other differences between imprisoned and non-imprisoned

Overview of Approach Focus on the effect of first-time imprisonment Match individuals who are the same age – Estimate effects of first-time imprisonment by age from Males only Estimate effects contingent on trajectory of prior offending Use risk set matching to balance measured differences between the imprisoned and the non- imprisoned

Estimating Effect of 1 st Time Imprisonment at Age t (t=18,..38) Estimate trajectory model on convictions thru t-1 for the never imprisoned thru t-1 Within trajectory group match 1 st time imprisoned at age t with comparable individuals receiving non- custodial sanctions at age t Check for balance between the imprisoned and their matched controls Estimate effect of 1 st time imprisonment in 3 years following the year of imprisonment

Use Group-based Trajectory Modeling to Test for Prior Offending Contingencies Based on finite mixture modeling – Poisson distribution this application – Cubic link function for rate Designed to identify clusters of individuals with similar trajectories of prior offending Trajectory groups can be thought of as latent strata of the pre-treatment time path of the outcome variable

Trajectories of Number of Convictions: age , age and age 12-30

Trajectories of Number of Convictions (cont.)

What is a propensity score? Propensity score is the probability of treatment (e.g., imprisonment) as a function of pre-treatment covariates (e.g., prior record; conviction offense characteristics) Propensity score matching balances imprisoned and non-imprisoned on these covariates Rules them out as potential confounders Important caution: Still may be unmeasured confounders

Risk Set Matching to Balance Measured Covariate Differences Imprisoned at age t matched with up to 3 non- imprisoned but convicted at t with same probability of imprisonment at t Time dependent propensity for imprisonment at t based on covariates measured up to t Propensity for imprisonment at t measured by logit model of imprisonment at t

Constructing the Propensity Score Logistic regression Independent variables – Characteristics of Conviction Offense Violence, property.. Severity – Criminal history characteristics: Num. of convictions age 12-25, and at 25, Age of first registration, age of first conviction, Trajectory group membership probabilities. – Personal Characteristics: Age in 1977, non-Dutch, Unemployed around age 25, Number of years married at age 25, Married at age 25, Number of years children at age 25, children at age 25, Alcohol and/or drugs dependent around age 25

Matching Strategy Randomly selected 50% of those imprisoned for the first time between to serve as “treated at t” pool Remaining 50% served as potential controls but only up to the year of their imprisonment Randomly selected among the treated pool, noted year of imprisonment t and matched to non-imprisoned but convicted based on propensity score at t Used.05 caliper

Number of Imprisoned and non-imprisoned offenders - Full and Matched Sample Full sample Matched sample At ageImprisonedNot Imprisoned ImprisonedNot Imprisoned Total

Box plots of propensity scores: Full sample

Significant differences before and after matching Before Matching (partial listing) – Convictions (also by type) – Convictions (also by type) – Convictions 25 (also by type) – Numerous Conviction offence characteristics – Age in ’77 – Non-Dutch – # of children at 25

Box plots of propensity scores: Matched sample

Significant differences before and after matching Before Matching (partial listing) – Convictions (also by type) – Convictions (also by type) – Convictions 25 (also by type) – Numerous Conviction offence characteristics – Age in ’77 – Non-Dutch – # of children at 25 After matching – Cohort (marginal) – # violent convictions past 5 years (marginal )

Calculation of Effect of 1 st time Imprisonment: Average of Differences

Further Analyses Analysis of more recent data—1997 conviction cohort Analysis of groups on the “margin” of imprisonment Analysis of mediating processes—What is the source of the criminogenic effect Bounding ala Manski and Nagin (1998) to account for the possible effects of “hidden bias”

Conclusions Conclusion: – First-time imprisonment appears to increase conviction rate by.4 convictions per year in first 3 years after imprisonment – No 1 st imprisonment effects apparent after age 25 Theoretical implications—Criminogenic effects of first- time imprisonment outweigh any preventive effects for the individual who is sanctioned Policy implications: – Incapacitation and general deterrent effect of imprisonment may partly be nullified by imprisoned offenders subsequently offending at higher rates