U.S. Department of Justice Office of Justice Programs Bureau of Justice Statistics Criminal Victimization, 2010 National Crime Victimization Survey Bulletin Jennifer L. Truman, Ph.D., BJS Statistician ---------------------------------------------------------- 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 on BJS website at: http://www.bjs.gov/index.cfm?ty=pbdetail&iid=2224. 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.bjs.gov/index.cfm?ty=pbse&sid=32. ----------------------------------------------------------- During 2010, U.S. residents age 12 or older experienced an estimated 18.7 million violent and property crime victimizations, down from 20.1 million in 2009 and 24.2 million in 2001, according to the Bureau of Justice Statistics' (BJS) National Crime Victimization Survey (NCVS). These criminal victimizations in 2010 included an estimated 3.8 million violent victimizations, 1.4 million serious violent victimizations, 14.8 million property victimizations, and 138,000 personal thefts. Violent and serious violent victimizations declined by nearly 34% between 2001 and 2010 (figure 1). The NCVS collects information on nonfatal crimes reported and not reported to the police against persons age 12 or older from a nationally representative sample of U.S. households. It produces national rates and levels of personal and property victimization, as well as information on the characteristics of crimes and victims, and the consequences of victimization to victims. Because the NCVS is based on interviews with victims, it cannot measure murder. Information on homicide presented in this report was obtained from the FBI's Uniform Crime Reporting Program (UCR). ----------------------------------------------------------- HIGHLIGHTS *The rate of total violent crime victimizations declined by 13% in 2010, which was about three times the average annual decrease observed from 2001 through 2009 (4%). *The decline in the rate of simple assault accounted for about 82% of the total decrease in the rate of violent victimization in 2010. *In 2010 the property victimization rate declined by 6%, compared to the average annual decrease of 3% observed from 2001 through 2009. *From 2001 to 2010, weapon violence (26% to 22%) and stranger-perpetrated violence (44% to 39%) declined. *Between 2001 and 2010, about 6% to 9% of all violent victimization were committed with firearms. This percentage has remained stable since 2004. *After a slight overall decline from 2001 to 2008, the percentage of victims of violent crimes who suffered an injury during the victimization increased from 24% in 2008 to 29% in 2010. *About 50% of all violent victimizations and nearly 40% of property crimes were reported to the police in 2010. These percentages have remained stable over the past 10 years. *Males (15.7 per 1,000) and females (14.2 per 1,000) had similar rates of violent victimization during 2010. ---------------------------------------------------------- The NCVS collected information from victims of nonfatal violent crimes and property crimes The NCVS measures the violent crimes of rape, sexual assault, robbery, aggravated assault, and simple assault. The NCVS classifies rape, sexual assault, robbery, and aggravated assault as serious violent crimes. Property crimes include household burglary, motor vehicle theft, and theft. The survey also measures personal theft, which included pocket picking and purse snatching. Victimization is the basic unit of analysis used throughout this report. Victimization is a crime as it affects one individual person or household. For personal crimes, the number of victimizations is equal to the number of victims involved. The number of victimizations may be greater than the number of incidents because more than one person may be victimized during an incident. Each crime against a household is assumed to involve a single victim, the affected household. Victimization rate is a measure of the occurrence of victimizations among a specified population group. For personal crimes, this is based on the number of victimizations per 1,000 residents age 12 or older. For household crimes, the victimization rates are calculated using the number of incidents per 1,000 households. Violent and property victimizations declined in 2010 During 2010, the decline in the number of violent and property victimizations was greater than the average rate of decline during the nine years from 2001 through 2009. On average, violent victimizations declined by 3% per year over this period; however, these violent victimizations dropped by 12% during 2010 (table 1). Property crime victimizations slightly declined by 5% during 2010, which was more than two times the average annual rate of decline from 2001 to 2009. The number of violent victimizations declined from 4.3 million to 3.8 million from 2009 to 2010, which was a decline of 12%. Simple assault, which accounted for 63% of all violent victimizations, declined by 15%. This decline in simple assault accounted for 83% of the total decrease in violent victimizations. No measurable change occurred in the number of serious violent victimizations from 2009 to 2010. The number of property victimizations slightly declined by 5% between 2009 and 2010 from 15.6 million to 14.8 million victimizations. Similar to the number of violent victimizations, the violent crime victimization rate the number of violent criminal victimizations per 1,000 persons age 12 and older declined from 17.1 to 14.9 victimizations per 1,000 persons between 2009 and 2010, which was a 13% decline (table 2). This decline was more than the average annual 4% decline of the violent victimization rates since 2001. No measurable change occurred in the overall victimization rate for serious violent crimes between 2009 and 2010. The overall property crime victimization rate also declined between 2009 and 2010 from 127.4 to 120.2 victimizations per 1,000 households, which was a 6% decline compared to the average annual decline of 3% since 2001. Between 2001 and 2010, rates of all major violent and property victimizations measured by the NCVS declined. During the 10-year period, the overall violent victimization rate decreased by 40.5%, and the rate of serious violent victimization declined by 40.6%. The rate of overall property victimization fell by 28% from 2001 to 2010. Violent victimization rates fell to their lowest levels since 1993 The double-digit percentage decline in the violent crime victimization rate in 2010 continued a longer-term trend. Since 1993, the violent crime victimization rate declined steadily from 49.9 per 1,000 persons age 12 or older in 1993 to 14.9 per 1,000 in 2010, a decline of 70% (figure 2). Most of this decline occurred between 1993 and 2001, when the violent crime rate declined by half to reach 25.1 in 2001. The serious violent crime victimization rate followed a similar pattern of decline as the violent crime victimization rate. It declined by 73% since 1993, from 20.5 per 1,000 persons age 12 or older to 5.4 per 1,000. The serious violent crime victimization rate declined by more than half between 1993 and 2000, reaching 10.1 per 1,000 persons age 12 or older in 2000. It declined by almost half again from 2000 to 2010, reaching 5.4 per 1,000 persons age 12 or older. ******************************************************** Series victimization Among ongoing research efforts associated with its redesign of the NCVS, BJS is investigating ways to include high volume repeat victimizations in the total estimates of criminal victimization. The NCVS terms these high volume repeat victimizations series victimizations. The inclusion of series victimizations is important to obtain a more accurate estimate of victimization. Series victimizations may also involve certain types of victimizations, such as intimate partner abuse or repeated attacks on adolescents at school. ***Footnote 1 Planty, M., & Strom, K.J. (2007). Understanding the role of repeat victims in the production of annual US victimization rates. Journal of Quantitative Criminology.*** The NCVS measures victimizations that are similar in type but occur with such frequency that a victim is unable to recall each individual event or to describe each event in detail. Survey procedures allow NCVS interviewers to identify and classify these similar victimizations as series victimizations. The NCVS uses three questions to determine if victimizations qualify as series victimizations: (1) Did the incident occur six or more times in the past six months? (2) Are the incidents similar to each other in detail? (3) Is the respondent unable to recall enough detail of each incident to distinguish one from another? When all three conditions are met, the NCVS interviewer records the number of victimizations and collects detailed information on the last occurrence in the series. For various reasons, BJS has historically excluded series victimizations from its counts and rates of criminal victimization in prior Criminal Victimization bulletins. This is primarily because victims are unable to provide details for each event, and information is collected only on the last incident in the series. Basing estimates solely on the last incident may lead to overgeneralizing the characteristics of the last victimization to all victimizations. Victims who experience a large number of incidents may be unable to provide reliable counts of the number of times these victimizations occurred. Without such details it is difficult to count and classify victimizations for purposes of estimating national victimization rates. BJS has examined alternative methods for including series victimizations in its annual counts and rates of victimizations with the aim of implementing methods that produce reliable estimates of crime levels and changes in these levels. BJS analyzed various alternatives, including the use of the victim's estimate of the number of times the incident occurred, and the use of the victim's estimate with a cap on the maximum number of incidents to minimize the effects of extreme outliers on the rates. The findings from these analyses resulted in the decision to count series incidents as the number reported by the victim, but to cap that number at 10.***Footnote 2 BJS research findings underlying this decision will be made available in a forthcoming report on series victimization estimates.*** For the majority of series incidents, victims report that the incidents occurred 10 or fewer times. Research also indicates that the fact that the respondent is unable to separate each event suggests that these events are in fact very similar and over generalization may not be a problem. Further, many respondents estimate the number of incidents that occurred using common measurements of time, such as once a month (6 times in the 6-month period) or once a week (24 times in the 6-month period). Impact of series victimization When series incidents are counted as the victim's estimate with a cap of 10, the national estimates of victimization increase, as expected. When series incidents are excluded from the violent crime victimization rate, the rate ranges from 23% to 37% lower than the rate obtained when series incidents are included. This is consistent with research conducted by BJS and others that has shown that national victimization estimates can be highly sensitive to victims' estimates of the number of times these events occurred. ***Footnote 3 See Series victimization: Report of a field test, NCJ 104615, BJS web, April 1987; Rand, M., & Saltzman, L.E. (2003). The nature and extent of recurring intimate partner violence in the United States. Journal of Comparative Family Studies; and Planty, M., & Strom, K.J. (2007). Understanding the role of repeat victims in the production of annual US victimization rates.Journal of Quantitative Criminology.*** However, the general trends in the violent victimization rate are not affected by the introduction of series victimizations in these estimates. Both show a similar pattern of decline over the period from 1993 to 2010 (figure 3). When violent victimization rates excluded series incidents, the decline from 1993 to 2010 was 70%; when series incidents were included in the rates, the decline was 76%. Similarly, both rates declined by about 40% from 2001 to 2010. The violent victimization rate declined by 13% between 2009 and 2010 with series victimizations excluded and declined by 14% with series victimizations included. The two violent crime victimization rates converged because a decrease in the number of series incidents occurred in the U.S. In 1993, series incidents (when counted as one victimization) accounted for almost 7 percent of all violent crime victimizations, and by 2010 series incidents accounted for about 3% of all violent victimizations. Using the counting rule when the series incidents were counted as the victim estimate with a cap of 10, series accounted for almost 37% of all violent victimization in 1993 and 23% in 2010. ********************************************************** ********************************************************* Questions for series victimization Altogether, how many times did this type of incident happen during the last 6 months? ___ Number of incidents How many incidents? __1-5 incidents (not a "series") __6 or more incidents Are these incidents similar to each other in detail or are they different types of crimes? __Similar __Different (not a "series") Can you recall enough detail of each incident to distinguish them from each other? __Yes (not a "series") __No (is a "series") *********************************************************** *********************************************************** Both the NCVS and the preliminary UCR reported a decline in crime from 2009 to 2010 The 2010 annual decline in violent and property victimizations in the NCVS were consistent in direction with preliminary findings from the FBI's Uniform Crime Reporting Program (UCR) (table 3). Because the NCVS and UCR measure an overlapping, but not identical, set of offenses and use different methodologies, congruity between the estimates is not expected. Throughout the 39-year history of the NCVS, both programs have generally demonstrated similar year-to-year increases or decreases in the levels of violent and property crimes. Violent crime as measured by the FBI's UCR includes murder and non-negligent manslaughter, forcible rape, robbery, and aggravated assault. Property crimes include burglary, larceny-theft, and motor vehicle theft. The UCR measures crimes known to the police occurring to both persons and businesses. The FBI obtains data on the crimes from law enforcement agencies, while the NCVS collects data from victims. ***Footnote 4 See The Nation's Two Crime Measures, NCJ 122705, available online at http://bjs.ojp.usdoj.gov/content/pub/pdf/ntcm.pdf, October 2004.*** There are significant differences between the NCVS and UCR. The NCVS obtains estimates of crimes both reported and not reported to the police. The UCR collects data on crimes only known to the police. The UCR includes homicide, arson, commercial crimes, and crimes against children under age 12; the NCVS excludes these crime types. The UCR excludes simple assaults and sexual assaults. Simple assaults include attacks or attempted attacks without a weapon resulting in either no injury or minor injury. Sexual assaults include attacks or attempted attacks generally involving unwanted sexual contact between the victim and offender that may or may not involve force. Sexual assaults are commonly combined with rape estimates in the NCVS. While the UCR and the NCVS define rape similarly, the UCR measures the crime against women only, and the NCVS measures it against both men and women. The NCVS data are estimates from a nationally representative sample of U.S. households, and the UCR data are based on the actual counts of offenses reported by law enforcement jurisdictions. The NCVS excludes persons in institutions (e.g., nursing homes, etc.) and may exclude highly mobile populations and the homeless; however, victimizations against these persons may be included in the UCR. Given these differences, the two measures of crime should be considered to complement each other and provide a more comprehensive picture of crime in the United States. According to preliminary results released by the FBI, between 2009 and 2010 the number of violent crimes known to the police as measured by the UCR declined by about 6%, and the number of property crimes declined by about 3%. Between 2009 and 2010 the number of violent crimes in the NCVS declined by 12% and the number of property crimes declined slightly by 5%. Both the UCR and the NCVS reported declines in the numbers of violent crimes and property crimes. The UCR reported declines in the numbers of all other crimes measured. The change in the number of crimes reported to the police in the NCVS from 2009 to 2010 was not statistically significant. ******************************************************** Property victimization fell to the lowest levels since 1993 As with violent victimization rates, the property crime victimization rate also declined over the longer term. Property crime victimization rates were calculated based on the number of households that were victimized; the rate was calculated as the number of property crime victimizations per 1,000 households in the United States. The property crime victimization rate declined 50% from 318.9 per 1,000 households in 1993 to 159.0 per 1,000 households in 2002. It declined further to 120.2 per 1,000 households in 2010 (figure 4). Severity and nature of violent victimization With the reported declines in violent and serious violent victimization during the current decade, the nature and severity of violence changed. The prevalence of injury in violence increased in recent years to previous levels; weapon use in violent victimizations and violent victimizations perpetrated by strangers declined slightly. Reporting to the police remained stable, with about half of all violent victimizations reported to the police. The prevalence of injury in violence increased in 2010 to previous levels In 2010, 29% of all victims of violence suffered an injury. Of those victims of violence who were injured, 5% were seriously injured, and 23% suffered minor injuries (not shown in table). About 41% of all victims of serious violence suffered an injury from their victimization in 2010. Of the victims of serious violence who were injured, 15% were seriously injured, and 23% suffered minor injuries. From 2001 to 2006, the percentage of victims experiencing violent victimization who suffered an injury from their victimization was relatively stable at about 28% (figure 5). In 2008, the percentage of victims of violence who were injured dropped to 24%. The percentage has since increased to 28% in 2009 and 29% in 2010. Weapon use in violent victimization declined slightly between 2001 and 2010 For overall violent victimization, weapons were used in 22% of all violent victimizations and 61% of serious violent victimizations in 2010. Weapon use varied by type of crime. In 2010, 12% of rape and sexual assaults and 20% of all assaults involved a weapon (table 4). Firearms were used in violent victimizations more often than knives. Robbery (44%) was the most likely offense to involve an armed offender. Firearms were the most commonly used weapon in robberies (29%). During the past decade, the pattern of weapon use in violent victimization changed slightly. The percentage of violent victimizations involving weapons declined slightly from 26% in 2001 to 22% in 2010 (figure 6). During the 10-year period, about 6% to 9% of all violent victimizations were committed with firearms (figure 7). The percent of violent victimizations involving firearms has remained generally stable from 2004 to 2010. Violent victimizations perpetrated by strangers declined from 2001 to 2010 Strangers were offenders in about 39% of all violent victimizations during 2010, a percentage that has declined from 44% in 2001 (figure 8). From 2001 to 2010, close to half of all victims of violence knew their offenders. During the 10-year period, the relationship of the offender to the victim was unknown for an average of 9% of all violent victimizations. In 2010, the percentage of violence perpetrated by strangers and nonstrangers varied by the victim's sex. Females knew their offenders in 64% of violent victimizations committed against them, and males knew their offenders in 40% of violent victimizations against them (table 5). Females were more likely to be victimized by someone they knew (a nonstranger) than by a stranger for all measured violent crimes except robbery. The percentages of overall violence, robbery, or simple assaults committed by strangers were higher for males than for females. Offenders known to both male and female victims were most often identified as friends or acquaintances. For overall violent victimization, robbery, and assault, males and females were equally likely to have been victimized by an acquaintance. Trends in violence perpetrated by strangers and nonstrangers from 2001 to 2010 were also slightly different for females and males (not shown in figure). The percentage of females who were victimized by a nonstranger remained relatively stable near 60% each year from 2001 to 2010. The percentage of males who were victimized by a nonstranger averaged about 39% from 2001 to 2010. The percentage of males who were victimized by a stranger declined from 55% to 48% over the 10-year period (not shown in figure). For females, the percentage of stranger-perpetrated violence remained relatively stable, except for a decline from 2005 to 2008. While these percentages remained stable for females, males experienced a decrease in stranger-perpetrated violence. This may be why the trends in stranger-perpetrated and onstranger-perpetrated violence converged in 2005. The percentage of female victims (22%) of intimate partner violence was about 4 times that of male victims (5%). The NCVS defines intimate partners as current or former spouses, boyfriends, or girlfriends. The rate of intimate partner violence for females decreased from 2009 to 2010. In comparison, there were no significant differences in the numbers and rates of intimate partner victimizations for males from 2009 to 2010 (table 6). The percentage of violent victimizations reported to the police remained nearly stable from 2001 to 2010 Reporting to the police indicates whether or not the police were notified about the victimization. The victim, other third parties (including witnesses, other victims, household members, or other officials, such as school officials), or police already at the scene may report the incident. Police notification may occur during or immediately following a criminal incident or days or even weeks later. During 2010, a greater percentage of violent victimizations (51%) than property victimizations (39%) were reported to police (table 7). More than half of all serious violent victimizations (58%) were reported to the police, compared to 47% of simple assaults. The percentage of violent and serious violent victimizations reported to the police was generally stable from 2001 to 2010 (figure 9). No significant difference was found between the percentage of violent victimizations (49% in 2001 and 51% in 2010) and serious violent victimizations (57% in 2001 and 58% in 2010). In 2010, the percentage of violent victimizations against females (53%) and males (49%) reported to the police were similar (table 8). The percentage of violent victimizations reported to police against white non-Hispanic (50%), black non-Hispanic (48%), and Hispanic (53%) males were similar. For females, the percentage of violent victimizations reported to the police against white non-Hispanics (52.4%), black non-Hispanics (55.4%), Hispanics (62.5%) were also similar. Male and female victimization rates converged in 2010 In 2010, for the first time since the NCVS began reporting on differences in victimizations by sex, males (15.7 per 1,000 males age 12 or older) and females (14.2 per 1,000) had similar rates of violent victimization. This indicates a continuing convergence of male and female victimization (table 9). Historically, males have had higher rates of violent victimization compared to females. For example, in 1994 the rate of violent victimization for males was 59.6 per 1,000 and 42.5 per 1,000 for females.***Footnote 5 See Criminal Victimization 1994, NCJ 158022, BJS Web, April 1996.*** For simple assault, no detectable statistical differences were noted between male (9.7 per 1,000) and female (9.2 per 1,000) rates during 2010. During the past decade male and female simple assault rates have been similar three times: 2001, 2007, and 2009 (data not shown). Consistent with previous years, the robbery victimization rate was higher for males (2.4 per 1,000 males age 12 or older) than for females (1.4 per 1,000). Aggravated assault rates were also higher for males (3.4 per 1,000) than for females (2.3 per 1,000). Females (1.3 per 1,000) were more likely than males (0.1 per 1,000) to be victims of rape or sexual assault. Persons of two or more races had higher rates of violent victimization than white non-Hispanics, black non-Hispanics, Hispanics, and Asians or Pacific Islanders In 2010, the overall violent victimization and aggravated assault rates for black non-Hispanics (20.8 per 1,000 age 12 or older) were higher than for white non-Hispanics (13.6 per 1,000) and for Hispanics (15.6 per 1,000). Asians and Pacific Islanders had the lowest rates of overall violent victimization (6.3 per 1,000). Persons of two or more races (52.6 per 1,000) were victims of overall violent victimization at higher rates than persons of any other racial or ethnic category, except American Indians and Alaskan Natives. American Indians and Alaskan Natives (42.2 per 1,000) had higher rates of violent victimization than white non-Hispanics (13.6 per 1,000), Hispanics (15.6 per 1,000), Asian and Pacific Islander (6.3 per 1,000), and slightly higher rates than black non-Hispanics (20.8 per 1,000). Persons ages 25 or older generally experienced lower violent victimization when compared to younger persons Generally, persons ages 25 or older had lower violent victimization rates than younger persons. Persons ages 18 to 20 had higher robbery rates (5.9 per 1,000) than persons ages 12 to 14 (0.7 per 1,000) and ages 25 or older (from 2.5 to 0.6 per 1,000), and slightly higher rates than persons ages 15 to 17 (2.7 per 1,000). Lower income households and larger households experienced higher property crime Lower income households were more likely than higher income households to experience property crime. In general, lower income households had higher rates of overall property crime and household burglary, compared to higher income households (table 10). Households in the lowest income category less than $7,500 per year had a higher overall property victimization rate (168.7 per 1,000 households), compared to households earning $75,000 or more (119.3 per 1,000). Households in the lowest income category were victims of burglary at a rate (44.4 per 1,000) that was more than two times higher than the rate for households earning $75,000 per year or more (20.8 per 1,000). Households whose income was unknown (due to missing data or refusal to provide the household income) had lower rates of overall property victimization (98.2 per 1,000) and property theft (74.8 per 1,000) compared to other households.***Footnote 6 Income was not ascertained for 32% of all households.*** Consistent with previous years of the NCVS, property crime rates were higher for larger households than for smaller households in 2010. Overall, property crime rates were greater for larger households compared to smaller households. For property theft, patterns across households of different sizes were similar to patterns of overall property crime. Households with six or more persons experienced more overall property crime and property theft, and slightly more household burglary compared to smaller households. Methodology The National Crime Victimization Survey (NCVS) is an annual data collection conducted by the U.S. Census Bureau for the Bureau of Justice Statistics (BJS). The NCVS collects information on nonfatal victimizations, reported and not reported to the police, against persons age 12 or older from a nationally representative sample of U.S. households. Violent crimes measured by the NCVS include rape or sexual assault, robbery, aggravated assault, and simple assault. Property crimes include household burglary, motor vehicle theft, and theft. Victimizations that occurred outside of the U.S. are excluded from this report. The survey results presented in this report are based on data gathered from residents living throughout the United States, including persons living in group quarters, such as dormitories, rooming houses, and religious group dwellings. Armed Forces personnel living in military barracks and institutionalized persons, such as correctional facility inmates, were not included in the scope of this survey. Each housing unit selected for the National Crime Victimization Survey (NCVS) remains in the sample for 3 years, with each of seven interviews taking place at 6-month intervals. An NCVS field representative's first contact with a household selected for the survey is in person. The field representative may conduct subsequent interviews by telephone. To elicit more accurate reporting of incidents, the NCVS uses a self-respondent method that requires a direct interview with each person 12 years or older in the household except under certain specific conditions. Proxy interviews accounted for about 4% of all NCVS interviews in 2010. Annual collection year estimates of the levels and rates of victimization are derived by accumulating estimates quarterly. The weights of all crimes reported during the interviews in that year are summed, regardless of when the crime occurred. The base for the collection year rate for personal crimes is the sum of all person weights. The base for the property crime rates is the sum of all household weights. For more detail, see the Methodology in Criminal Victimization in the United States, Statistical Tables, BJS Web, May 2011. In 2010, 40,974 households and 73,283 individuals age 12 and older were interviewed for the NCVS. Each household was interviewed twice during the year. The response rate was 92.3% of households and 87.5% of eligible individuals. Methodological changes to the NCVS in 2006 As discussed in the previous editions in this bulletin series, Criminal Victimization, 2006 and Criminal Victimization, 2007, methodological changes implemented in 2006 impacted the estimates for that year to an extent that the estimates were not considered comparable to those of previous years. Evaluation of 2007 and later data from the NCVS conducted by BJS and the Census Bureau have found a high degree of confidence that estimates for these years are consistent with and comparable to those for 2005 and previous years. Standard error computations Any time national estimates are derived from a sample rather than the entire population, as is the case with the NCVS, it is important to be cautious when drawing conclusions about the size of one population estimate in comparison to another or about whether a time series of population estimates is changing. Although one estimate may be larger than another, estimates based on responses from a sample of the population each have some degree of sampling error. The sampling error of an estimate depends on several factors, including the amount of variation in the responses, the size and representativeness of the sample, and the size of the subgroup for which the estimate is computed. One measure of the sampling error associated with an estimate is the standard error. The standard error can vary from one estimate to the next. In general, an estimate with a smaller standard error provides a more reliable approximation of the true value than an estimate with a higher standard error. Estimates with relatively large standard errors are associated with less precision and reliability and should be interpreted with caution. The relative standard error (RSE) is a measure of an estimate's reliability. The RSE is the ratio of the standard error to the estimate. In this report, the RSE was calculated for all estimates, and in cases where the RSE was greater than 50% or when the estimate was based on 10 or fewer sample cases, the estimate was noted with a "!" symbol. ("! Interpret with caution; estimate based on 10 or fewer sample cases, or coefficient of variation is greater than 50%.") A statistical test is used to determine whether differences in means or percentages are statistically significant once sampling error is taken into account. Comparisons made in the text were tested for statistical significance at the p < .05 level to ensure that the differences were larger than might be expected due to sampling variation. Significance testing calculations were conducted at BJS using statistical programs developed specifically for the NCVS by the U.S. Census Bureau. These programs take into consideration many aspects of the complex NCVS sample design when calculating estimates. Standard errors for average annual estimates were calculated based on the ratio of the sums of victimizations and respondents across years. Many of the variables examined in this report may be related to one another and to other variables not included in the analyses. Complex relationships among variables were not fully explored in this report and warrant more extensive analysis. Readers are cautioned not to draw causal inferences based on the results presented. Statistical differences defined BJS tested the comparisons between the percentages and rates for Criminal Victimization, 2010 to determine if observed differences were statistically significant. Differences described as higher, lower, or different passed a test at the .05 level of statistical significance (95%-confidence level). Differences described as somewhat, slightly, or marginally different, or some indication of difference, passed a test at the .10 level of statistical significance (90%-confidence level). Caution is required when comparing estimates not explicitly discussed in this bulletin. Average annual rate of change The average annual rate of change (r) was calculated as where Pt = number or rate in the current year Pt-n = number or rate in the nth prior year n = number of years Change in the rape or sexual assault rate for 2009 to 2010 While the change in the rape or sexual assault rate from 2009 to 2010 is significantly different at the 90%-confidence level, care should be taken in interpreting this change because the estimates of rape/sexual assault are based on a small number of cases reported to the survey. Therefore, small absolute changes and fluctuations in the rates of victimization can result in large year-to-year percentage change estimates. For 2010, the estimate of rape or sexual assault is based on 57 unweighted cases compared to 36 unweighted cases in 2009. The measurement of rape or sexual assault represents one of the most serious challenges in the field of victimization research. Rape and sexual assault remain sensitive subjects that are difficult to ask about in the survey context. As part of the ongoing redesign of the NCVS, BJS is exploring methods for improving the reporting of these crimes. ------------------------------------------------------------------------------------------------------ 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. James P. Lynch is the director. This bulletin was written by Jennifer L. Truman. Lynn Langton provided statistical review and verification of the report. Vanessa Curto and Jill Thomas edited the report, Barbara Quinn and Morgan Young produced the report, and Jayne E. Robinson prepared the report for final printing under the supervision of Doris J. James. September 2011, NCJ 235508 This report in portable document format and in ASCII and its related statistical data and tables are available on the BJS website at: http://www.bjs.gov/index.cfm?ty=pbdetail&iid=2224. ------------------------------------------------------------------------------------- September 6, 2011 /JER/ 4:30pm