Analyzing multiple-item measures of crime and deviance II: Tobit regression analysis of transformed scores

D. Wayne Osgood, Laura L. Finken, Barbara J. McMorris

Research output: Contribution to journalArticle

122 Citations (Scopus)

Abstract

The purpose of this article is to inform criminological researchers about tobit regression, an alternative regression model that deserves more attention in this field. Tobit regression is intended for continuous data that are censored, or bounded at a limiting value. The tobit model may be a particularly good match to measures of self-reported offending, provided they have been transformed to reduce skewness. We present empirical analyses that evaluate the match of self-report measures to the assumptions of ordinary least square (OLS) and tobit regression models and that assess the consequences of any violations of assumptions. The analyses use a fourteen-item, self-report measure of delinquency from the Monitoring the Future study, a national survey of high school seniors. These analyses provide clear evidence that (1) transformations to reduce skewness improve the match of OLS to the data but still leave considerable discrepancies, and (2) the tobit model is well suited to the transformed measure. We conclude by assessing the purposes for which tobit offers greater and smaller advantages over OLS regression.

Original languageEnglish (US)
Pages (from-to)319-347
Number of pages29
JournalJournal of Quantitative Criminology
Volume18
Issue number4
DOIs
StatePublished - Dec 1 2002

Fingerprint

Crime
deviant behavior
Least-Squares Analysis
regression analysis
Regression Analysis
offense
regression
Self Report
Research Personnel
delinquency
monitoring
school
evidence
Values

All Science Journal Classification (ASJC) codes

  • Pathology and Forensic Medicine
  • Law

Cite this

Osgood, D. Wayne ; Finken, Laura L. ; McMorris, Barbara J. / Analyzing multiple-item measures of crime and deviance II : Tobit regression analysis of transformed scores. In: Journal of Quantitative Criminology. 2002 ; Vol. 18, No. 4. pp. 319-347.
@article{aac0ca6ab15a472199806148fcf889c3,
title = "Analyzing multiple-item measures of crime and deviance II: Tobit regression analysis of transformed scores",
abstract = "The purpose of this article is to inform criminological researchers about tobit regression, an alternative regression model that deserves more attention in this field. Tobit regression is intended for continuous data that are censored, or bounded at a limiting value. The tobit model may be a particularly good match to measures of self-reported offending, provided they have been transformed to reduce skewness. We present empirical analyses that evaluate the match of self-report measures to the assumptions of ordinary least square (OLS) and tobit regression models and that assess the consequences of any violations of assumptions. The analyses use a fourteen-item, self-report measure of delinquency from the Monitoring the Future study, a national survey of high school seniors. These analyses provide clear evidence that (1) transformations to reduce skewness improve the match of OLS to the data but still leave considerable discrepancies, and (2) the tobit model is well suited to the transformed measure. We conclude by assessing the purposes for which tobit offers greater and smaller advantages over OLS regression.",
author = "Osgood, {D. Wayne} and Finken, {Laura L.} and McMorris, {Barbara J.}",
year = "2002",
month = "12",
day = "1",
doi = "10.1023/A:1021198509929",
language = "English (US)",
volume = "18",
pages = "319--347",
journal = "Journal of Quantitative Criminology",
issn = "0748-4518",
publisher = "Springer New York",
number = "4",

}

Analyzing multiple-item measures of crime and deviance II : Tobit regression analysis of transformed scores. / Osgood, D. Wayne; Finken, Laura L.; McMorris, Barbara J.

In: Journal of Quantitative Criminology, Vol. 18, No. 4, 01.12.2002, p. 319-347.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Analyzing multiple-item measures of crime and deviance II

T2 - Tobit regression analysis of transformed scores

AU - Osgood, D. Wayne

AU - Finken, Laura L.

AU - McMorris, Barbara J.

PY - 2002/12/1

Y1 - 2002/12/1

N2 - The purpose of this article is to inform criminological researchers about tobit regression, an alternative regression model that deserves more attention in this field. Tobit regression is intended for continuous data that are censored, or bounded at a limiting value. The tobit model may be a particularly good match to measures of self-reported offending, provided they have been transformed to reduce skewness. We present empirical analyses that evaluate the match of self-report measures to the assumptions of ordinary least square (OLS) and tobit regression models and that assess the consequences of any violations of assumptions. The analyses use a fourteen-item, self-report measure of delinquency from the Monitoring the Future study, a national survey of high school seniors. These analyses provide clear evidence that (1) transformations to reduce skewness improve the match of OLS to the data but still leave considerable discrepancies, and (2) the tobit model is well suited to the transformed measure. We conclude by assessing the purposes for which tobit offers greater and smaller advantages over OLS regression.

AB - The purpose of this article is to inform criminological researchers about tobit regression, an alternative regression model that deserves more attention in this field. Tobit regression is intended for continuous data that are censored, or bounded at a limiting value. The tobit model may be a particularly good match to measures of self-reported offending, provided they have been transformed to reduce skewness. We present empirical analyses that evaluate the match of self-report measures to the assumptions of ordinary least square (OLS) and tobit regression models and that assess the consequences of any violations of assumptions. The analyses use a fourteen-item, self-report measure of delinquency from the Monitoring the Future study, a national survey of high school seniors. These analyses provide clear evidence that (1) transformations to reduce skewness improve the match of OLS to the data but still leave considerable discrepancies, and (2) the tobit model is well suited to the transformed measure. We conclude by assessing the purposes for which tobit offers greater and smaller advantages over OLS regression.

UR - http://www.scopus.com/inward/record.url?scp=0036439184&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036439184&partnerID=8YFLogxK

U2 - 10.1023/A:1021198509929

DO - 10.1023/A:1021198509929

M3 - Article

AN - SCOPUS:0036439184

VL - 18

SP - 319

EP - 347

JO - Journal of Quantitative Criminology

JF - Journal of Quantitative Criminology

SN - 0748-4518

IS - 4

ER -