U.S. Department of Justice Office of Justice Programs Bureau of Justice Statistics Bulletin Criminal Victimization, 2006 December 2007, NCJ 219413 ----------------------------------------------------------- ----------------------------------------------------------- This file is text only without graphics and many of the tables. A Zip archive of the tables in this report in spreadsheet format (.csv) and the full report including tables and graphics in .pdf format are available from: http://www.ojp.usdoj.gov/bjs/abstract/cv06.htm ------------------------------------------------------------ ----------------------------------------------------------- This report is one in a series. More recent editions may be available. To view a list of all in the series go to http://www.ojp.usdoj.gov/bjs/pubalp2.htm#cvus ------------------------------------------------------------ ------------------------------------------------------------ by Michael Rand and Shannan Catalano, Ph.D. BJS Statisticians ------------------------------------------------------------ NCVS estimates based on new methods Violent and property crime rates in urban and suburban areas of the United States remained stable between 2005 and 2006, according to findings from the National Crime Victimization Survey (NCVS). Due to changes in survey methodology in 2006 that mainly affected rural areas, national-level estimates were not comparable to estimates based on NCVS data from previous years. Continuity between urban and suburban areas in the sample for both years enabled year-to-year comparisons for these areas. In urban and suburban areas, U.S. residents age 12 or older in 2006 experienced an estimated 3.7 million violent crimes (rape or sexual assault, robbery, and aggravated and simple assault), 138,520 personal thefts (pocket picking and purse snatching), and 12 million property crimes (burglary, motor vehicle theft, and theft).***footnote 1: Estimates are based on urban and suburban areas in the sample (continuing areas) in both 2005 and 2006. See forthcoming Technical notes for details on changes in sample design.*** The overall violent crime rate in these areas was 23.3 victimizations per 1,000 persons age 12 or older; the property crime rate was 159.1 per 1,000 households. The U.S. Census Bureau, the Bureau of Justice Statistics (BJS), and a panel of outside experts extensively reviewed the 2006 NCVS data and determined that there was a break in series between 2006 and previous years that prevented annual comparison of criminal victimization at the national level. This was mainly the result of three major changes in the survey methodology-- *introducing a new sample to account for shifts in population and location of households that occur over time *incorporating responses from households that were in the survey for the first time *using computer-assisted personal interviewing (CAPI). The introduction of the new sample affected the NCVS estimates in areas that were added in 2006, especially nonurban areas. The new sample required hiring and training a large number of new interviewers in the new areas. In addition, based on the experience of the U.S. Census Bureau computer-assisted personal interviewing has been associated with improved, but higher survey estimates. The variation in the amount and rate of crime was too extreme to be attributed to actual year-to-year changes. For areas that were in both the old and new samples--primarily urban and suburban areas--the data for 2006 were consistent with data from previous years. Survey changes had the most impact on estimates for rural areas. Eighty-three percent of rural households were in new sampling areas, compared with 14% of households in urban areas and 15% in suburban areas. Annual nationwide estimates of crime victimization can be generated from NCVS for 2006. Overall U.S. residents age 12 or older experienced an estimated 25 million crimes of violence and theft. The overall violent crime rate was 24.6 victimizations per 1,000 persons age 12 or older; for property crimes it was 159.5 per 1,000 households. Implementation of the methodological changes in the NCVS The NCVS sample was redrawn to update representation of the entire population of the United States based on more recent Census counts. A selected number of households in the sample that were based on the 1990 Decennial Census was replaced with newly selected households based on the 2000 Census. In general, interviews from households in NCVS for the first time produce higher rates of victimization. Typically, these first interviews are not included in the data for analysis but are used as a reference (bounding interview) for subsequent interviews. In 2006 BJS was required to use data from these first-time interviews due to insufficient funding (See forthcoming Technical notes for discussion of bounding interviews). Similar to first-time interviews, automation of data collections also typically produce higher rates of victimization. In July 2006, NCVS replaced paper and pencil interviews (PAPI) with CAPI because the Census Bureau discontinued paper and pencil household surveys. While the conversion to CAPI was expected to produce higher rates of crime, BJS did not have sufficient funds to develop procedures to evaluate the impact of the questionnaire automation and generate statistical parameters to control for the effects. Victimization estimates showed the effects of pre- redesign and post-redesign adjustments in the past When NCVS underwent a redesign in 1992, two comparable samples were conducted. This made it possible to develop an adjustment factor that showed what the victimization estimates would have been if the redesigned survey had been used from 1973 through 1992.***Footnote 2:See Effects of the Redesign on Victimization Estimates (April 1997) at .*** When the adjustment ratio was applied to the data, violent crime rates in 1992 increased from 32.1 to 47.8 per 1,000 persons (figure 1). For property crimes, in 1992 the rates increased from 152.2 to 325.3 per 1,000 households (figure 2). The adjustments in the series between 1973 and 1992 for violent and property crime permitted trend data to be maintained. If it had been possible to conduct two comparable samples in the 2006 redesign, there would have been a similar adjustment factor to make the 2006 data comparable to 2005. While the rates for both violent and property crime increased between 2005 and 2006, it is unknown how much of the increase was caused by methodological changes rather than any real change in crime trends. Estimates for urban and suburban areas in 2006 were comparable to previous years Some areas in the sample were included in both the old and new sample designs. They were principally in urban and suburban locations. Violent and property crime rates in these locations remained unchanged between 2005 and 2006 (table 1). In 2006 U.S. residents age 12 or older residing in continuing urban areas experienced an estimated 8.3 million violent and property crimes. These criminal victimizations included about 2 million violent crimes, 90,000 personal thefts, and 6.3 million property crimes. The rate of violent crime in continuing urban areas, 30 victimizations per 1,000 individuals age 12 or older, was unchanged from 2005. The rate of property crime victimization, 195 victimizations per 1,000 urban households, was also unchanged. In 2006 U.S. residents age 12 or older residing in continuing suburban areas experienced an estimated 7.7 million violent and property crimes. These criminal victimizations included an estimated 1.8 million violent crimes, 48,000 personal thefts, and 5.9 million property crimes. In 2006 the rate of violent crime (19 victimizations per 1,000 individuals age 12 or older) and property crime (133 per 100 households) were unchanged from 2005. U.S. residents age 12 or older experienced an estimated 25 million violent and property crimes in 2006 While national-level estimates of criminal victimizations in 2006 cannot be compared to previous years, the data provide an annual description of the nature of crime in the United States. In 2006 U.S. residents age 12 or older experienced an estimated 25 million violent and property crime victimizations, according to the NCVS (table 2). These criminal victimizations included an estimated 19 million property crimes, 6 million violent crimes, and 174,000 personal thefts. At the national level characteristics of victims remained the same as in previous years The break in the NCVS series shifted the relative magnitude of victimization rates overall, but did not alter the relative proportions of crimes experienced among various demographic groups. In 1993 after the NCVS redesign, which improved the ability to measure crimes, the relative risk of victimization for certain groups remained the same. For instance, males were still more likely to experience victimization than females. In 2006 estimates of characteristics of crime victims and incidents of crime remained consistent with those of previous years. Gender In 2006 males experienced higher rates of victimizations than females. During this time, males experienced 26 violent victimizations per 1,000 males age 12 or older. The rate of violent victimizations for females in 2006 was 23 per 1,000 females age 12 or older (table 3). Age Persons in older age groups generally experienced lower rates of violent victimization than persons in younger age groups. In 2006, households that were headed by persons age 65 or older experienced lower rates of property victimization than households headed by younger persons (table 4). Race Black victims experienced higher rates of violence than whites or persons of other races (table 5). The rate of violent victimization for black individuals was 33 victimizations per 1,000 persons age 12 or older. In 2006 households headed by black individuals were at a greater risk of property victimization than those headed by whites or persons of other races. Victim and offender relationship Of offenders victimizing males in 2006, 5% were described as intimates and 47% as strangers (table 6). In contrast, of offenders victimizing females 21% were described as intimates and 29% as strangers. Males and females were equally likely to be victimized by an offender they previously knew. Presence of weapons In 2006 an estimated 25% of all violent crime incidents were committed by an armed offender (table 7). The presence of a firearm was involved in 9% of these incidents. In 2006 there were 499,890 incidents and 560,300 firearm victimizations (not shown in table). There were 2.3 victimizations per 1,000 persons age 12 or older involving a firearm. An incident is a specific criminal act involving one or more victims and offenders while a victimization is a crime that affects one individual person or household. Reporting to the police During 2006, 49% of all violent victimizations and 38% of all property crimes were reported to the police (table 8). Rape or sexual assault was less likely to be reported to the police than robbery and aggravated assault. Robbery and aggravated assault were equally likely to be reported to the police. Fifty-seven percent of robberies and 59% of aggravated assaults were reported to the police in 2006. As in previous years, motor vehicle theft was the property crime most likely to be reported to the police. About 81% of these victimizations were reported to the police in 2006. Methodology This Bulletin presents data on nonlethal violence and property crimes from the National Crime Victimization Survey (NCVS). Victimization rates are based on data collected during the calendar year. In 2006, about 76,000 households and 135,300 individuals age 12 or older were interviewed for the NCVS. The response rate was 90.9% of eligible households and 86.1% of eligible individuals. See the Technical Notes Appendix for details on methodological changes to the 2006 survey. Standard error computations Comparisons of percentages and rates made in this report were tested to determine if observed differences were statistically significant. Differences described as higher, lower, or different passed a test at the 0.05 level of statistical significance (95% confidence level). Differences described as somewhat, slightly, marginally, or some indication passed a test at the 0.10 level of statistical significance (90% confidence level). Caution is required when comparing estimates not explicitly discussed in this Bulletin. ------------------------------------------------------------ ------------------------------------------------------------ This report in portable document format and in ASCII and its related statistical data are available at the BJS World Wide Web Internet site: . Technical notes to the report are forthcoming. ------------------------------------------------------------ ------------------------------------------------------------ Office of Justice Programs Innovation • Partnerships • Safer Neighborhoods http://www.ojp.usdoj.gov ------------------------------------------------------------ ------------------------------------------------------------ The Bureau of Justice Statistics is the statistical agency of the U.S. Department of Justice. Jeffrey L. Sedgwick is the director. This Bulletin was written by Michael Rand and Shannan Catalano, Ph.D. Cathy Maston verified the report. Patsy Klaus provided statistical review. Tina Dorsey produced and edited the report, and Jayne E. Robinson prepared it for final printing, under the supervision of Doris J. James. December 2007, NCJ 219413 End of File 12/10/07 /JR