U.S. Department of Justice Office of Justice Programs Bureau of Justice Statistics ------------------------------------------------------ This file is text only without graphics and many of the tables. A Zip archive of the tables in this report inspreadsheet format (.csv) and the full report includingtables and graphics in .pdf format are available on BJS website at http://www.bjs.gov/index.cfm?ty=pbdetail&iid=5844 This reports is one in series. More recent editions may be available. To view a list of all reports in the series go to http://www.bjs.gov/index.cfm?ty=pbse&sid=65 ------------------------------------------------------ Crime Against Persons with Disabilities, 2009–2014 - Statistical Tables Erika Harrell, Ph.D., BJS Statistician The rate of violent victimization against persons with disabilities (31.7 victimizations per 1,000 persons age 12 or older) was 2.5 times higher than the age-adjusted rate for persons without disabilities (12.5 per 1,000) in 2014 (figure 1). In every other year examined, the rate of violent victimization against persons with disabilities was at least twice the age- adjusted rate for persons without disabilities. For both persons with and without disabilities, the rate of violent victimization increased from 2011 to 2012 and remained steady through 2014. This report details the rates of nonfatal violent victimization against persons with and without disabilities, describes the types of disabilities, and compares victim characteristics. Nonfatal violent crimes include rape or sexual assault, robbery, aggravated assault, and simple assault. The findings are based on the Bureau of Justice Statistics’ (BJS) National Crime Victimization Survey (NCVS), a household survey that collects data on U.S. residents age 12 or older (excluding those living in institutions). The NCVS adopted survey questions from the U.S. Census Bureau’s American Community Survey (ACS) to identify crime victims with disabilities. The NCVS defines disability as the product of interactions among individuals’ bodies; their physical, emotional, and mental health; and the physical and social environment in which they live, work, or play. A disability exists where this interaction results in limitations of activities and restrictions to full participation at school, at work, at home, or in the community. Disabilities are classified according to six limitations: hearing, vision, cognitive, ambulatory, self-care, and independent living. Data from the ACS were used to estimate age-adjusted victimization rates for persons without disabilities. Unless noted, all rates for persons without disabilities are age-adjusted. Victimization rates were generated by using the ACS population estimates for persons with disabilities. See appendix table 18. The Methodology further details data sources, computational procedures, and data limitations. ***************** List of tables ***************** Table 1. Rate of violent victimization and average annual number of persons, by victim's disability status and age, 2010–2014 Table 2. Rate of violent victimization against persons with and without disabilities, by type of crime, 2010–2014 Table 3. Rate of violent victimization against persons with and without disabilities, by victim characteristics, 2010–2014 Table 4. Rate of violent victimization against persons with disabilities, by disability type and type of crime, 2010–2014 Table 5. Rate of violent victimization against persons with disabilities, by disability type and sex, 2010–2014 Table 6. Percent of violent crime against persons with disabilities, by type of crime and number of disability types, 2010–2014 Table 7. Rate of violent victimization, by number of disability types and type of crime, 2010–2014 Table 8. Victim-offender relationship, by victim's disability status, 2010–2014 Table 9. Time violent crime occurred, by victim's disability status, 2010–2014 Table 10. Percent of violent crime reported to police, by victim’s disability status and disability type, 2010–2014 Table 11. Person who notified police of violent crime, by victim's disability status, 2010–2014 Table 12. Reasons for not reporting violent crime to police, by victim's disability status, 2010–2014 Table 13. Percent of violent victimizations in which assistance from a nonpolice victim services agency was received, by victim's disability status, 2010–2014 ************************* List of appendix tables ************************* Appendix table 1. Rates and standard errors for figure 1: Rate of violent victimization, by disability status, 2009–2014 Appendix table 2. Standard errors for table 1: Rate of violent victimization and average annual number of persons, by victim's disability status and age, 2010–2014 Appendix table 3. Standard errors for table 2: Rate of violent victimization against persons with and without disabilities, by type of crime, 2010–2014 Appendix table 4. Standard errors for table 3: Rate of violent victimization against persons with and without disabilities, by victim characteristics, 2010–2014 Appendix table 5. Standard errors for table 4: Rate of violent victimization against persons with disabilities, by disability type and type of crime, 2010–2014 Appendix table 6. Standard errors for table 5: Rate of violent victimization against persons with disabilities, by disability type and sex, 2010–2014 Appendix table 7. Standard errors for table 6: Percent of violent crime against persons with disabilities, by type of crime and number of disability types, 2010–2014 Appendix table 8. Standard errors for table 7: Rate of violent victimization, by number of disability types and type of crime, 2010–2014 Appendix table 9. Standard errors for table 8: Victim-offender relationship, by victim's disability status, 2010–2014 Appendix table 10. Standard errors for table 9: Time violent crime occurred, by victim's disability status, 2010–2014 Appendix table 11. Standard errors for table 10: Percent of violent crime reported to police, by victim’s disability status and disability type, 2010–2014 Appendix table 12. Standard errors for table 11: Person who notified police of violent crime, by victim's disability status, 2010–2014 Appendix table 13. Standard errors for table 12: Reasons for not reporting violent crime to police, by victim's disability status, 2010–2014 Appendix table 14. Standard errors for table 13: Percent of violent victimizations in which assistance from a nonpolice victim services agency was received, by victim's disability status, 2010–2014 Appendix table 15. Unadjusted rates and standard errors of violent victimization against persons without disabilities, 2009– 2014 Appendix table 16. Unadjusted rates and standard errors for violent victimization against persons without disabilities, by type of crime, 2010–2014 Appendix table 17. Unadjusted rates and standard errors for violent victimization against persons without disabilities, by victim characteristics, 2010–2014 Appendix table 18. U.S. population, according to the U.S. Census Bureau's American Community Survey Public Use Microdata Sample data, by disability status and demographic characteristics, 2010– 2014 ******************************** Violent crime by victim’s age and disability status ******************************* * In 2010-14, for each age group measured except persons age 65 or older, the rate of violent victimization against persons with disabilities was at least double the rate for those without disabilities (table 1). Among persons age 65 or older, there was no statistically significant difference between the rates of violent victimization by disability status. * Among those with disabilities, persons ages 12 to 15 had a higher rate of violent victimization than all other age groups, except persons ages 16 to 19. There was no statistically significant difference between the rates of violent victimization against persons with disabilities ages 12 to 15 and ages 16 to 19. ********************************************************* ****************************************** Disability population in the United States ****************************************** From 2010 to 2014, about 14% of the U.S. population age 12 or older living outside of institutions had a disability, according to the American Community Survey (ACS). Characteristics of the populations with and without disabilities are compared in appendix table 18. In 2010-14, among noninstitutionalized persons with disabilities, 47% were male and 53% were female. Whites accounted for about 70% of the population with disabilities, blacks accounted for 14%, and persons of two or more races accounted for 2%. An estimated 11% were Hispanic. About 42% of the population with disabilities was age 65 or older, compared to about 12% of the population without disabilities. The 2010-14 ACS population estimates of persons by disability status were generated from Public Use Microdata Sample (PUMS) data. ******************************************* Crime Victims with Disabilities Awareness Act (Public Law 105-301), 1998 ******************************************* The Crime Victims with Disabilities Awareness Act mandates that the National Crime Victimization Survey (NCVS) include statistics on crimes against people with disabilities and the characteristics of these victims. The act was designed “to increase public awareness of the plight of victims of crime with developmental disabilities, to collect data to measure the magnitude of the problem, and to develop strategies to address the safety and justice needs of victims of crime with developmental disabilities.” Section 5 of the act directed the Department of Justice to include statistics relating to “the nature of crimes against people with developmental disabilities; and the specific characteristics of the victims of those crimes” in the NCVS. This report is a part of the Bureau of Justice Statistics’ (BJS) series on crime against people with disabilities. More information can be found on the BJS website. ******************************* The use of age-adjusted rates ******************************* The differences in age distributions between the persons with and without disabilities must be taken into account when making direct comparisons of the violent victimization rate between the two populations. The age distribution of persons with disabilities differs considerably from that of persons without disabilities, and violent crime victimization rates vary significantly with age. According to the U.S. Census Bureau’s American Community Survey, persons with disabilities are generally older than persons without disabilities. For example, in 2010-14, about 42% of persons with disabilities were age 65 or older, compared to 12% of persons without disabilities (appendix table 18). The age adjustment standardizes the rate of violence against persons without disabilities to show what the rate would be if persons without disabilities had the same age distribution as persons with disabilities. ********************************************************* ******************************** Violent crime by type of crime ******************************** * The rate of violent victimization against persons with disabilities (30.7 per 1,000) was more than twice the rate for persons without disabilities (12.8 per 1,000) in 2010-14 (table 2). * The rate of serious violent crime (rape or sexual assault, robbery, and aggravated assault) for persons with disabilities (12.7 per 1,000) was more than three times the rate for persons without disabilities (3.9 per 1,000). * The rate of simple assault against persons with disabilities (18.0 per 1,000) was more than twice the rate for persons without disabilities (8.8 per 1,000). * Serious violent crime accounted for a greater percentage of violence against persons with disabilities (41%) than violence against persons without disabilities (31%) (not shown). * One in 5 violent crime victims with disabilities believed they were targeted due to their disability (not shown). ************************************ Violent crime by sex and race and Hispanic origin ************************************ Sex *** * For both males and females in 2010-14, the rate of violent victimization was higher for persons with disabilities than for those without disabilities (table 3). * The rate of violent victimization against males with disabilities was 31.2 per 1,000, compared to 14.8 per 1,000 for males without disabilities. * For females with disabilities, the rate of violent victimization was 30.3 per 1,000, compared to 11.0 per 1,000 females without disabilities. * Among persons with disabilities, no statistically significant difference by sex was found in the rate of violent victimization. However, among those without disabilities, males (14.8 per 1,000) had a higher rate than females (11.0 per 1,000). Race and Hispanic origin ************************** * For each racial and ethnic group measured, persons with disabilities had higher violent victimization rates than persons without disabilities in 2010-14. * Among the racial groups examined, persons of two or more races had the highest rates of violent victimization among persons with disabilities (101.4 per 1,000) and without disabilities (30.4 per 1,000). * There was no statistically significant difference between the victimization rates of whites (29.7 per 1,000), blacks (28.8 per 1,000), Hispanics (28.6 per 1,000), and persons of other races (28.0 per 1,000) with disabilities. * Among persons without disabilities, blacks (18.8 per 1,000) had a higher age-adjusted rate of violent victimization than whites (12.1 per 1,000), Hispanics (13.0 per 1,000), and persons of other races (7.1 per 1,000). ********************* Types of disability ********************* * In 2010-14, persons with cognitive disabilities had the highest rates of total violent crime (56.6 per 1,000), serious violent crime (24.0 per 1,000), and simple assault (32.6 per 1,000) among the disability types measured (table 4). * Persons with hearing disabilities (15.5 per 1,000) had the lowest rates of total violent victimization among the disability types examined. * Persons with vision, ambulatory, self-care, and independent living disabilities had similar rates of serious violent crime and simple assault. * Among both males (55.1 per 1,000) and females (58.0 per 1,000), those with cognitive disabilities had the highest rate of total violent victimization among the disability types measured (table 5). * Males and females had similar rates of total violent victimization in every disability type measured except vision disabilities. * Among those with vision disabilities, males (22.8 per 1,000) had a lower rate of total violent victimization than females (31.9 per 1,000). *************************************************************** ************************************** Disability types used in this report ************************************* * Hearing limitation entails deafness or serious difficulty hearing. * Vision limitation is blindness or serious difficulty seeing, even when wearing glasses. * Cognitive limitation includes serious difficulty in concentrating, remembering, or making decisions because of a physical, mental, or emotional condition. * Ambulatory limitation is difficulty walking or climbing stairs. * Self-care limitation is a condition that causes difficulty dressing or bathing. * Independent living limitation is a physical, mental, or emotional condition that impedes doing errands alone, such as visiting a doctor or shopping. *************************************************************** ******************************************** Violent crime by number of disability types ********************************************* * Fifty-three percent of violence against persons with disabilities occurred against those with multiple disability types (table 6). * An estimated 69% of rapes or sexual assaults against persons with disabilities were committed against those with multiple disability types, the highest percentage among the crime types examined. * There was no statistically significant difference between the rates of total violent victimization against persons with a single disability type (28.6 per 1,000) and persons with multiple disability types (32.8 per 1,000) (table 7). * The rate of serious violence against persons with a single disability type (11.1 per 1,000) was lower than the rate for persons with multiple disability types (14.4 per 1,000). * Persons with a single disability type (1.1 per 1,000) had a lower rate of rape or sexual assault than those with multiple disability types (2.4 per 1,000). * Rates of robbery, aggravated assault, and simple assault did not differ significantly by the number of disability types. ****************************** Victim-offender relationship ****************************** * A higher percentage of violence against persons with disabilities (40%) was committed by persons the victim knew well or who were casual acquaintances than against persons without disabilities (32%) (table 8). * A lower percentage of total violence against persons with disabilities (30%) was committed by strangers than against persons without disabilities (39%) in 2010-14. * There was no statistically significant difference in the percentage of total violence committed by intimate partners for victims with (14%) and without disabilities (13%). * Other relatives (including parents, children, and other relatives) accounted for a higher percentage of total violence against persons with disabilities (11%) than persons without disabilities (7%). *************** Time of crime *************** * For 2010–14, the rates of violent victimization against persons with disabilities that occurred in the daytime (after 6 a.m. to 6 p.m.) and nighttime (after 6 p.m. to 6 a.m.) were higher than those found for persons without disabilities (not shown). * For violent crime victims with and without disabilities in 2010-14, a higher percentage of the total violence occurred during the daytime than during the nighttime (table 9). * Persons with disabilities (59%) experienced a higher percentage of total violence during the daytime than persons without disabilities (53%). * Persons with disabilities (36%) experienced a lower percentage of nighttime total violence than persons without disabilities (43%). ******************* Police reporting ******************* * There was no statistically significant difference in the percentages of total violent crime reported to police for victims with (47%) and without disabilities (47%) in 2010- 14 (table 10). * The percentage of total violence reported to police did not vary by the number of disability types. * Total violence against persons with ambulatory disabilities (51%) was more likely to be reported to police than violence against persons with vision (39%) or self-care (44%, 90% confidence level) disabilities. * The majority of total violent crime against persons with (62%) and without disabilities (61%) reported to the police was reported by the victim (table 11). * A household member other than the victim reported 6% of violence against persons with disabilities to police, which was smaller than the percentage reported for persons without disabilities (10%). * Victims with and without disabilities offered similar reasons for not reporting to police (table 12). * Forty percent of violence against persons with disabilities was not reported to police because it was dealt with in another way. * Twenty percent of unreported violence against persons with disabilities was not reported because it was not important enough to the victim. Twenty-two percent was not reported because the victim did not think the police would help. ***************** Victim services ***************** * In 2010-14, a greater percentage of violence against persons with disabilities (13%) involved receipt of assistance from a victim service agency than violence against persons without disabilities (8%) (table 13). ************** Methodology ************** Survey coverage ***************** 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 is a self-report survey in which interviewed persons are asked about the number and characteristics of victimizations they experienced during the prior 6 months. The NCVS collects information on nonfatal personal crimes (rape or sexual assault, robbery, aggravated assault, simple assault, and personal larceny) and household property crimes (burglary, motor vehicle theft, and other theft) both reported and not reported to police. In addition to providing annual level and change estimates on criminal victimization, the NCVS is the primary source of information on the nature of criminal victimization incidents. Survey respondents provide information about themselves (e.g., age, sex, race and Hispanic origin, marital status, education level, and income) and whether they experienced a victimization. The NCVS collects information for each victimization incident about the offender as perceived by the victim (e.g., age, race and Hispanic origin, sex, and victim offender relationship), characteristics of the crime (including time and place of occurrence, use of weapons, nature of injury, and economic consequences), whether the crime was reported to police, reasons the crime was or was not reported, and experiences with the criminal justice system. The NCVS is administered to persons age 12 or older from a nationally representative sample of households in the United States. The survey defines a household as a group of persons who all reside at a sampled address. Persons are considered household members when the sampled address is their usual place of residence at the time of the interview and when they have no usual place of residence elsewhere. Once selected, households remain in the sample for 3 years, and eligible persons in these households are interviewed every 6 months either in person or over the phone for a total of seven interviews. Generally, all first interviews are conducted in person, with subsequent interviews conducted either in person or by phone. New households rotate into the sample on an ongoing basis to replace outgoing households that have been in the sample for a 3-year period. The sample includes persons living in group quarters (such as dormitories, rooming houses, and religious group dwellings) and excludes persons living in military barracks and institutional settings, (such as correctional or hospital facilities) and persons who are homeless. In 2007, the NCVS adopted questions from the U.S. Census Bureau’s American Community Survey (ACS) to measure the rate of victimization against people with disabilities. The NCVS does not identify persons in the general population with disabilities. The ACS Subcommittee on Disability Questions developed the disability questions based on those used in the 2000 Decennial Census and earlier versions of the ACS. The questions identify persons who may require assistance to maintain their independence, be at risk for discrimination, or lack opportunities available to the general population because of limitations related to a prolonged (i.e., 6 months or longer) sensory, physical, mental, or emotional condition. More information about the ACS and the disability questions is available on the U.S. Census Bureau’s website at https://www.census.gov/people/disability/methodology/acs.html. Changes to the disability questions in the NCVS and ACS in 2008 ************************************ In 2008, the U.S. Census Bureau changed some of the disability questions on the ACS. The question about sensory disability was separated into two questions about blindness and deafness, and the questions about physical disability asked only about serious difficulty walking or climbing stairs. Also, questions on employment disability and going outside of the home were eliminated in 2008. Analysis of 2007 and 2008 ACS disability data by the U.S. Census Bureau revealed significant conceptual and measurement differences between the 2007 and 2008 disability questions. The U.S. Census Bureau concluded that data users should not compare the 2007 estimates of the population with disabilities to those of later years. Because the 2007 and 2008 NCVS disability questions mirrored the ACS disability questions, estimates of victimization of people with disabilities from the 2007 and 2008 NCVS should not be compared. As a result, the 2007 disability data are not presented in this report. Further explanation about incomparability of the 2007 and 2008 ACS disability data is available at https://www.census.gov/people/ disability/files/2008ACS_disability.pdf. Definitions of disability types ********************************* Disabilities are classified according to six limitations: hearing, vision, cognitive, ambulatory, self-care, and independent living. * Hearing limitation entails deafness or serious difficulty hearing. * Vision limitation is blindness or serious difficulty seeing, even when wearing glasses. * Cognitive limitation includes serious difficulty in concentrating, remembering, or making decisions because of a physical, mental, or emotional condition. * Ambulatory limitation is difficulty walking or climbing stairs. * Self-care limitation is a condition that causes difficulty dressing or bathing. * Independent living limitation is a physical, mental, or emotional condition that impedes doing errands alone, such as visiting a doctor or shopping. Disability questions included in the NCVS from 2009 through 2014 ************************************** Questions 169a through 173 169a. Are you deaf or do you have serious difficulty hearing? 169b. Are you blind or do you have serious difficulty seeing even when wearing glasses? 170a. Because of a physical, mental, or emotional condition, do you have serious difficulty-- * concentrating, remembering, or making decisions? * walking or climbing stairs? * dressing or bathing? 170b. Because of a physical, mental, or emotional condition, do you have difficulty doing errands alone, such as visiting a doctor’s office or shopping? 171. Is “Yes” marked in any of 169a-170b? (That is, has the respondent indicated that he/she has a health condition or disability?) 172. During the incident you just told me about, do you have reason to suspect you were victimized because of your health condition(s), impairment(s), or disability(ies)? 173. What health conditions, impairments, or disabilities do you believe caused you to be targeted for this incident? Age limitation on independent living ************************************** In the ACS, persons ages 12 to 14 are not asked about having an independent living disability and are, therefore, excluded in the populations with independent living disabilities. Even though crime victims ages 12 to 14 receive this question in the NCVS (question 170b), victims ages 12 to 14 who respond affirmatively are excluded from rates of violent victimization against persons with an independent living disability to match the age limitations for having an independent living disability in the ACS (age 15 or older). In this report, rates of violence against persons with an independent living disability are per 1,000 persons age 15 or older, compared to rates per 1,000 persons age 12 or older for other disability types. Also, violent crime victims ages 12 to 14 who report in the NCVS that they have an independent living disability and no other disability type are classified as not having a disability to be compatible with age limits on disability definitions in the ACS. Limitations of the estimates ****************************** The NCVS was designed to measure the incidence of criminal victimization against the U.S. civilian household population, excluding persons who live in institutions and the homeless. Institutions include adult correctional facilities, juvenile facilities, nursing or skilled nursing facilities, inpatient hospice facilities, residential schools for people with disabilities, and hospitals with patients who have no usual home elsewhere. The measures of crime against persons with disabilities (as measured by the NCVS) cover only people with disabilities who are living among the general population in household settings. Subsequently, there is some coverage error in using just the noninstitutionalized population. For example, according to the ACS, about 95% of the 1.3 million people age 65 or older living in institutions had disabilities in 2014 (not shown). Because persons in these facilities would not be covered in the NCVS, estimates of violence against these persons are not counted. The lack of information from the institutions will result in an undercount of violence against persons with disabilities. Certain aspects of the NCVS design can also contribute to underestimating the level or type of violence against persons with disabilities. For example, the survey instruments, modes of interview, and interviewing protocols used in the NCVS may not be suited for interviewing people who have difficulty communicating, especially by telephone. Some people have disabilities that limit their verbal communication and use technology to enhance their ability to communicate, but many people do not have access to such technology. Proxy interviews may also lead to an underestimate of violence against persons with disabilities. The survey requires direct interviews with eligible respondents but allows the use of proxy interviews with a caregiver or other eligible party in a limited set of circumstances. A proxy interview is allowed when a respondent is physically or mentally incapable of responding. The survey restrictions on proxy interviews were instituted because someone else may not know about the victimization experiences of the respondent, and because the person providing the information via proxy may be the perpetrator of the violence experienced by the respondent. Because proxy respondents may be more likely to omit crime incidents or may not know some details about reported incidents, the number or types of crimes against persons with disabilities may be underestimated. In 2014, information from about 5% of violent crime incidents against persons with disabilities was obtained from proxy interviews. In addition, 62% of the reports of violent incidents against persons with disabilities obtained through proxy interviews were for simple assault, compared to about 57% of reports of violent incidents against persons with disabilities obtained through nonproxy interviews (not shown). Public Use Microdata Sample data *********************************** To generate populations by disability status for 2008 through 2014, PUMS data from the U.S. Census Bureau’s ACS were used to calculate populations by disability status. The ACS PUMS dataset is a sample of population and housing unit records from the ACS. Usually, the PUMS files include only about two-thirds of the cases contained in the larger, complete confidential dataset. The ACS PUMS files include the actual responses collected in ACS questionnaires, although some responses have been edited to protect the confidentiality of respondents. The ACS PUMS file included sample weights for each person and housing unit, which were applied to the individual records to expand the sample to estimate totals and percentages of the full population. For more information on ACS PUMS data from the U.S. Census Bureau, see https://www.census.gov/programs-surveys/acs/ technical-documentation/pums.html. Direct standardization *********************** The method used to generate age-adjusted rates of violent victimization of persons without disabilities was direct standardization with the population with disabilities as the standard population.***Footnote 1 1For more information on direct standardization, see Curtin, L. R. & Klein, R. J. (1995). Direct standardization (age-adjusted death rates). Healthy People 2000: Statistical Notes, 6 Revised. Available at http://www.cdc.gov/ nchs/data/statnt/statnt06rv.pdf. This procedure eliminates the problem of different age distributions between and within groups. In general, persons with disabilities are an older population than persons without disabilities. Because crime rates vary by age, direct standardization produces age-adjusted rates for persons without disabilities that would occur if the population without disabilities had the same age distribution as the population with disabilities. The age-adjusted violent victimization rate, using direct standardization (Rd), is calculated as— Rd = Σ (wa * ra) Where Rd = age-adjusted rate of violent victimization of the population without disabilities calculated using direct standardization wa = weight calculated from the population with disabilities for age-group a ra = unadjusted rate of violent victimization of persons without disabilities in age-group a d = direct standardization. The weight (wa) for age-group a is calculated as-- wa = na / N where wa = weight calculated from the population with disabilities for age-group a na = number of persons in age-group a in the population with disabilities N = total number of persons in the population with disabilities. This method produces rates of violent victimization as if the population without disabilities had the same age distribution as the population with disabilities. In figure 1, for each year, unadjusted rates were calculated for persons with disabilities. For persons without disabilities, rates were age-adjusted to the population with disabilities for that year. For example, the 2013-14 rate of violent victimization against persons with disabilities was unadjusted. The 2013-14 rate of violent victimization against persons without disabilities was age-adjusted using the 2013-14 population with disabilities as the standard population. Change in direct standardization calculations *********************************************** In previous BJS reports about crimes against persons with disabilities, several different methods were used to calculate age-adjusted rates. More specifically, changes in the standard population were made. Over the years, the population without disabilities and the 2000 U.S. standard population generated by the U.S. Census Bureau have both been used as the standard population in calculating age-adjusted rates for persons with and without disabilities. Each time a change was made to the standard population, rates for all years were recalculated using the new standard population. This resulted in previous years having different rates from earlier reports. Nonresponse and weighting adjustments **************************************** In 2014, about 90,380 households and 158,090 persons age 12 or older were interviewed for the NCVS. Each household was interviewed twice during the year. The response rate was 84% for households and 87% for eligible persons. Victimizations that occurred outside of the United States were excluded from this report. In 2014, less than 1% of the unweighted victimizations occurred outside of the United States and were excluded from the analysis. Estimates in this report use data from the 2008 to 2014 NCVS data files weighted to produce annual estimates for persons age 12 or older living in U.S. households. Because the NCVS relies on a sample rather than a census of the entire U.S. population, weights are designed to inflate sample point estimates to known population totals and to compensate for survey nonresponse and other aspects of the sample design. The NCVS data files include both household and person weights. The household weight is commonly used to calculate estimates of property crimes, such as motor vehicle theft or burglary, which are identified with the household. Person weights provide an estimate of the population represented by each person in the sample. Person weights are most frequently used to compute estimates of crime victimizations of persons in the total population. After proper adjustment, both household and person weights are also used to form the denominator in calculations of crime rates. The victimization weights used in this analysis account for the number of persons present during an incident and for repeat victims when a series of incidents occurs. The weighting counts a series of incidents as the actual number of incidents reported by the victim, up to a maximum of 10 incidents. Series victimizations are 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 and collect detailed information on only the most recent incident in the series. In 2014, series incidents accounted for about 1% of all victimizations and 4% of all violent victimizations. The approach to weighting series incidents as the number of incidents up to a maximum of 10 produces more reliable estimates of crime levels, while the cap at 10 minimizes the effect of extreme outliers on the rates. Additional information on the series enumeration is detailed in the report Methods for Counting High Frequency Repeat Victimizations in the National Crime Victimization Survey (NCJ 237308, BJS web, April 2012). Standard error computations for percentages and unadjusted rates ************************************ When national estimates are derived from a sample, as is the case with the NCVS, caution must be taken when comparing one estimate to another or when comparing estimates over time. Although one estimate may be larger than another, estimates based on a sample 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 of the sample, and the size of the subgroup for which the estimate is computed. When the sampling error around the estimates is taken into consideration, estimates that appear different may not be statistically different. 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, for a given metric, an estimate with a smaller standard error provides a more reliable approximation of the true value than an estimate with a larger standard error. Estimates with relatively large standard errors are associated with less precision and reliability and should be interpreted with caution. To generate standard errors around numbers and estimates from the NCVS, the U.S. Census Bureau produces generalized variance function (GVF) parameters for BJS. The GVFs take into account aspects of the NCVS complex sample design and represent the curve fitted to a selection of individual standard errors based on the Jackknife Repeated Replication technique. The GVF parameters were used to generate standard errors for each point estimate (such as counts, percentages, and unadjusted rates) in this report. For estimates, standard errors were based on the ratio of the sums of victimizations and respondents across years. BJS conducted tests to determine whether differences in estimated numbers, percentages, and unadjusted rates in this report were statistically significant once sampling error was taken into account. Using statistical programs developed specifically for the NCVS, all comparisons in the text were tested for significance. The primary test procedure was the Student’s t- statistic, which tests the difference between two sample estimates. Unless otherwise noted, the findings described in this report as higher, lower, or different passed a test at the 0.05 level of statistical significance (95% confidence level). Findings that passed a test at the 0.10 level of significance are noted as such in the text, i.e. (90% confidence level). Caution is required when comparing estimates not explicitly discussed in this report. Data users can use the estimates and the standard errors of the estimates provided in this report to generate a confidence interval around the estimate as a measure of the margin of error. The following example illustrates how standard errors can be used to generate confidence intervals: According to the NCVS, from 2010 to 2014, 50.7% of simple assaults against persons with disabilities involved victims with multiple disability types (see table 6). Using the GVFs, BJS determined that the estimate has a standard error of 2.39% (see appendix table 7). A confidence interval around the estimate was generated by multiplying the standard error by ±1.96 (the t-score of a normal, two-tailed distribution that excludes 2.5% at either end of the distribution). Therefore, the confidence interval around the 50.7% estimate is 50.7% ± 2.39% * 1.96 (or 45.98% to 55.36%). In other words, if we used the same sampling method to select different samples and computed an interval estimate for each sample we would expect the true population parameter (percent of simple assaults against persons with disabilities in which the victim had multiple disability types) to fall within the interval estimates 95% of the time. In this report, a coefficient of variation (CV), representing the ratio of the standard error to the estimate, was also calculated for all estimates. CVs provide a measure of reliability and a means for comparing the precision of estimates across measures with differing levels or metrics. In cases where the CV was greater than 50%, or the unweighted sample had 10 or fewer cases, the estimate was noted with a “!” symbol (Interpret data with caution. Estimate based on 10 or fewer sample cases, or coefficient of variation is greater than 50%.) Standard error computations and statistical significance for age-adjusted rates ********************************************* Due to the complexity in generating age-adjusted rates of violent crime, other methods were used to compute standard errors and determine statistical significance. ***Footnote 2 For more information on computing standard errors for age-adjusted rates, see Anderson, R. N., & Rosenberg, H. M. (1998). Age standardization of death rates: Implementation of the year 2000 standard. National Vital Statistics Reports, 47 (3). Available at http://www.cdc.gov/nchs/data/nvsr/nvsr47/nvs47_03.pdf.*** The standard error for age-adjusted rates of violent victimization against persons without disabilities was calculated as— Sd = √Σ (wa^2 * va) where Sd = standard error for an age-adjusted rate of violent victimization against persons without disabilities that was computed using direct standardization wa = weight calculated from the population with disabilities for age-group a va = variance calculated for an unadjusted rate of violent victimization of persons without disabilities for age group a using information from the generalized variance function (GVF) parameters that the Census Bureau produced for the NCVS. To calculate statistical significance among two age-adjusted rates, the standard errors for the two rates were calculated using the formula above. A Student’s t-statistic also was calculated, which tests the difference between two sample estimates. Unless otherwise noted, the findings described in this report as higher, lower, or different passed a test at the 0.05 level of statistical significance (95% confidence level). Findings that passed a test at the 0.10 level of significance are noted as such in the text, i.e. (90% confidence level). ********************************************************* The Bureau of Justice Statistics of the U.S. Department of Justice is the principal federal agency responsible for measuring crime, criminal victimization, criminal offenders, victims of crime, correlates of crime, and the operation of criminal and civil justice systems at the federal, state, tribal, and local levels. BJS collects, analyzes, and disseminates reliable and valid statistics on crime and justice systems in the United States, supports improvements to state and local criminal justice information systems, and participates with national and international organizations to develop and recommend national standards for justice statistics. Jeri M. Mulrow is Acting Director. These statistical tables were prepared by Erika Harrell. Jennifer Truman provided verification. Brigitte Coulton and Morgan Young edited the report. Tina Dorsey produced the report. November 2016, NCJ 250200 ********************************************************** *********************************************** Office of Justice Programs Building Solutions | Supporting Communities | Advancing Justice www.ojp.gov *********************************************** ************************** 11/8/2016/ JER/ 3:30AM **************************