Highlights
“The National Crime Victimization Survey (NCVS) is the nation’s primary source of information on criminal victimization,” the US Census Bureau. No one is saying that about national FBI crime data.
Advocates claim they want an evidence-based approach to crime yet they ignore the best available data. We are dismissing a chance to create better, safer communities.
Journalists insist that democracy dies in the darkness but they pay little to no attention to the National Crime Victimization Survey and its findings.
This article is available as a podcast on YouTube and other podcast platforms.
Author
Leonard Adam Sipes, Jr.
Former Senior Specialist for Crime Prevention and Statistics for the Department of Justice’s clearinghouse. Former Director of Information Services, National Crime Prevention Council. Former Adjunct Associate Professor of Criminology and Public Affairs-University of Maryland, University College. Former police officer. Retired federal senior spokesperson.
Former advisor to presidential and gubernatorial campaigns. Former advisor to the “McGruff-Take a Bite Out of Crime” national media campaign. Produced successful state anti-crime media campaigns.
Thirty-five years of directing award-winning (50+) public relations for national and state criminal justice agencies. Interviewed thousands of times by every national news outlet, often with a focus on crime statistics and research. Created the first state and federal podcasting series. Produced a unique and emulated style of government proactive public relations.
Certificate of Advanced Study-The Johns Hopkins University.
Author of ”Success With The Media: Everything You Need To Survive Reporters and Your Organization” available at Amazon and additional booksellers.
Sign up for notice of new articles on the front page of this site.
Daily news summations on crime, violent crime, law enforcement, and the justice system are offered under “Google Crime News” in the banner of this website.
A comprehensive overview of crime for recent years is available at Violent and Property Crime Rates In The U.S.
Article
“The National Crime Victimization Survey (NCVS) is the nation’s primary source of information on criminal victimization,” the US Census Bureau. No criminologist can make the same claim about crimes reported to law enforcement offered by the FBI. Considering that the FBI offers reported crime, it’s filled with considerable flaws. The overwhelming majority of crime is not reported to law enforcement.
Per the US Department of Justice, rates for violent crime rose approximately 44 percent (per analyst Jeff Asher and The Marshall Project) in 2022 and rates were essentially the same in 2023 per the National Crime Victimization Survey.
It’s the largest increase in crime in our nation’s history.
An overview of the NCVS from the Bureau of Justice Statistics is available here.
There is no article advocating change within the justice system that does not include a demand that we be evidence-based in our approaches to crime. Yet we purposely choose to ignore the best available evidence when it comes to national crime numbers or rates.
From a criminological or methodological point of view, this undermines every ethical proposition possible. From a journalism perspective, not including the best available evidence violates every journalistic guideline. Yet many willingly do it.
We have a golden opportunity to ask why we have the largest increase in violent crime in our nation’s history. What caused it? Are there methodological or research concerns with the data or how it’s collected? Can we geo-locate (yes, the USDOJ has that capacity) to understand where it’s happening? Can we investigate who it’s happening to and look for explanations for why? We can do all of this but we don’t.
Can you imagine a huge increase in cancer or AIDs or COVID or pediatric diseases or employment-unemployment or any other condition without there being a national outcry as to why? The federal government and the scientific or journalism communities would be accused of malfeasance. The uproar would be enormous.
Yet when it comes to crime, we do not seem to care. So within this article, I will partially try what the US Department of Justice, the criminological community, and journalists refuse to do and add some context.
A 44 Percent Increase In Violent Crime
The US Department of Justice’s National Crime Victimization Survey from the Bureau Of Justice Statistics recorded the largest increase in rates of violent crime in the nation’s history for 2022 and the latest full report in 2023. It increased by approximately 44 percent in 2022. Per BJS, the rate of violent victimization in the United States was 22.5 victimizations per 1,000 persons age 12 or older in 2023, which was similar to the 2022 rate.
But as I talk to reporters, most have never heard of the 50-year-old National Crime Victimization Survey. When I bring this issue up in my writings, the pushback is considerable. On Reddit or social media groups, I’m accused of a string of right-wing incriminations meaning I’m called every derogatory name possible (i.e., you Trump-loving Natzi). Moderators of these groups never intervene.
Voters Were Right About the Economy. The Data Was Wrong. It’s Similar To Crime
Federal statistics are routinely corrected and can be wrong, similar to our unrealistic choice of FBI data over figures produced by the National Crime Victimization Survey. Gallup records record fear or concern about crime yet FBI data indicates declines. Multiple media articles suggested that voters were worrying about nothing.
Politico: “Before the presidential election, many Democrats were puzzled by the seeming disconnect between “economic reality” as reflected in various government statistics and the public’s perceptions of the economy on the ground. Many in Washington bristled at the public’s failure to register how strong the economy really was. They charged that right-wing echo chambers were conning voters into believing entirely preposterous narratives about America’s decline.”
“What they rarely considered was whether something else might be responsible for the disconnect — whether, for instance, government statistics were fundamentally flawed (emphasis added). What if the numbers supporting the case for broad-based prosperity were themselves misrepresentations? What if, in fact, darker assessments of the economy were more authentically tethered to reality”?
“What we uncovered shocked us. The bottom line is that, for 20 years or more, including the months prior to the election, voter perception was more reflective of reality (emphasis added) than the incumbent statistics. Our research revealed that the data collected by the various agencies is largely accurate. Moreover, the people staffing those agencies are talented and well-intentioned. But the filters used to compute the headline statistics are flawed. As a result, they paint a much rosier picture of reality than bears out on the ground” (emphasis added).
The National Crime Victimization Survey
The National Crime Victimization Survey was introduced over 50 years ago as a far superior method of collecting crime data when compared to the FBI’s crimes reported to law enforcement. Criminologists demanded that the federal government do a better job of collecting crime statistics. They stated that other countries were using surveys and we should also.
The NCVS is a collection of all crimes beyond business crimes or homicides or those under the age of 12 victimized. Each year, data are obtained from a nationally representative sample of about 240,000 persons in about 150,000 households. Persons are interviewed on the frequency, characteristics, and consequences of criminal victimization in the United States.
Yet today, the data from the NCVS is mostly ignored.
People willingly cite crime data from the FBI that is reported to local and state law enforcement. The problem is that the overwhelming majority of what we call crime is never reported to law enforcement. For example, approximately 80 percent of crimes are property events and, according to the National Crime Victimization Survey, approximately 30 percent of property events are reported to the police. Currently, 45 percent of violent crimes are reported.
And I’m just addressing the tip of the iceberg as to reporting. There are a slew of reports, mostly from the Bureau of Justice Statistics indicating that the overwhelming majority of crimes (i.e., identity theft, shoplifting, porch theft, rapes and sexual assaults, and violence against juveniles) are not reported to law enforcement.
The FBI does not release all the data it has thus there is an automatic undercount in all of their reports. Millions of crimes do not make their way into FBI reports.
We Seem To Exclusively Use Reported Crime Data From The FBI
We know it’s vastly incomplete. We know it’s a tiny snapshot of overall crime. Yet even bad or incomplete data can be useful as long as it’s consistently collected. It can be conducive to establishing trends.
However, the FBI is undergoing a transition in the way it collects data from the previous Summary Reporting System (SRS) that records ONE primary crime to the Incident-Based Reporting System (NIBRS) that collects up to TEN crimes per incident and acquires more qualitative data than the SRS. It’s had problems with the participation of law enforcement agencies which is now mostly resolved.
Because it collects multiple data points and includes more crime per incident, we assume that the quality of the data via the NIBRS will be greatly improved.
Per the latest full report from the FBI, violent crime decreased by three percent. Per the latest full report from the National Incident-Based Reporting System, the rate of violent crime increased by approximately 44 percent in 2022. Considering that violent crime was essentially flat per the Bureau of Justice Statistics, that approximate increase continues for 2023.
Are There Problems Within The National Crime Victimization Survey?
First, I asked two AI sources for problems or issues in the National Crime Victimization Survey. They are listed in the appendix of this article. Interestingly, many listed “problems” or issues focus on underreporting, not overreporting.
Second, the Bureau of Justice Stratistics is currently undergoing a review of their methodology which is standard operating practice of any agency doing national surveys. There have been redesigns in the past. See their website for those reports.
Third, there are no studies from the research community suggesting that we should disregard the findings of the National Crime Victimization Survey. I found one report from the National Library of Medicine stating that rapes or sexual assaults are hard to measure. But it also states that “This basic design is used for a number of general household surveys conducted by the Census Bureau, and it is a good design for an omnibus type survey.”
If we don’t have an issue with the national census, then why do we have an issue with the census-based National Crime Victimization Survey?
Since the first year of NCVS data collection in 1973, the survey has been cited more than 35,000 times in state and federal legislation, in state and federal court cases, in academic literature, and in the media. The NCVS is invaluable to students, lawmakers, policymakers, researchers, victim service providers, advocates, and society as a whole.
A Review Of The Questions Asked In The NCVS-Why It Records More Crime
The questions are action-oriented. They don’t ask if there was a burglary. The NCVS asks if “Anyone Broke in or ATTEMPTED to break into your home by forcing a door or window, pushing past someone, jimmying a lock, cutting a screen, or entering through an open door or window?”
That leads to people reporting more incidents than if you are asked by a police officer if you were the victim of a burglary. You may not know if the signs that your door was attacked (mildly splintered wood) was an attempted burglary.
The NCVS will ask “Were you attacked or threatened OR did you have something stolen from you?” It’s the same concern as the above.
The NCVS will ask “People often don’t think of incidents committed by someone they know. (Other than any incidents already mentioned,) did you have something stolen from you OR were you attacked or threatened by someone at work or school – (b) a neighbor or friend – (c) a relative or family member – (d) any other person you’ve met or known?”
This is the main difference between crimes reported to law enforcement and crimes offered by the National Crime Victimization Survey. Most violent crimes involve someone you know. If you and a friend are in a bar getting drunk and your associate insults your wife and if you push the offender, that’s a violent crime. If you throw a beer bottle, that’s technically an aggravated assault.
Will it be reported to the police? In all probability, no.
The NCVS records events NOT reported to law enforcement. There are endless examples of interpersonal events that are handled privately. Participants do not want the participation of law enforcement.
Decades ago when I was a senior specialist for the US Department of Justice’s clearinghouse, that’s the way it was explained to me by USDOJ researchers and project managers.
One opined that stranger-to-stranger crimes or serious events (i.e., injury) between people who know each other were most likely reported. Then there are crimes where the victim is afraid to report but they will willingly agree to the survey because they are not asked for the identity of the person who attacked them.
Am I suggesting that important crimes (from the perspective of victims) are reported and unimportant crimes are not? It’s an imprecise way of putting it but it has relevance.
Conclusions
Advocates claim they want an evidence-based approach to crime yet they ignore the best available data.
Journalists insist that democracy dies in the darkness but they pay little to no attention to the NCVS.
Is there any wonder why polling data suggests that the media and institutions (especially government) rank at or near the bottom of lists?
It’s interesting that when I quote the NCVS, the pushback is considerable with obvious political overtones. Candidate Biden ran on a platform quoting FBI data. Candidate Trump espoused NCVS numbers and rates.
Regardless, when I took university-based research courses, I was told that it was unethical not to use the best available data. I was taught to look suspiciously at poorly designed research or studies improperly administered.
I have immense respect for FBI data and the coming improvements to their National Incident-Based Reporting System but the title of the FBI’s annual report, “Crime in the United States” is wildly misleading. It’s not an account of crime, it’s a record of reported crime.
We have a golden opportunity to study what happened and why so we can protect the American public. We are dismissing a chance to create better, safer communities by not fully investigating the nation’s largest increase in violent crime.
Privacy Policy
We do not collect your personal information. See our privacy policy at “About This Site.”
See More
See more articles on crime and justice at Crime in America.
Most Dangerous Cities/States/Countries at Most Dangerous Cities.
US Crime Rates at Nationwide Crime Rates.
National Offender Recidivism Rates at Offender Recidivism.
The Crime in America.Net RSS feed (https://crimeinamerica.net/?feed=rss2) provides subscribers with a means to stay informed about the latest news, publications, and other announcements from the site.
Appendix
I Googled and Asked Chat GPT If There Were Any Problems Or Issues With The National Crime Victimization Survey
First, understand that ANY methodology measuring ANYTHING has issues. It’s a basic premise of any survey tool. You could say the same things below about any survey-based endeavor. Nevertheless:
Google:
Underreporting and Recall Issues
Some victims may forget or misreport incidents, especially if they happened months before the survey.
Victims may downplay crimes, particularly minor offenses or those committed by acquaintances.
Sensitive crimes, such as domestic violence or sexual assault, may be underreported due to stigma or fear.
Exclusion of Certain Populations
The NCVS excludes homeless individuals, people in institutions (prisons, nursing homes, military bases), and those in group living situations, meaning it may miss crimes affecting these groups.
It also does not cover crimes against businesses, which leaves out a significant portion of property crime, including shoplifting, fraud, and cybercrime.
Sampling Issues
The NCVS relies on household surveys, meaning its sample may not fully represent the entire U.S. population.
Certain demographics, such as transient or immigrant populations, may be undercounted.
Low response rates in some areas can lead to sampling bias.
Reliability of Self-Reported Data
Unlike police data, the NCVS depends entirely on self-reported experiences. Some people may exaggerate or misinterpret events.
Memory decay: If someone is asked about a crime months after it occurred, they might confuse details or dates.
Limited Coverage of Certain Crimes
Murder is not included in the NCVS because victims cannot report it.
White-collar crimes, cybercrimes, and identity theft are not well covered.
Drug offenses are mostly absent, since they are often victimless or not recognized as a crime by the victim.
Comparison Issues with Other Crime Data
The NCVS often reports higher crime rates than the FBI’s Uniform Crime Reporting (UCR) system because many crimes go unreported to police. This can cause confusion when comparing trends.
Differences in definitions and methodologies between NCVS and police data make it hard to track certain crime trends accurately.
Lag in Data Release
NCVS data takes time to process and release, meaning it may not reflect real-time crime trends.
Policymakers and researchers working with recent crime waves may struggle to use NCVS data effectively.
Despite these challenges, the NCVS is still one of the best tools available for understanding unreported crime and measuring crime trends beyond police reports. However, its findings should be used alongside other sources, like the FBI’s crime data, for a more complete picture of crime in America.