Www.sccjr.ac.uk Something Fishy? Uncovering heterogeneity in the distribution of crime victimisation in general populations Tim Hope and Paul Norris SCCJR.

Slides:



Advertisements
Similar presentations
Multiple Indicator Cluster Surveys Survey Design Workshop
Advertisements

Statistical vs Clinical or Practical Significance
TABLE OF CONTENTS CHAPTER 5.0: Workforce Chart 5.1: Total Number of Active Physicians per 1,000 Persons, 1980 – 2009 Chart 5.2: Total Number of Active.
Estimating the Level of Underreporting of Expenditures among Expenditure Reporters: A Further Micro-Level Latent Class Analysis Clyde Tucker Bureau of.
Paul Biemer, UNC and RTI Bac Tran, US Census Bureau Jane Zavisca, University of Arizona SAMSI Conference, 11/10/2005 Latent Class Analysis of Rotation.
The Use of Remand in Scotland and Some Speculative Ideas for Change Sarah Armstrong.
Lecture 5. Social Survey Research III: Other Techniques Of Quantitative Data Collection And Generation: Secondary Data, Experiments And Social Indicators.
Multilevel Multivariate Models with responses at several levels Harvey Goldstein Centre for Multilevel Modelling University of Bristol.
Use of health surveys in resource allocation Matt Sutton Senior Research Fellow University of Glasgow Health Survey's User Group.
S2: Youth Unemployment S2.1 Economic status of young men and women aged S2.2 Regional variations in unemployment and variations within regions S2.3.
The Scottish Crime and Justice Survey Helen Fogarty Research Officer Justice Analytical Services Scottish Government.
Offending Crime and Justice Survey Stephen Roe Crime Surveys Programme, Home Office Tel:
Crime Victimisation Risk – data and modelling requirements Tim Hope and Alan Trickett Keele University © 5 December 2006.
Looking forward to the 2006/07 HBAI publication: New analyses and improvements Peter Matejic (DWP) Households Below Average Income ESDS Government FRS.
Update on BCS developments Crime Surveys User Group - 7 December 2009
The Scottish Crime and Justice Survey Barry Stalker Scottish Government.
THE BRITISH CRIME SURVEY: PRESENTATION TO THE BCS USER GROUP 11 December 2007 Progress with data archiving Last meeting we described our review of current.
Helen Chester University of Manchester. Brief overview of study and findings Focus on issues and recommendations for: Researchers wishing to do similar.
The Economic Impacts of Migration on the UK Labour Market Howard Reed (Landman Economics and ippr) Maria Latorre (ippr) 15 December 2009.
Domestic violence, sexual assault and stalking:
SADC Course in Statistics Assessing data critically Module B1 Session 17.
SADC Course in Statistics Modelling ideas in general – an appreciation (Session 20)
School of Computing FACULTY OF ENGINEERING MJ11 (COMP1640) Modelling, Analysis & Algorithm Design Vania Dimitrova Lecture 18 Statistical Data Analysis:
Test of significance for proportions FETP India
Active Appearance Models
Using Matching Techniques with Pooled Cross-sectional Data Paul Norris Scottish Centre for Crime and Justice Research University of Edinburgh
Rural crime in Scotland: What can we learn from the Scottish Crime Survey and Scottish Neighbourhood Statistics? Susan McVie University of Edinburgh.
Their Strengths and Limitations. 1. Practically – available for free 2. More detail as there are more categories of crime than with the British Crime.
What role should probabilistic sensitivity analysis play in SMC decision making? Andrew Briggs, DPhil University of Oxford.
Point and Confidence Interval Estimation of a Population Proportion, p
Aaker, Kumar, Day Seventh Edition Instructor’s Presentation Slides
Measures of Central Tendency
Aaker, Kumar, Day Ninth Edition Instructor’s Presentation Slides
Multilevel models for predicting personal victimisation in England and Wales Andromachi Tseloni Analysis of crime data ESRC Research Methods Festival 2010.
Chapter 3 Statistical Concepts.
B AD 6243: Applied Univariate Statistics Understanding Data and Data Distributions Professor Laku Chidambaram Price College of Business University of Oklahoma.
Spatial Statistics Applied to point data.
Statistics Workshop Tutorial 3
© 2008 McGraw-Hill Higher Education The Statistical Imagination Chapter 7. Using Probability Theory to Produce Sampling Distributions.
Copyright © 2010, 2007, 2004 Pearson Education, Inc. Review and Preview This chapter combines the methods of descriptive statistics presented in.
Chapter 4 Statistics. 4.1 – What is Statistics? Definition Data are observed values of random variables. The field of statistics is a collection.
Review of the Binomial Distribution Completely determined by the number of trials (n) and the probability of success (p) in a single trial. q = 1 – p If.
Chapter 2 Frequency Distributions
1 Things That May Affect Estimates from the American Community Survey.
Agricultural and Biological Statistics. Sampling and Sampling Distributions Chapter 5.
The Examination of Residuals. Examination of Residuals The fitting of models to data is done using an iterative approach. The first step is to fit a simple.
North Carolina Program Integrity Sampling/Extrapolation Practicum Bradford Woodard, M.S. Senior Health Data Analyst.
Saffron Karlsen 1, James Nazroo 2 1 Department of Epidemiology and Public Health, University College London 2 Sociology, School of Social Sciences, University.
University of Sunderland CSEM03 R.E.P.L.I. Unit 1 CSEM03 REPLI Research and the use of statistical tools.
To accompany Quantitative Analysis for Management, 9e by Render/Stair/Hanna 17-1 © 2006 by Prentice Hall, Inc. Upper Saddle River, NJ Chapter 17.
Welcome to MM305 Unit 8 Seminar Diallo Wallace Statistical Quality Control.
Lecture 2 Forestry 3218 Lecture 2 Statistical Methods Avery and Burkhart, Chapter 2 Forest Mensuration II Avery and Burkhart, Chapter 2.
Copyright © 2014 by Nelson Education Limited. 3-1 Chapter 3 Measures of Central Tendency and Dispersion.
Catherine Millington Scottish Crime and Justice Survey,
Agenda Descriptive Statistics Measures of Spread - Variability.
June 11, 2008Stat Lecture 10 - Review1 Midterm review Chapters 1-5 Statistics Lecture 10.
1 Descriptive Statistics 2-1 Overview 2-2 Summarizing Data with Frequency Tables 2-3 Pictures of Data 2-4 Measures of Center 2-5 Measures of Variation.
BASIC STATISTICAL CONCEPTS Chapter Three. CHAPTER OBJECTIVES Scales of Measurement Measures of central tendency (mean, median, mode) Frequency distribution.
An ecological analysis of crime and antisocial behaviour in English Output Areas, 2011/12 Regression modelling of spatially hierarchical count data.
Probability and Distributions. Deterministic vs. Random Processes In deterministic processes, the outcome can be predicted exactly in advance Eg. Force.
3.1 Statistical Distributions. Random Variable Observation = Variable Outcome = Random Variable Examples: – Weight/Size of animals – Animal surveys: detection.
Chapter15 Basic Data Analysis: Descriptive Statistics.
Approaches to quantitative data analysis Lara Traeger, PhD Methods in Supportive Oncology Research.
Measures of Dispersion Measures of Variability
Multiple Regression Reference: Chapter 18 of Statistics for Management and Economics, 7 th Edition, Gerald Keller. 1.
1. Data Processing Sci Info Skills.
Elementary Applied Statistics
Types of Poisson Regression. Offset Regression  A variant of Poisson Regression  Count data often have an exposure variable, which indicates the number.
Mean, Median, Mode The Mean is the simple average of the data values. Most appropriate for symmetric data. The Median is the middle value. It’s best.
Introductory Statistics
Presentation transcript:

Something Fishy? Uncovering heterogeneity in the distribution of crime victimisation in general populations Tim Hope and Paul Norris SCCJR (CJ-QUEST) University of Edinburgh December 2008

The Distribution of Property Crime in the BCS Maximum count present in BCS is 27. Based on six crimes capped at 6 incidents per crime. Unweighted BCS Sample: , , , 2003/ , 2006/ , Total

Understanding and Modelling the Distribution of Crime The distribution shown on the previous slide poses two questions :- - Substantive question: What is the data generation process that underpins the distribution? - Statistical question: What kind of dependent variable is best employed to model victimisation?

Theoretical Models of Victimisation Simple Exposure (pure heterogeneity) Mixture Model Simple RV (pure state-dependency) T. Hope and A. Trickett (2004). La distribution de la victimation dans la population, Déviance et Société, 28 (3), Large proportion of the population experience no victimisation - Small proportion of the population experience chronic victimisation - One or more groups for low-level victimisation

Dependent Variable for Victimisation Research Type of crime victimisation –Type of incident –One type verses more generalist victim Frequency of crime victimisation –Nominal (0,1), Ordinal (0, 1, 2+), Count (0-n) –Distribution of count variables – Poisson verses Negative Binomial

Data British Crime Survey - England and Wales (BCS) – 1992, 1996, 2001, 2003/04, 2006/07 Scottish Crime Victimisation Survey (SCVS) –1993, 1996, 2000, 2003, 2006 Crime types –Household Property Crime (6 questions) –Count data (victim screeners, capped at 6)

Latent Class Models Latent Class Analysis (LCA) is analogous to cluster analysis but:Latent Class Analysis (LCA) is analogous to cluster analysis but: -Can handle missing data-Can handle missing data -Can handle non-normal data-Can handle non-normal data -Can be used with longitudinal data-Can be used with longitudinal data

A Simple LCA Model Victim Type Household Theft Victimisation Vandalism VictimisationForced Entry Victimisation ++= Total Victimisation AgeHousehold IncomeNeighbourhood Type LCA indicator considers both level of victimisation and type of crime

Accuracy Verses Parsimony How many groups are required? -range of statistical indicators -substantive interpretation is crucial Within group variation?

Distribution of Victimisation Indicators Count data often modelled using Poisson distribution Victimisation appears to follow Negative Binomial distribution BCS Combined Sample VariableMeanStd. DevVarianceRatio of Variance to Mean Defaced Property (Outside) Stolen Property (Outside) Property Stolen from Home Tried to Gain Entry to Commit Theft/Damage Entered Property and Caused Damage Entered Property and Commited Theft Unweighted BCS Sample: , , , 2003/ , 2006/ , Total What about zero-inflation?

ABIC for BCS Data Lower ABIC figures represent better fit between model and data ABIC suggests six groups should be used Results based on Negative Binomial Distribution. Results using zero-inflated Negative Binomial reveal an identical pattern but exhibit a slightly worse fit to the data

BCS Six Class Solution

Results for Scottish Data Distribution of property crime in Scottish data is very similar to BCS ABIC statistic suggests 4 class solution is optimal Results based on Negative Binomial Distribution. Results using zero-inflated Negative Binomial reveal an identical pattern but exhibit a slightly worse fit to the data

Scottish 4 Class Solution

Summary Overall distribution obscures heterogeneity Heterogeneity of both substantive and statistical interest Most uncertainty occurs around the middle of the distribution Key issues around how solution is affected by sample design, prevalence of incidents and how useful apparent classes are for analysis