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 in spreadsheet format (.csv) and the full report including tables and graphics in .pdf format are available on BJS website at: http://www.bjs.gov/index.cfm?ty=pbdetail&iid=4821 This report is one in a series. More recent editions may be available. To view a list of all in the series go to http://bjs.gov/index.cfm?ty=pbse&sid=60 --------------------------------------------------------- *************** Bulletin *************** Victims of Identity Theft, 2012 Erika Harrell, Ph.D. and Lynn Langton, Ph.D., BJS Statisticians Approximately 16.6 million persons or 7% of all U.S. residents age 16 or older, were victims of one or more incidents of identity theft on 2012 (figure 1). Among identity theft victims, existing bank (37%) or credit card accounts (40%) were the most common types of misused information. This report uses data from the 2012 Identity Theft Supplement (ITS) to the National Crime Victimization Survey (NCVS). From January to June 2012, the ITS collected data from persons who experienced one or more attempted or successful incidents of identity theft during the 12 months preceding their interview. Identity theft victims are defined as persons age 16 or older who experienced one or more of the following incidents: * unauthorized use or attempted use of an existing account, such as a credit or debit card, checking, savings, telephone, online, or insurance account (referred to as fraud or misuse of an existing account). * unauthorized use or attempted use of personal information to open a new account, such as a credit or debit card, telephone, checking, savings, loan, or mortgage account (referred to as fraud or misuse of a new account). * misuse of personal information for a fraudulent purpose, such as getting medical care, a job, or government benefits; renting an apartment or house; or providing false information to law enforcement when charged with a crime or traffic violation (referred to as fraud or misuse of personal information). **************************************************** *********** Highlights ********** * The purpose of this report is to describe the prevalence of identity theft, its victims, and the characteristics and effects of this crime. The 2012 Identity Theft Supplement (ITS) of the National Crime Victimization Survey (NCVS) provided the data for this report. * About 7% of persons age 16 or older were victims of identity theft in 2012. * The majority of identity theft incidents (85%) involved the fraudulent use of existing account information, such as credit card or bank account information. * Victims who had personal information used to open a new account or for other fraudulent purposes were more likely than victims of existing account fraud to experience financial, credit, and relationship problems and severe emotional distress. * About 14% of identity theft victims experienced out-of- pocket losses of $1 or more. Of these victims, about half suffered losses of less than $100. * Over half of identity theft victims who were able to resolve any associated problems did so in a day or less. * About 36% of identity theft victims reported moderate or severe emotional distress as a result of the incident. * Direct and indirect losses from identity theft totaled $24.7 billion in 2012. * Fourteen percent of persons age 16 or older have experienced identity theft during their lives. ******************************************************** This report details the number, percentage, and demographic characteristics of victims who reported one or more incidents of identity theft during a 12-month period. It focuses on the most recent incident experienced to describe victim characteristics and victim responses to identity theft. It describes how the victim discovered the crime; financial losses and other consequences of identity theft, including the amount of time victims spent resolving associated problems; reporting of the incident to credit card companies, credit bureaus, and law enforcement agencies; and the level of distress identity theft victims experienced. ********************************************* For 85% of identity theft victims, the most recent incident involved he unauthorized use of an existing account ********************************************* In 2012, the unauthorized misuse or attempted misuse of an existing account was the most common type of identity theft, experienced by 15.3 million persons age 16 or older (6% of all persons) (table 1). The majority of victims experienced the fraudulent use of their credit cards (7.7 million or 3% of all persons) or bank accounts (7.5 million or 3% of all persons). Another 1.7 million victims (0.7% of all persons) experienced other types of existing account theft, such as misuse or attempted misuse of an existing telephone, online, or insurance account. An estimated 1.1 million victims (less than 1% of all persons) reported the fraudulent misuse of their information to open a new account, such as a credit card. Another 833,600 victims reported the misuse of their personal information for other fraudulent purposes. During the most recent identity theft incident in 2012, 8% of 1.2 million victims experienced multiple types of identity theft during a single incident. For 66% of victims of multiple types of identity theft, the incident involved the unauthorized use of a combination of existing accounts, such as credit card, checking, savings, telephone, or online accounts. The remaining 34% who experienced multiple types of identity theft during a single incident (less than 3% of all victims) reported some combination of misuse of an existing account, misuse of personal information to open a new account, and personal information used for other fraudulent purposes. ********************************************* Persons in households with higher annual incomes were more likely to experience identity theft than persons in lower-income households ********************************************* A similar percentage of males and females (7%) experienced identity theft in 2012 (table 2). Across all types of identity theft, prevalence rates did not vary significantly by sex. After accounting for whether a person owned a credit card and bank account, prevalence rates for existing credit card and existing banking account misuse did not vary by sex. Persons ages 16 to 17 (less than 1%) were the least likely to experience identity theft, followed by persons ages 18 to 24 (5%) and 65 or older (5%). After accounting for credit card ownership, persons ages 16 to 24 were the least likely to experience the misuse of an existing account, while persons age 65 or older had a similar prevalence rate as persons ages 25 to 34. Among those who had a bank account, persons ages 16 to 17 and 65 or older were the least likely to experience banking account fraud. A greater percentage of white non-Hispanics (7%) experienced identity theft in 2012 than black non-Hispanics (5%) and Hispanics (5%). This relationship also held true for the misuse of an existing credit card account among persons who had a credit card. However, among persons who had a bank account, there were no significant differences in the prevalence of bank account misuse among whites, blacks, and Hispanics. Overall, persons in the highest income category (those with an annual household income of $75,000 or more) had a higher prevalence of identity theft than persons in other income brackets. After accounting for credit card ownership, persons in the highest income bracket had the highest rate of existing credit card account misuse. Among persons who had a bank account, there were no significant differences in the prevalence of identity theft across income categories, with the exception of the unknown category. ********************************************* The most common way victims discovered the identity theft was from contact by a financial institution about a problem ********************************************* The way victims discovered that their identifying information was misused varied by the type of identity theft. Among victims who experienced the unauthorized use of an existing account, 45% discovered the identity theft when a financial institution contacted them about suspicious activity on their account (figure 2). In comparison, 15% of victims who experienced the misuse of personal information to open a new account or for other fraudulent purposes discovered the incident when a financial institution contacted them. Victims of these other types of identity theft were more likely than victims of existing account misuse to discover the incident when another type of company or agency contacted them (21%) or after they received an unpaid bill (13%). Twenty percent of victims of existing account misuse discovered the incident because of fraudulent charges on their account, compared to 8% of victims of other types of identity theft. ********************************************* The majority of identity theft victims did not know how the offender obtained their information ********************************************* About 32% of identity theft victims knew how the offender obtained their information (figure 3). Victims who experienced multiple types of identity theft during a single incident (47%) were among the most likely victims to know how the offender obtained the information. Victims who had an existing credit card account misused (24%) were among the least likely to know how the offender obtained the account information. Of the 5.3 million victims who knew how the identity theft occurred, the most common way offenders obtained information (43%) was to steal it during a purchase or other transaction (not shown). ********************************************* 9 in 10 identity theft victims did not know anything about the offender ********************************************* Overall, most identity theft victims (91%) in 2012 did not know anything about the identity of the offender (table 3). However, the percentage of victims who knew something about offender varied depending on the type of identity theft. Victims who had personal information used to open a new account (25%) or for other fraudulent purposes (23%) were more likely than victims of existing account misuse (7%) to know something about the offender. Across all types of identity theft, victims who experienced the misuse of an existing credit card (3%) were the least likely to know something about the offender. ********************************************* Two-thirds of identity theft victims reported a direct financial loss ********************************************* The economic impact of identity theft is comprised of direct and indirect financial loss. Direct financial loss, the majority of the total loss associated with identity theft, refers to the monetary amount the offender obtained from misusing the victim’s account or personal information, including the estimated value of goods, services, or cash obtained. Indirect loss includes any other costs caused by the identity theft, such as legal fees, bounced checks, and other miscellaneous expenses (e.g., postage, phone calls, or notary fees). In 2012, 68% of identity theft victims reported a combined direct and indirect financial loss associated with the most recent incident (appendix table 8). Overall, victims who experienced a direct and indirect financial loss of at least $1 lost an average of $1,769 with a median loss of $300. The amount of financial loss varied by the type of identity theft. Approximately 69% of credit card fraud, 74% of bank fraud, 46% of new account fraud, and 38% of personal information fraud victims experienced a financial loss during the past 12 months. Of those victims who experienced multiple types of identity theft, 69% reported a financial loss. In 2012, 66% of the 16.6 million victims of identity theft reported a direct financial loss as a result of the identity theft incident. About 68% of credit card fraud victims, 74% of bank fraud victims, 42% of new account fraud victims, and 32% of personal information fraud victims reported that the offender obtained money, goods, or services. Of those victims who experienced multiple types of identity theft, 67% reported a direct financial loss associated with the incident. Of those who reported a direct financial loss, victims who experienced the misuse of their personal information reported a mean direct loss of $9,650 and a median direct loss of $1,900. Victims of new account fraud incurred an average loss per incident of $7,135 and a median loss of $600. Victims of multiple types of fraud reported an average direct loss of $2,140 with a median direct loss of $400, while victims of existing account misuse had an average loss of $1,003 per incident with a median direct loss of $200. In addition to any direct financial loss, 6% of all identity theft victims reported indirect losses associated with the most recent incident of identity theft. Victims who suffered an indirect loss of at least $1 reported an average indirect loss of $4,168, with a median of $30. With the exception of victims of personal information fraud, identity theft victims who reported indirect financial loss had a median indirect loss of $100 or less. ********************************************* Direct and indirect identity theft losses totaled $24.7 billion in 2012 ********************************************* Identity theft victims reported a total of $24.7 billion in direct and indirect losses attributed to all incidents of identity theft experienced in 2012 (table 4).***Footnote 2 2For victims who experienced multiple incidents of identity theft, the total includes losses from all incidents experienced during the past 12 months.*** These losses exceeded the $14 billion victims lost from all other property crimes (burglary, motor vehicle theft, and theft) measured by the National Crime Victimization Survey in 2012. Identity theft losses were over 4 times greater than losses due to stolen money and property in burglaries ($5.2 billion) and theft ($5.7 billion), and eight times the total losses associated with motor vehicle theft ($3.1 billion). ********************************************* In 2012, 14% of identity theft victims suffered an out-of-pocket financial loss ********************************************* In some instances, a company (e.g., credit card or insurance company) may reimburse some or all of the financial loss, reducing or eliminating the out-of-pocket losses for victims. At the time of the interview, 14% of victims of identity theft had experienced personal out-of-pocket financial losses of $1 or more. Of these victims who suffered an out-of-pocket financial loss, 49% had total losses of $99 or less (figure 4). About 18% of victims reported out-of-pocket expenses of $100 to $249. An additional 16% of identity theft victims reported that out- of-pocket expenses of $1,000 or more. ********************************************* Victims of identity theft who experienced existing account misuse were the least likely to have credit-related problems ********************************************* In addition to suffering monetary losses, some identity theft victims experienced other financial and legal problems. They paid higher interest rates on credit cards, they were turned down for loans or other credit, their utilities were turned off, or they were the subject of criminal proceedings. Victims who experienced the misuse of an existing account were generally less likely to experience financial and legal problems as a result of the incident than victims who had other personal information misused. In 2012, 2% of victims of existing account misuse experienced problems with debt collectors, compared to 17% of victims who had personal information misused (figure 5). Two percent of victims of existing account misuse experienced credit- related problems (e.g., higher interest rates or repeatedly having to correct information on a credit report), compared to 12% of victims of other types of identity theft. Less than 1% of victims of existing account misuse and 3% of victims of other types of identity theft had utilities cut off or service denied, legal problems (e.g., being arrested), or other problems (e.g., income tax issues). ********************************************* Identity theft victims were less likely than violent crime victims to have significant school, work, or relationship problems as a result of the crime ********************************************* The 2012 NCVS asked victims of violent crime (including rape or sexual assault, robbery, aggravated assault, and simple assault) about the impact of the victimization on work, school, and personal relationships, and the amount of emotional distress it caused. Compared to violent crime victims surveyed in 2012, a lower percentage of identity theft victims reported significant problems at work or school or with family members or friends due to the incident (figure 6). About 1% of identity theft victims reported significant problems at work or school, compared to 12% of violent crime victims. Similarly, 4% of identity theft victims reported significant problems with family members or friends, compared to 19% of violent crime victims. The percentage of identity theft victims who reported significant problems at work or school as a result of the incident varied by type of identity theft. About 6% of victims who had personal information used to open a new account reported significant problems at work or school, compared to about 1% of victims of existing credit card and bank account misuse (appendix table 11). The largest percentage of identity theft victims who had significant problems with family or friends had their personal information used to create new accounts (10%) or for other fraudulent purposes (10%). Identity theft victims (10%) were also less likely than violent crime victims (27%) to report that the victimization was severely distressing (figure 7). However, the level of emotional distress varied by type of identity theft. Thirty- two percent of victims of personal information fraud reported that they found the incident severely distressing, compared to 5% of credit card fraud victims. Twenty-two percent of victims of new account fraud reported that the crime was severely distressing. ********************************************* The majority of identity theft victims spent a day or less resolving associated financial and credit problems ********************************************* At the time of the interview, 86% of identity theft victims had resolved any problems associated with the incident (appendix table 13). Of these, the majority spent a day or less clearing up the problems, while about 10% spent more than a month (figure 8). Victims of the misuse of existing accounts (54%) were more likely to resolve any associated financial and credit problems within a day, compared to victims of new account fraud (42%) and victims of multiple types of identity theft (36%). Among victims who had resolved all problems associated with the identity theft, 29% who experienced the misuse of personal information for fraudulent purposes spent over a month clearing up the problems, compared to 9% of victims of existing account misuse. Whether identity theft victims had resolved associated problems or not at the time of the interview, victims reported spending an average of about 9 hours clearing up the issues. Victims of existing credit card account misuse spent an average of 3 hours resolving problems, while victims whose personal information was used to open a new account or for other fraudulent purposes spent an average of about 30 hours resolving all problems (not shown). ********************************************* 14% of persons experienced identity theft at some point during their lives ********************************************* Resolving the problems caused by identity theft may take more than a year for some victims. Of the 20.3 million persons age 16 or older who experienced the misuse of existing accounts or other personal information prior to 2012, 7% were still resolving the problems associated with the identity theft more than a year later (table 5). A greater percentage of persons who experienced the misuse of personal information to open a new account (16%) or for other fraudulent purposes (15%) prior to 2012 had unresolved problems more than a year later, compared to persons who experienced existing account misuse (4%). Overall, 14% of persons age 16 or older, or 34.2 million persons, experienced one or more incidents of identity theft during their lives. The lifetime prevalence rate for identity theft varied to some degree with age. Younger persons, ages 16 to 17 (1%) and 18 to 24 (7%) and persons ages 65 or older (11%) had the lowest lifetime prevalence rates, while between 15% and 17% of persons ages 25 to 64 experienced identity theft at some point in their lives (not shown in table). ********************************************* The level of emotional distress victims experienced was related to the length of time they spent resolving problems ********************************************* Victims who spent more time resolving the financial and credit-related problems associated with the identity theft incident were more likely to experience problems with work and other relationships and severe emotional distress than victims who were able to resolve the problems relatively quickly. Among identity theft victims who spent 6 months or more resolving financial and credit problems due to the theft, 47% experienced severe emotional distress (figure 9). In comparison, 4% of victims who spent a day or less clearing up problems reported that the incident was severely distressing. Similarly, 14% of victims who spent 6 months or more resolving issues related to the identity theft reported having significant problems with family members or friends, compared to about 2% of victims who spent a day or less resolving problems. ********************************************* Fewer than 1 in 10 identity theft victims reported the incident to police ********************************************* In 2012, about 9% of identity theft victims reported the incident to police (figure 10). Victims of personal information fraud were the most likely to report the incident to police (40%), followed new account fraud victims (23%) and victims of multiple types of identity theft (22%). Fewer than 10% of victims of existing credit card (4%), existing bank account (9%), and other existing account misuse (6%) reported the incident to police. The 91% of identity theft victims who did not report an incident to police offered a variety of reasons for not reporting (appendix table 17). Among all victims who did not report the incident to police, the most common reason was that the victim handled it another way (58%). About a third (29%) of nonreporting victims did not contact police because they suffered no monetary loss. One in five nonreporting victims did not think that the police could help and another 15% did not know how to report the incident to law enforcement. ********************************************* Of the 9% of identity theft victims who contacted a credit bureau, 7 in 10 placed a fraud alert on their credit report ********************************************* In 2012, 88% of all victims of identity theft reported the incident to one or more nonlaw enforcement agencies, either government or commercial (not shown). About 86% of identity theft victims contacted a credit card company or bank to report misuse or attempted misuse of an account or personal information (appendix table 19). Six percent of all identity theft victims contacted a credit monitoring service, 3% contacted an agency that issues identity documentation, (e.g., Social Security Administration or an agency that issues drivers’ licenses), 1% contacted the Federal Trade Commission, and 1% contacted a government consumer affairs agency or other consumer protection organization, (e.g., Better Business Bureau). Nine percent of identity theft victims contacted a credit bureau to report the incident. Victims whose identifying information was fraudulently used to open a new account (30%) were most likely to contact a credit bureau, followed by victims of multiple types of theft (20%) and victims whose personal information was used for other fraudulent purposes (19%). Victims of any type of identity theft who contacted a credit bureau could take several different actions. About 70% of victims who contacted a credit bureau placed a fraud alert on their credit report (figure 11). Two-thirds (66%) of victims who contacted a credit bureau requested a credit report, 41% requested corrections to their credit report, 38% placed a freeze on their credit report, and 19% provided a police report to the credit bureau. ********************************************* About 85% of persons took some action to prevent identity theft victimization ********************************************* The ITS asked persons about actions they took during the prior 12 months to prevent identity theft, such as checking credit reports, shredding documents with personal information, and changing passwords on financial accounts. In 2012, 85% of persons engaged in one or more of the preventative actions asked about in the survey (table 6). A greater percentage of victims (96%) than nonvictims (84%) engaged in at least one preventative action. However, about 12% of victims who took preventative action did so in response to experiencing identity theft in the past year. Overall, the two most common preventative actions in 2012 were checking bank or credit statements (75%) and shredding or destroying documents with personal information (67%). A higher percentage of victims than nonvictims engaged in both of these preventative actions. However, about 13% of victims began shredding or destroying documents with personal information as a result of experiencing identity theft during the prior 12 months and 26% began checking bank or credit statements as a result of the victimization. Less than 10% of victims purchased identity theft protection (4%) or insurance (6%) or used an identity theft security program on the computer (6%) after experiencing identity theft, while about a quarter of victims checked financial accounts or changed passwords on these accounts as a result of the victimization. Among persons who did not experience identity theft in 2012, 37% checked their credit report; 27% changed passwords on financial accounts; 16% used identity theft security programs on their computer; 5% purchased identity theft insurance or used a credit monitoring service; and 3% purchased identity theft protection. ************** Methodology ************** Data collection ***************** The Identity Theft Supplement (ITS) was administered as a supplement to the Bureau of Justice Statistic’s (BJS) National Crime Victimization Survey (NCVS). The NCVS collects data on crime reported and not reported to the police against persons age 12 or older from a nationally representative sample of U.S. households. 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 the homeless. (For more information, see the Survey Methodology in Criminal Victimization in the United States, 2008, NCJ 231173, BJS website, May 2011.) From January 1, 2012, through June 30, 2012, persons age 16 or older in sampled NCVS households received the ITS at the end of the NCVS interview. Proxy responders and those who complete the NCVS interview in a language other than English did not receive the ITS. All NCVS and ITS interviews were conducted in a computer-assisted personal interviewing (CAPI) environment. Interviews were conducted by telephone or by personal visit. A final sample size of 69,814 of the original NCVS-eligible respondents completed the ITS questionnaire, resulting in a response rate of 91.9%. The combined overall NCVS-ITS unit response rate for NCVS households, NCVS persons, and ITS persons was 68.2%. Because of the level of nonresponse, a bias analysis was conducted. To the extent that those who responded to the survey and those who did not differ in important ways, there is potential for bias in estimates from the survey data. However, the result of the nonresponse bias analysis suggested that there was little or no bias of substantive importance due to nonresponse in the ITS estimates. The ITS collected individual data on the prevalence of and victim response to the attempted or successful misuse of an existing account, misuse of personal information to open a new account, or misuse of personal information for other fraudulent purposes. Respondents were asked whether they experienced any of these types of misuse during the 12 months prior to the interview. For example, persons interviewed in July 2012 were asked about identity theft incidents that occurred between July 2011 and June 2012. To simplify the discussion of the findings, this report refers to all identity theft experienced during the 12 months prior to the interviews as occurring in 2012. Persons who reported one or more incidents of identity theft during 2012 were asked more detailed questions about the incident and response to the incident, such as how they discovered the identity theft; financial, credit, and other problems resulting from the incident; time spent resolving associated problems; and reporting to police and credit bureaus. For most sections of the survey instrument, the ITS asked victims who experienced more than one incident during the 12-month reference period to describe only the most recent incident when answering questions. The ITS asked victims who experienced multiple incidents of identity theft during the year to report on the total financial losses suffered as a result of all incidents. The ITS asked both victims and nonvictims a series of questions about identity theft they experienced outside of the 12-month reference period and about measures they took to avoid or minimize the risk of becoming an identity theft victim. Comparison of 2012 findings to prior BJS identity theft statistics ********************************************* This report uses data that differ from previous BJS statistical collections on the topic of identity theft. Due to the differences, it was not possible to compare the identity theft estimates presented in this report to previously reported estimates. Initial BJS reports on identity theft used household-level data from the core NCVS. Data were reported for the household as a whole rather than for individual respondents, and the questions were more limited, providing less detail on the characteristics of the incident and the victim response. For additional information, see Identity Theft, 2005, NCJ 219411, BJS website, November 2007, Identity Theft Reported by Households, 2007 - Statistical Tables, NCJ 230742, BJS website, June 2010, and Identity Theft Reported by Households, 2005 - 2010, NCJ 231680, BJS website, December 2010. In 2008, BJS conducted the first Identity Theft Supplement to the NCVS. Like the 2012 ITS, the 2008 ITS collected detailed information on victim experiences with identity theft from persons age 16 or older. For more information, see Victims of Identity Theft, 2008, NCJ 231680, BJS website, December 2010. Following the administration of the first ITS, BJS made substantial changes to the survey instrument, making it difficult to compare across the 2008 and 2012 datasets. Some of the major changes to the survey from 2008 to 2012 included— * Changing from a 2-year to 1-year reference period. The 2008 ITS asked about identity theft experienced in the 2 years prior to the interview. The 2-year reference period was intended to capture incidents of identity theft that were discovered more than 12 months prior to the interview but were still causing problems for the victim. The 2012 ITS used a 12-month reference period to be more consistent with the NCVS and other NCVS supplements. The 2012 ITS added a special section about identity theft experienced outside of the 1-year reference period to capture identity theft incidents with long-term consequences. * Integrating of successful and attempted identity theft incidents. The 2008 ITS tried to distinguish attempted identity theft from successfully completed identity theft. It asked slightly different questions depending on whether respondents screened into the attempted or successful module. However, the distinction between an attempted and successful incident of identity theft was not clear, and the two types were combined for reporting purposes to the extent possible. The 2012 ITS defined identity theft as attempted or completed misuse of personal information and collected the same information from all victims. * Focusing on the most recent incident of identity theft for detailed follow-up questions. In the 2008 ITS, victims were asked one set of questions about the characteristics of identity theft and the response to identity theft, regardless of the number of incidents they experienced during the 2-year reference period. This made it impossible to attribute the incident characteristics or monetary loss to one specific type of identity theft. The 2012 ITS asked victims to identify whether they experienced one or more than one incidents of identity theft during the year. ***Footnote 3 Victims received the following definition of an identity theft incident: “An incident of identity theft occurs when your identity is stolen. A stolen credit card or debit card may be used multiple times, but this should be considered a single incident."*** Victims who experienced more than one incident were asked to describe only the most recent incident when responding to detailed questions about the nature of and experiences with identity theft victimization. Possible over-reporting of losses from jointly held accounts ********************************************* Persons may have experienced the unauthorized use of a jointly held account. Joint accounts present a difficulty with counting financial harm or loss because of the potential for double-counting loss (e.g., both account holders report the same $500 loss). Because financial loss was not attributed to a particular type of identity theft, victims of multiple types of identity theft may have experienced some financial loss from a joint account and some financial loss from an independently held account. Therefore, it was not possible to correct for any potential over-reporting due to joint account holders who may have been double counted. Standard error computations ***************************** When national estimates are derived from a sample, as is the case with the ITS, caution must be taken when comparing one estimate to another. 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, the 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. In order to generate standard errors around estimates from the ITS, the 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 (i.e., numbers or percentages) in the report. In this report, BJS conducted tests to determine whether differences in estimated numbers and percentages 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 used was Student’s t-statistic, which tests the difference between two sample estimates. To ensure that the observed differences between estimates were larger than might be expected due to sampling variation, the significance level was set at the 95% confidence level. 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 ITS, in 2012, an estimated 6.7% of persons age 16 or older experienced identity theft (see table 1). Using the GVFs, BJS determined that the estimate has a standard error of 0.3 (see appendix table 1). A confidence interval around the estimate was generated by multiplying the standard errors 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 estimate is 6.7 ± (0.3 X 1.96) or 6.1 to 7.3. In other words, if different samples using the same procedures were taken from the U.S. population in 2012, 95% of the time the percentage of persons who experienced identity theft would be between 6.1% and 7.3%. In this report, BJS also calculated a coefficient of variation (CV) for all estimates, representing the ratio of the standard error to the estimate. CVs provide a measure of reliability and a means to compare 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 is based on 10 or fewer sample cases, or the coefficient of variation exceeds 50%). Many of the variables examined in this report may be related to one another and to other variables not included in the analyses. Complex relationships among variables were not fully explored in this report and warrant more extensive analysis. Readers are cautioned not to draw causal inferences based on the results presented. **************************************************** The Bureau of Justice Statistics, located in the Office of Justice Programs, U.S. Department of Justice, collects, analyses, and disseminates statistical information on crime, criminal offenders, victims of crime, and the operation of justice systems at all levels of government. William J. Sabol is acting director. This report was written by Erika Harrell, Ph.D. and Lynn Langton, Ph.D. Shannan Catalano, Ph.D. verified the report. Vanessa Curto and Jill Thomas edited the report, and Barbara Quinn produced the report. December 2013, NCJ 243779 **************************************************** **************************************************** Office of Justice Programs Innovation * Partnerships * Safer Neighborhoods www.ojp.usdoj.gov **************************************************** ********************* 11/21/13 JER 2:49pm revision *********************