Bureau of Justice Statistics
A division of the U.S. Department of Justice Office of Justice Programs, the Bureau of Justice Statistics (BJS) collects, analyzes, publishes, and disseminates statistical information on crime, criminal offenders, victims of crime, and the operations of the justice system at all levels of government and internationally. It also provides technical and financial support to state governments for development of criminal justice statistics and information systems on crime and justice.
For information on the BJS, see https://www.bjs.gov/.
National Crime Victimization Survey
The National Crime Victimization Survey (NCVS), administered for the U.S. Bureau of Justice Statistics (BJS) by the U.S. Census Bureau, is the nation’s primary source of information on crime and the victims of crime. Initiated in 1972 and redesigned in 1992 and 2016, the NCVS collects detailed information on the frequency and nature of the crimes of rape, sexual assault, robbery, aggravated and simple assault, theft, household burglary, and motor vehicle theft experienced by Americans and American households each year. The survey measures both crimes reported to the police and crimes not reported to the police.
NCVS estimates presented may differ from those in previous published reports. This is because a small number of victimizations, referred to as series victimizations, are included using a new counting strategy. High-frequency repeat victimizations, or series victimizations, are six or more similar but separate victimizations that occur with such frequency that the victim is unable to recall each individual event or describe each event in detail. As part of ongoing research efforts associated with the redesign of the NCVS, BJS investigated ways to include high-frequency repeat victimizations, or series victimizations, in estimates of criminal victimization. Including series victimizations results in more accurate estimates of victimization. BJS has decided to include series victimizations using the victim’s estimates of the number of times the victimizations occurred over the past 6 months, capping the number of victimizations within each series at a maximum of 10. This strategy for counting series victimizations balances the desire to estimate national rates and account for the experiences of persons who have been subjected to repeat victimizations against the desire to minimize the estimation errors that can occur when repeat victimizations are reported. Including series victimizations in national rates results in rather large increases in the level of violent victimization; however, trends in violence are generally similar regardless of whether series victimizations are included. For more information on the new counting strategy and supporting research, see Methods for Counting High-Frequency Repeat Victimizations in the National Crime Victimization Survey at https://www.bjs.gov/content/pub/pdf/mchfrv.pdf.
Readers should note that in 2003, in accordance with changes to the Office of Management and Budget’s standards for the classification of federal data on race and ethnicity, the NCVS item on race/ethnicity was modified. A question on Hispanic origin is now followed by a new question on race. The new question about race allows the respondent to choose more than one race and delineates Asian as a separate category from Native Hawaiian or Other Pacific Islander. An analysis conducted by the Demographic Surveys Division at the U.S. Census Bureau showed that the new race question had very little impact on the aggregate racial distribution of the NCVS respondents, with one exception: There was a 1.6 percentage point decrease in the percentage of respondents who reported themselves as White. Due to changes in race/ethnicity categories, comparisons of race/ethnicity across years should be made with caution.
There were changes in the sample design and survey methodology in the 2006 NCVS that may have affected survey estimates. Caution should be used when comparing the 2006 estimates to estimates of other years. Data from 2007 onward are comparable to earlier years. Analyses of the 2007 estimates indicate that the program changes made in 2006 had relatively small effects on NCVS estimates. For more information on the 2006 NCVS data, see Criminal Victimization, 2006, at https://www.bjs.gov/content/pub/pdf/cv06.pdf; the NCVS 2006 technical notes, at https://bjs.ojp.usdoj.gov/content/pub/pdf/cv06tn.pdf; and Criminal Victimization, 2007, at https://bjs.ojp.usdoj.gov/content/pub/pdf/cv07.pdf.
The NCVS sample was redesigned in 2016 in order to account for changes in the U.S. population identified through the 2010 Decennial Census and to make it possible to produce state- and local-level victimization estimates for the largest 22 states and specific metropolitan areas within those states. This redesign resulted in a historically large number of new households and first-time interviews in the sample and produced challenges in comparing 2016 to prior data years. In order to allow for year-to-year comparisons between 2016 and other data years, BJS worked with the U.S. Census Bureau to create a revised 2016 NCVS data file. For more information on the revised 2016 NCVS data file, see Criminal Victimization, 2016: Revised, at https://www.bjs.gov/content/pub/pdf/cv16re.pdf. (For the original release of the 2016 NCVS data, see Criminal Victimization, 2016, at https://www.bjs.gov/content/pub/pdf/cv16_old.pdf.)
The number of NCVS-eligible households in the 2017 NCVS sample was about 146,000. Households were selected using a stratified, multistage cluster design. In the first stage, the primary sampling units (PSUs), consisting of counties or groups of counties, were selected. In the second stage, smaller areas, called Enumeration Districts (EDs), were selected from each sampled PSU. Finally, from selected EDs, clusters of four households, called segments, were selected for interview. At each stage, the selection was done proportionate to population size in order to create a self-weighting sample. The final sample was augmented to account for households constructed after the decennial census. Within each sampled household, the U.S. Census Bureau interviewer attempts to interview all household members age 12 and over to determine whether they had been victimized by the measured crimes during the 6 months preceding the interview.
The first NCVS interview with a housing unit is conducted in person. Subsequent interviews are conducted by telephone, if possible. Households remain in the sample for 3 years and are interviewed seven times at 6-month intervals. Since the survey’s inception, the initial interview at each sample unit has been used only to bound future interviews to establish a time frame to avoid duplication of crimes uncovered in these subsequent interviews. Beginning in 2006, data from the initial interview have been adjusted to account for the effects of bounding and have been included in the survey estimates. After a household has been interviewed its seventh time, it is replaced by a new sample household. In 2017, the household response rate was about 76 percent and the completion rate for persons within households was about 84 percent. Weights were developed to permit estimates for the total U.S. population 12 years and older. For more information on the 2017 NCVS, see https://www.bjs.gov/content/pub/pdf/cv17.pdf.
Further information on the NCVS may be obtained from
School Crime Supplement
Created as a supplement to the NCVS and codesigned by the National Center for Education Statistics and Bureau of Justice Statistics, the School Crime Supplement (SCS) survey has been conducted in 1989, 1995, and biennially since 1999 to collect additional information about school-related victimizations on a national level. This report includes data from the 1995, 1999, 2001, 2003, 2005, 2007, 2009, 2011, 2013, 2015, and 2017 collections. The 1989 data are not included in this report as a result of methodological changes to the NCVS and SCS. The SCS was designed to assist policymakers, as well as academic researchers and practitioners at federal, state, and local levels, to make informed decisions concerning crime in schools. The survey asks students a number of key questions about their experiences with and perceptions of crime and violence that occurred inside their school, on school grounds, on the school bus, or on the way to or from school. Students are asked additional questions about security measures used by their school, students’ participation in after-school activities, students’ perceptions of school rules, the presence of weapons and gangs in school, the presence of hate-related words and graffiti in school, student reports of bullying and reports of rejection at school, and the availability of drugs and alcohol in school. Students are also asked attitudinal questions relating to fear of victimization and avoidance behavior at school.
The SCS survey was conducted for a 6-month period from January through June in all households selected for the NCVS (see discussion above for information about the NCVS sampling design and changes to the race/ethnicity variable beginning in 2003). Within these households, the eligible respondents for the SCS were those household members who had attended school at any time during the 6 months preceding the interview, were enrolled in grades 6–12, and were not homeschooled. In 2007, the questionnaire was changed and household members who attended school sometime during the school year of the interview were included. The age range of students covered in this report is 12–18 years of age. Eligible respondents were asked the supplemental questions in the SCS only after completing their entire NCVS interview. It should be noted that the first or unbounded NCVS interview has always been included in analysis of the SCS data and may result in the reporting of events outside of the requested reference period.
The prevalence of victimization for 1995, 1999, 2001, 2003, 2005, 2007, 2009, 2011, 2013, 2015, and 2017 was calculated by using NCVS incident variables appended to the SCS data files of the same year. The NCVS type of crime variable was used in the SCS to classify student victimizations into the categories “serious violent,” “violent,” and “theft.” The NCVS variables asking where the incident happened (at school) and what the victim was doing when it happened (attending school or on the way to or from school) were used to ascertain whether the incident happened at school. Only incidents that occurred inside the United States are included.
In 2001, the SCS survey instrument was modified. In 1995 and 1999, “at school” had been defined for respondents as meaning in the school building, on the school grounds, or on a school bus. In 2001, the definition of at “school” was changed to mean in the school building, on school property, on a school bus, or going to and from school. The change to the definition of “at school” in the 2001 questionnaire was made in order to render the definition there consistent with the definition as it is constructed in the NCVS. This change to the definition of “at school” has been retained in subsequent SCS collections. Cognitive interviews conducted by the U.S. Census Bureau on the 1999 SCS suggested that modifications to the definition of “at school” would not have a substantial impact on the estimates.
A total of about 9,700 students participated in the 1995 SCS, and 8,400 students participated in both the 1999 and 2001 SCS. In 2003, 2005, 2007, 2009, 2011, 2013, 2015, and 2017, the numbers of students participating were 7,200, 6,300, 5,600, 5,000, 6,500, 5,700, 5,500, and 7,100, respectively.
In the 1995, 1999, 2001, 2003, 2005, 2007, 2009, 2011, 2013, 2015, and 2017 SCS collections, the household completion rates were 95 percent, 94 percent, 93 percent, 92 percent, 91 percent, 90 percent, 92 percent, 91 percent, 86 percent, 82 percent, and 76 percent, respectively, and the student completion rates were 78 percent, 78 percent, 77 percent, 70 percent, 62 percent, 58 percent, 56 percent, 63 percent, 60 percent, 58 percent, and 52 percent, respectively. The overall SCS unit response rate (calculated by multiplying the household completion rate by the student completion rate) was about 74 percent in 1995, 73 percent in 1999, 72 percent in 2001, 64 percent in 2003, 56 percent in 2005, 53 percent in 2007, 51 percent in 2009, 57 percent in 2011, 51 percent in 2013, 48 percent in 2015, and 40 percent in 2017. (Prior to 2011, overall SCS unit response rates were unweighted; starting in 2011, overall SCS unit response rates are weighted.)
There are two types of nonresponse: unit and item nonresponse. NCES requires that any stage of data collection within a survey that has a unit base-weighted response rate of less than 85 percent be evaluated for the potential magnitude of unit nonresponse bias before the data or any analysis using the data may be released (NCES Statistical Standards, 2002, at https://nces.ed.gov/statprog/2002/std4_4.asp). Due to the low unit response rate in 2005, 2007, 2009, 2011, 2013, 2015, and 2017, a unit nonresponse bias analysis was done. Unit response rates indicate how many sampled units have completed interviews. Because interviews with students could only be completed after households had responded to the NCVS, the unit completion rate for the SCS reflects both the household interview completion rate and the student interview completion rate. Nonresponse can greatly affect the strength and application of survey data by leading to an increase in variance as a result of a reduction in the actual size of the sample and can produce bias if the nonrespondents have characteristics of interest that are different from the respondents. In order for response bias to occur, respondents must have different response rates and responses to particular survey variables. The magnitude of unit nonresponse bias is determined by the response rate and the differences between respondents and nonrespondents on key survey variables. Although the bias analysis cannot measure response bias since the SCS is a sample survey and it is not known how the population would have responded, the SCS sampling frame has several key student or school characteristic variables for which data are known for respondents and nonrespondents: sex, age, race/ethnicity, household income, region, and urbanicity, all of which are associated with student victimization. To the extent that there are differential responses by respondents in these groups, nonresponse bias is a concern.
In 2005, the analysis of unit nonresponse bias found evidence of bias for the race, household income, and urbanicity variables. White (non-Hispanic) and Other (non-Hispanic) respondents had higher response rates than Black (non-Hispanic) and Hispanic respondents. Respondents from households with an income of $35,000–$49,999 and $50,000 or more had higher response rates than those from households with incomes of less than $7,500, $7,500–$14,999, $15,000–$24,999, and $25,000–$34,999. Respon¬dents who live in urban areas had lower response rates than those who live in rural or suburban areas. Although the extent of nonresponse bias cannot be determined, weighting adjustments, which corrected for differential response rates, should have reduced the problem.
In 2007, the analysis of unit nonresponse bias found evidence of bias by the race/ethnicity and household income variables. Hispanic respondents had lower response rates than respondents of other races/ethnicities. Respondents from households with an income of $25,000 or more had higher response rates than those from households with incomes of less than $25,000. However, when responding students are compared to the eligible NCVS sample, there were no measurable differences between the responding students and the eligible students, suggesting that the nonresponse bias has little impact on the overall estimates.
In 2009, the analysis of unit nonresponse bias found evidence of potential bias for the race/ethnicity and urbanicity variables. White students and students of other races/ethnicities had higher response rates than did Black and Hispanic respondents. Respondents from households located in rural areas had higher response rates than those from households located in urban areas. However, when responding students are compared to the eligible NCVS sample, there were no measurable differences between the responding students and the eligible students, suggesting that the nonresponse bias has little impact on the overall estimates.
In 2011, the analysis of unit nonresponse bias found evidence of potential bias for the age variable. Respondents 12 to 17 years old had higher response rates than did 18-year-old respondents in the NCVS and SCS interviews. Weighting the data adjusts for unequal selection probabilities and for the effects of nonresponse. The weighting adjustments that correct for differential response rates are created by region, age, race, and sex, and should have reduced the effect of nonresponse.
In 2013, the analysis of unit nonresponse bias found evidence of potential bias for the age, region, and Hispanic origin variables in the NCVS interview response. Within the SCS portion of the data, only the age and region variables showed significant unit nonresponse bias. Further analysis indicated that only the age 14 and the west region categories showed positive response biases that were significantly different from some of the other categories within the age and region variables. Based on the analysis, nonresponse bias seems to have little impact on the SCS results. In 2015, the analysis of unit nonresponse bias found evidence of potential bias for age, race, Hispanic origin, urbanicity, and region in the NCVS interview response. For the SCS interview, the age, race, urbanicity, and region variables showed significant unit nonresponse bias. The age 14 group and rural areas showed positive response biases that were significantly different from other categories within the age and urbanicity variables. The northeast region and Asian race group showed negative response biases that were significantly different from other categories within the region and race variables. These results provide evidence that these subgroups may have a nonresponse bias associated with them. In 2017, the analysis of unit nonresponse bias found that the race/ethnicity and census region variables showed significant differences in response rates between different race/ethnicity and census region subgroups. Respondent and nonrespondent distributions were significantly different for the race/ethnicity subgroup only. However, after using weights adjusted for person nonresponse, there was no evidence that these response differences introduced nonresponse bias in the final victimization estimates. Response rates for SCS survey items in all survey years were high—typically over 95 percent of all eligible respondents, meaning there is little potential for item nonresponse bias for most items in the survey. The weighted data permit inferences about the eligible student population who were enrolled in schools in all SCS data years.
Further information about the SCS may be obtained from
Cross-Sectional Surveys Branch
Sample Surveys Division
National Center for Education Statistics
550 12th Street SW
Washington, DC 20202
Federal Bureau of Investigation
The Federal Bureau of Investigation (FBI) collects statistics on crimes from law enforcement agencies throughout the country through the Uniform Crime Reporting (UCR) Program. The UCR Program was conceived in 1929 by the International Association of Chiefs of Police to meet a need for reliable, uniform crime statistics for the nation. In 1930, the FBI was tasked with collecting, publishing, and archiving those statistics. Today, several annual statistical publications, such as the comprehensive Crime in the United States (CIUS), are produced from data provided by over 18,000 law enforcement agencies across the United States. CIUS is an annual publication in which the FBI compiles the volume and rate of crime offenses for the nation, the states, and individual agencies. This report also includes arrest, clearance, and law enforcement employee data.
For more information on the UCR Program, see https://ucr.fbi.gov/ucr.
Studies of Active Shooter Incidents
The Investigative Assistance for Violent Crimes Act of 2012, which was signed into law in 2013, authorizes the attorney general, upon the request of an appropriate state or local law enforcement official, to “assist in the investigation of violent acts and shootings occurring in a place of public use and in the investigation of mass killings and attempted mass killings.” The attorney general delegated this responsibility to the FBI.
In 2014, the FBI initiated studies of active shooter incidents in order to advance the understanding of these incidents and provide law enforcement agencies with data that can inform efforts toward preventing, preparing for, responding to, and recovering from them.
Data on active shooter incidents at educational institutions come from the FBI reports A Study of Active Shooter Incidents in the United States Between 2000 and 2013, Active Shooter Incidents in the United States in 2014 and 2015, and Active Shooter Incidents in the United States in 2016 and 2017, which can be accessed at https://www.fbi.gov/about/partnerships/office-of-partner-engagement/active-shooter-resources.
Further information about FBI resources on active shooter incidents may be obtained from
Active Shooter Resources
Office of Partner Engagement
Federal Bureau of Investigation
U.S. Department of Justice
935 Pennsylvania Avenue NW
Washington, DC 20535
Supplementary Homicide Reports
Supplementary Homicide Reports (SHR) are a part of the Uniform Crime Reporting (UCR) program of the Federal Bureau of Investigation (FBI). These reports provide incident-level information on criminal homicides, including situation type (e.g., number of victims, number of offenders, and whether offenders are known); the age, sex, and race of victims and offenders; the weapon used; circumstances of the incident; and the relationship of the victim to the offender. The data are provided monthly to the FBI by local law enforcement agencies participating in the UCR program. The data include murders and nonnegligent manslaughters in the United States; thus, negligent manslaughters and justifiable homicides have been eliminated from the data.
About 90 percent of homicides are included in the SHR program. However, adjustments can be made to the weights to correct for missing victim reports. Estimates from the SHR program used in this report were generated by the Bureau of Justice Statistics (BJS).
Further information on the SHR program may be obtained from
Criminal Justice Information Services Division
Federal Bureau of Investigation
1000 Custer Hollow Road
Clarksburg, WV 26306