Survey of Gun Owners in the United States, 1996 (ICPSR 2750)

Time Period(s) View help for Time Period(s)

Date of Collection View help for Date of Collection

Data Collection Notes View help for Data Collection Notes

Hide

Study Purpose View help for Study Purpose

Data regarding the incidence and characteristics of weapons-related events can be valuable in assessing the costs and benefits of private gun ownership. The majority of previous research had focused primarily on gun ownership. Very few studies covered a national population, distinguished civilian use from military or police use, or distinguished gun use against humans from that against animals. This study sought to report on the characteristics of gun ownership, gun-carrying practices, and weapons-related incidents -- specifically, gun use and other weapons used in self-defense against humans and animals. In addition, the study also focused on how the respondents described the weapons-related events.

Study Design View help for Study Design

Data for Parts 1 and 2 were gathered using a national random-digit-dial telephone survey. The sample was comprised of randomly-selected adults aged 18 and older living in randomly-selected households in the 50 United States. First, draft versions of the questionnaire were pilot-tested on an unspecified group to help ensure that the final questionnaire would be comprehensive and free of any contextual bias. The responses from the pilot tests were analyzed, and the final questionnaire incorporated adjustments indicated by the pilot tests. The pilot test interviews were not included in the final survey sample. To start the interview, six qualifying questions were asked, dealing with (1) gun ownership, (2) gun-carrying practices, (3) gun display against the respondent, (4) gun use in self-defense against animals, (5) gun use in self-defense against people, and (6) other weapons used in self-defense. A "yes" response to a qualifying question led to a series of additional questions on the same topic as the qualifying question. The interviews, lasting between 5 and 20 minutes, were completed between May 28 and July 2, 1996. No more than one adult from each household was interviewed. The sample was designed to be a representative sample of households, not of individuals. Rather than interview the adult who answered the phone or who happened to be home at the time of the call, the study was designed to select a household adult chosen at random. In practice, this meant researchers alternately asked to speak with a man or with a woman living in the household. If there was no person of the requested gender living in the household, the initial respondent was interviewed. Once a telephone number had been randomly selected for inclusion in the survey sample, as many as ten repeat phone calls were made until a final disposition was assigned. Respondents were guaranteed anonymity, and no identifying information was collected. As with many telephone surveys, the data may be subject to various response-related biases, including telescoping and self-presentation bias. Coupled with the rarity of some of the reported events (e.g., self-defense gun use), the principal investigators note that population-based estimates generated from these data should be viewed cautiously.

Sample View help for Sample

Stratified random sampling.

Universe View help for Universe

All households in the United States.

Unit(s) of Observation View help for Unit(s) of Observation

Data Source View help for Data Source

Data Type(s) View help for Data Type(s)

Description of Variables View help for Description of Variables

Information collected for Part 1 covers how many firearms were owned by household members, types of firearms owned (handguns, revolvers, pistols, fully automatic weapons, and assault weapons), whether the respondent personally owned a gun, reasons for owning a gun, type of gun carried, whether the gun was ever kept loaded, kept concealed, used for personal protection, or used for work, and whether the respondent had a permit to carry the gun. Additional questions focused on incidents in which a gun was displayed in a hostile manner against the respondent, including the number of times such an incident took place, the location of the event in which the gun was displayed against the respondent, whether the police were contacted, whether the individual displaying the gun was known to the respondent, whether the incident was a burglary, robbery, or other planned assault, and the number of shots fired during the incident. Variables concerning gun use by the respondent in self-defense against an animal include the number of times the respondent used a gun in this manner and whether the respondent was hunting at the time of the incident. Other variables in Part 1 deal with gun use in self-defense against people, such as the location of the event, if the other individual knew the respondent had a gun, the type of gun used, any injuries to the respondent or to the individual that required medical attention or hospitalization, whether the incident was reported to the police, whether there were any arrests, whether other weapons were used in self-defense, the type of other weapon used, location of the incident in which the other weapon was used, and whether the respondent was working as a police officer or security guard or was in the military at the time of the event. Demographic variables in Part 1 include the gender, race, age, household income, and type of community (city, suburb, or rural) in which the respondent lived. Open-ended questions asked during the interview comprise the variables in Part 2. Responses include descriptions of where the respondent was when he or she displayed a gun (in self-defense or otherwise), specific reasons why the respondent displayed a gun, how the other individual reacted when the respondent displayed the gun, how the individual knew the respondent had a gun, whether the police were contacted for specific self-defense events, and if not, why not.

Response Rates View help for Response Rates

Of the households randomly selected for the survey, 27 percent refused to participate. Once the interviews began, less than 2 percent did not complete the entire survey.

Presence of Common Scales View help for Presence of Common Scales

Several Likert-type scales were used.

Hide

Original Release Date View help for Original Release Date

2000-12-04

Version History View help for Version History

Hide