1 Introduction

This report describes the design and methods used in the 2006 New Zealand Crime and Safety Survey (2006 NZCASS hereafter). The survey was conducted for the Ministry of Justice by a consortium comprising the Crime and Justice Research Centre (Victoria University), ACNielsen (who managed the fieldwork), James Reilly (Statistical Insights), and two Māori consultants, Laurie Porima and Nan Wehipeihana (of LLE Research).

The 2006 NZCASS was based on a nationally representative random sample of 5,416 people aged 15 and over living in private households throughout New Zealand (excluding most offshore islands). This includes a 'booster' sample of 1,187 Māori. Those who took part were interviewed at home between February and June 2006 by ACNielsen interviewers. They were asked whether they had been a victim of crimes covered by the survey since 1st January 2005. They were asked about the circumstances and impact of any offences they had experienced, and about a number of other crime-related issues.

This is the third time that a national victimisation survey has been run in New Zealand. The two previous surveys were conducted in 1996 and 2001, under the title of the New Zealand National Survey of Crime Victims (NSCV). ACNielsen carried out both in conjunction with the Crime and Justice Research Centre (Victoria University).

What the 2006 New Zealand Crime and Safety Survey does

The 2006 NZCASS offers a wide range of information:

• It measures the amount of crime in New Zealand in 2005 by asking people about crimes they experienced themselves. The survey includes crimes not reported to the police, so it is an important alternative to police records. Victims do not report crime for various reasons. Without the NZCASS, we would have no information on these unreported crimes.

• It looks at how many offences are reported to the police, and the reasons for not reporting. It also looks at how well victims thought the Police responded when a crime report was made.

• The survey can examine trends in survey-measured crime since 1996 and 2001, although there are limits on the comparisons imposed by changes in survey design.[1]

• The survey helps identify those most at risk of different types of crime in terms of age, gender, ethnicity, etc. This helps in planning crime prevention programmes. As said, Police figures tell us little on this front.

• It gives information on the nature of victimisation, such as its physical, financial and emotional effects.

• It gives information on the public's perception of crime problems in their area, and on their concerns about personal victimisation.

Structure of report

This report generally follows a chronological path through the design and methodology employed in the NZCASS. The sample design is described first, followed by questionnaire design and testing. Interviewer and fieldwork procedures are covered next, then the validation and checking of interviews. Response rate calculations are shown, along with an analysis of interview length.

The classifications and standards used in the NZCASS are then detailed, followed by descriptions of the weighting and imputation methods used in the survey.

Footnote

1 Initially changes between the 2001 and 2006 surveys were to be minimised to avoid these complications where possible, and much of the sample design and estimation framework reflects this initial emphasis. Significant changes to the questionnaire were later found to be necessary, requiring associated modifications to the sampling and imputation design.