Crime Victimization in the US

Printer Friendly version
Collapse open tabs

Goal

The goal of this exercise is to explore crime victimization in the US. Frequencies, crosstabulations and comparisons of means will be used.

Concept

Crime victimization is defined as the involuntary, personal exposure to criminal acts. Victimization can be economic, physical, psychological and/or emotional.

It is difficult to know exactly how many crimes are committed and how many people are victimized every year because a significant percentage of crimes (almost half of violent crimes and about one third of property crimes) go unreported to, or undiscovered by, police. Criminologists refer to this unknown as the "dark figure of crime." By polling a large number of households, victimization surveys such as the National Crime Victimization Survey are able to uncover some of the crime incidents that were never reported or discovered by police. They also provide more detailed information about the crime, victim, and offender(s), than other official sources of crime statistics such as the FBI's Uniform Crime Reports. Victimization surveys are therefore an important source of data for criminologists, but they are not without their limitations. For example, they rely on respondents' honesty and ability to recall facts accurately; since they typically survey only people 12 and older, they provide no data on crimes committed against children; and since they survey crime victims, there is no data on murders either, for obvious reasons!

When discussing crime statistics, it is important to distinguish between incidents (how many crimes have occurred) and rates (number of crimes committed among a given number of people - typically, though not always, per 100,000). For example, there were 368 murders in Detroit, Michigan, in 2008, which corresponds to a murder rate of 40.7 per 100,000 residents.

Examples of possible research questions about victimization include:

  • In which demographic groups is victimization the highest?
  • What factors affect the likelihood that someone will be victimized?
  • How have victimization rates changed over time, and why?
  • Who are different social groups most likely to be victimized?
  • Which crimes are more likely to be reported to police, and why?
  • What are some of the reasons why people do not report crimes to the police?

This exercise will use the National Crime Victimization Survey, 1992-2005: Concatenated Incident-Level Files.

This exercise will use the National Crime Victimization Survey (NCVS), previously called the National Crime Surveys (NCS). NCVS is the nation's primary source of information on criminal victimization. Each year, data are obtained from a nationally representative sample of 76,000 households comprising nearly 135,300 persons on the frequency, characteristics and consequences of criminal victimization in the United States. The NCVS was designed with four primary objectives: (1) to develop detailed information about the victims and consequences of crime, (2) to estimate the number and types of crimes not reported to the police, (3) to provide uniform measures of selected types of crimes, and (4) to permit comparisons over time and types of areas. The survey categorizes crimes as "personal" or "property." Personal crimes include rape and sexual attack, robbery, aggravated and simple assault, and purse-snatching/pocket-picking, while property crimes include burglary, theft, motor vehicle theft, and vandalism. Each respondent is asked a series of screening questions designed to determine whether she or he was victimized during the six-month period preceding the first day of the month of the interview. A "household respondent" is also asked to report on crimes against the household as a whole (e.g., burglary, motor vehicle theft). The data include type of crime, month, time, and location of the crime, relationship between victim and offender, characteristics of the offender, self-protective actions taken by the victim during the incident and results of those actions, consequences of the victimization, type of property lost, whether the crime was reported to police and reasons for reporting or not reporting, and offender use of weapons, drugs, and alcohol. Basic demographic information such as age, race, gender, and income is also collected, to enable analysis of crime by various subpopulations.

This exercise will use the following variables:

  • Type of crime code (V4529)
  • Year (V3027)
  • Household income (V2026)
  • Age (V2042)
  • Sex (V2045)
  • Number of crime incident reports (V2073)
  • About what time did incident occur? (V4021 and V4021B)
  • Respondent's relationship to offender: spouse (V4513)
  • Respondent's relationship to offender: parent (V4515)
  • Respondent's relationship to offender: other relative (V4516)
  • Respondent's relationship to offender: neighbor (V4518)
  • Respondent's relationship to offender: schoolmate (V4519)
  • Respondent's relationship to offender: stranger (V4521)
  • Reported to police (V4399)
  • Most important reason not reported (V4422)
  • Most important reason for reporting (V4437)

In this exercise, we will explore general trends about crime victimization, how different demographic groups are affected by crime victimization, relationships between victims and offenders, and why victims choose to report or not to report crimes to the police.

Victimization: types and trends

The NCVS classifies crimes in 3 broad categories: violent crimes, purse snatching/pocket picking, and property crimes. We used this categorization to recode the variable V4529 by collapsing the long list of crime codes into the categories: "Violent crimes" ("1"), "Purse snatching/pocket picking" ("2"), and "Property crimes" ("3"). The new variable is called CRIMETYPE.

Consider the frequency distribution of CRIMETYPE. What percentage of crimes falls under the category "Property crimes"? What percentage of crimes are "Violent crimes"?

The comparison of means with V2073 (Number of incident reports) and V3027 (Year) shows trends in victimization over time. In what year was the mean number of incident reports the highest? In what year was it the lowest? Overall, does victimization appear to have increased or decreased over time?

Most people assume that the likelihood of victimization increases at night. Is that really the case? Take a look at the frequency distribution of TIMEINC, a variable that provides information about the time of the incident. What time of day (or night) is victimization the highest? If we consider that daytime is between 6am and 6pm, what percentage of incidents happens in the daytime? What percentage happens at nighttime?

Victim demographics

In this section we will be looking at the relationship between victimization (measured by the variables CRIMETYPE and Number of incident reports) and gender, age, and household income.

We used a crosstab of CRIMETYPE and gender (V2045) to see whether there is a relationship between gender and victimization. According to the results of the analysis, what percentage of males has been the victim of a violent crime? How does this compare to females in the sample? Do the results surprise you?

Now consider the results of the comparison of means with Number of incident reports (V2073) and gender (V2045). What is the mean number of incident reports for females? Is it higher or lower for males?

Does age affect victimization? Before running the analysis, we recoded the age variable (V2042), which is a continuous variable, into a categorical variable. The new variable is called AGECAT and has 7 age categories (12-19, 20-29, 30-39, 40-49, 50-59, 60-79, and 80+).

Take a look at the results of the crosstab of AGECAT and CRIMETYPE. Which age group appears to have the highest violent crime victimization rate? Which age group reported the highest property crime victimization rate?

In the comparison of means with Number of incident reports and AGECAT, which age group has the highest number of incident reports? Which group has the lowest?

The variable household income (V2026) contains 14 categories - too many for a useful analysis. We collapsed the categories from 14 to 5 and named the new variable HHINC. According to the results of the crosstab of HHINC and CRIMETYPE, which income group reported the highest property crime victimization rate? Which income group reported the highest violent crime victimization rate?

Finally, in the comparison of means with HHINC, what is the average number of incident reports for respondents in the $0-19,000 income bracket? What is that number for respondents who reported earning over $75,000?

Victim-offender relationship

NCVS ascertains victim-offender relationships through a series of yes-no questions: for example, "What was the offender relationship to you: spouse?" (V4513). For ease of analysis, we combined 6 of these questions (V4513: spouse; V4515: parent; V4516: other relative; V4518: neighbor; V4519: schoolmate; V4521: stranger) into a single variable, called OFFREL, where "Spouse" is coded "1," "Parent" "2," "Other relative" "3," "Neighbor" "4," "Schoolmate" "5," and "Stranger" "6."

We then ran a crosstab with (V2045) OFFREL and sex (V2045). Who are males most likely to be victimized by? What percentage of females is victimized by a spouse? Look at the "Row Total" column in the results table. On average, who are people more likely to be victimized by: someone they know (categories 1-5), or a stranger (category 6)?

To break down the relationship between victim and offender along a different dimension, we ran a crosstab with OFFREL and AGECAT. In which age group are people the most likely to be victimized by someone they don't know (a stranger)? Who are those most likely to be victimized by a neighbor?

Reporting

One of the major difficulties in studying crime is that crimes are not always reported to police. As evidence, please take a look at the frequency distribution of V4399 (Reported to police). What percentage of respondents brought their victimization to the attention of police? Does this surprise you?

To investigate this further, examine the crosstabs of V4422 (Most important reason not reported) and CRIMETYPE, and V4437 (Most important reason for reporting) and CRIMETYPE. Since V4422 and V4437 each list a large number of reasons, it may be helpful to look at the bar charts. What are the top 5 reasons respondents cited for not reporting a violent crime to the police? How are those different from the top reasons for not reporting a property crime? What are the top reasons mentioned for reporting a violent crime? What are the top reasons mentioned for reporting a property crime?

Think about your answers to the application questions before you click through the interpretation guide for help in answering them.

Victimization: types and trends

What percentage of crimes falls under the category "Property crimes"? What percentage of crimes are "Violent crimes"?

In what year was the mean number of incident reports the highest? In what year was it the lowest? Overall, does victimization appear to have increased or decreased over time?

What time of day (or night) is victimization the highest? If we consider that daytime is between 6am and 6pm, what percentage of incidents happens in the daytime? What percentage happens at nighttime?

Victim demographics

What percentage of males has been the victim of a violent crime? How does this compare to females in the sample? Do the results surprise you?

What is the mean number of incident reports for females? Is it higher or lower for males?

Which age group appears to have the highest violent crime victimization rate? Which age group reported the highest property crime victimization rate?

Which age group has the highest number of incident reports? Which group has the lowest?

Which income group reported the highest property crime victimization rate? Which income group reported the highest violent crime victimization rate?

What is the average number of incident reports for respondents in the $0-19,000 income bracket? What is that number for respondents who reported earning over $75,000?

Victim-offender relationship

Who are males most likely to be victimized by? What percentage of females is victimized by a spouse? On average, who are people more likely to be victimized by: someone they know (categories 1-5), or a stranger (category 6)?

In which age group are people the most likely to be victimized by someone they don't know (a stranger)? Who are those most likely to be victimized by a neighbor?

Reporting

What percentage of respondents brought their victimization to the attention of police? Does this surprise you?

What are the top 5 reasons respondents cited for not reporting a violent crime to the police? How are those different from the top reasons for not reporting a property crime? What are the top reasons mentioned for reporting a violent crime? What are the top reasons mentioned for reporting a property crime?

Interpretation

Things to think about in interpreting the results:

  • The numbers in each cell of the crosstabulation tables show the percent of the people who fall into the overlapping categories, followed by the actual number of people that represents in this sample. The coloring in the tables demonstrates how the observed numbers in each cell compares to the expected number if there were no association between the two variables. The accompanying bar charts display the patterns visually as well.

  • In the comparison of means tables, the top number in each cell represents the mean of the dependent variable for each category of the independent variable(s) and the bottom number is the actual number of people in that category in the sample. For example, the mean number incidents for those ages 50-59 is 1.66.

  • Weights (mathematical formulas) are often used to adjust the sample proportions, usually by race, sex, or age, to more closely match those of the general population. The weight "WGTVICDY-ADJUSTED VICTIMIZATION WEIGHT-DATA YEAR" was used throughout this guide.

  • The analyses show the following:

    • Victimization: types and trends

    • Nearly three quarters (73.9%) of crimes are property crimes. Violent crimes make up 25.1% of crimes.

    • The mean number of incident reports was highest in 1995, with 1.95, and lowest in 2002, with 1.52. Victimization decreased in the second half of the 1990s, and remained constant through 2005. It increased again in 2006, but it is too early to say whether this is significant.

    • Over a quarter (27.5%) of incidents happen between 12 and 6pm. In this dataset, there isn't much evidence to suggest that more incidents take place during the night than the daytime. 46.4% of incidents take place during the daytime (6am-6pm), compared to 46% at nighttime.

    Victim demographics

    • 24.3% of males have been the victim of a violent crime. This number is slightly higher for females: 26.2%.

    • With 1.82, the mean number of incidents is higher for females than it is for males (1.73).

    • 12-19 year olds had the highest violent crime victimization rate (30.9%), while respondents 80 years or older had the highest property crime victimization rate (87.1%).

    • There appears to be an inverse relationship between age and victimization. The mean number of incident reports is highest for the 12-19 year olds in the sample (2.16) and lowest for those over 80 (1.35).

    • With 27.7%, respondents in the 0-$19,999 income bracket had the highest violent crime victimization rate, while those earning more than $75,000 were the most likely to be the victim of a property crime (77.6%).

    • The mean number of incident reports for those in the lowest income bracket was 1.93, compared to 1.59 for those in the highest income group.

    Victim-offender relationship

    • The most likely offender for males was a stranger (45.3% were victimized by a stranger, compared to 22.4% for females). Females on the other hand were most likely to be victimized by their spouse (20.8%, compared to 5.5% for males). Overall, one third of respondents were victimized by strangers, while two thirds were victimized by someone they know.

    • Victimization at the hands of a stranger is highest for 20-29 year olds (57.8%). Almost half of respondents in the oldest age group were victimized by neighbors-the highest percentage of all age groups.

      • Reporting

    • Only 38.1% of respondents have reported their victimization to the police.

    • The 5 most important reasons for not reporting a violent crime are: it is a private, personal matter (20.6%); minor unsuccessful crime (17.3%); other (16.7%); the crime was reported to an official other than police (14.4%); and police would not think it was important (4.5%). For property crimes, reasons differed in nature and importance: minor, unsuccessful crime (29.1%); other (10.8%); reported to different official (10.7%); could not ID the offender (9.3%); and police would not think it was important (7%).

    • The most important reasons for reporting a violent crime are: because it's a crime (28.3%); to stop the incident (16.8%); to prevent more crimes (17.5%); other (8.2%); and to stop the offender from committing crimes (6%). Here again, reasons cited for reporting a property crime differed: because it's a crime (36%); to recover property (25.9%); to prevent more crimes (4.9%); other (4.5%); and to collect insurance (4.4%).

Summary

The goal of this exercise was to explore crime victimization in the US. Taken together, the results show that property crimes make up a large proportion of all crimes, of which only about 40% get reported to police for reasons that vary by type of crime. There has been a small decrease in the mean number of incidents since the early 1990s, which is consistent with other official sources of crime data. Perhaps contrary to popular belief, the data show that most people are victimized during the daytime, and by someone they know. This holds true across gender and age groups. The social groups most likely to be victims of violent crimes are the poor and those 19 and under, while the most likely to be victims of property crimes are the rich and the elderly. Females had a higher mean number of incidents than males, and were slightly more likely to be the victim of a violent crime.

Further research might compare these findings to those obtained from other official sources of crime data such as the FBI's Uniform Crime Reports.

CITATION: Inter-university Consortium for Political and Social Research. Crime Victimization in the US: A Data-Driven Learning Guide. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2011-02-04. Doi: https://doi.org/10.3886/victimization

Creative Commons License This work is licensed under a Creative Commons Attribution-Noncommercial 3.0 United States License.