Data were obtained by mailed questionnaires and web form reporting. The ASJ collection began in February of 2017, and ended in July of the same year.
BJS has consistently maintained high survey and item response rates. In an effort to minimize respondent burden and maximize response, the data collection plan allows for the jail respondents to submit data by mailing their reply in a postage-paid envelope or by fax, in addition to the internet-based reporting system (which BJS implemented and redesigned in 2011).
To maximize the accuracy of survey, at the direction of BJS, data collection staff conduct out-of-range analysis of critical items and use the results from this analysis to prioritize follow-up contacts. Follow-up telephone calls and emails to non respondents are used to encourage high response rates. These methods have proved effective in reaching a 97% response rate while minimizing missing data.
In years between the complete census of local jails, the
Bureau of Justice Statistics (BJS) conducts the Annual Survey of Jails (ASJ). ASJ uses a stratified probability sample of jail jurisdictions to estimate the number and characteristics of local inmates nationwide. The 2016 ASJ sample consisted of 846 jail jurisdictions, represented by 902 jail facilities (referred to as reporting units). This sample represents 2,871 jail jurisdictions nationwide. Local jail jurisdictions include counties (parishes in Louisiana) or municipal governments that administer one or more local jails.
The 2016 ASJ differs from the 2006-2012 ASJ's, as data after 2012 includes in the sample a probability of all California jail jurisdictions in response to the two enacted laws -- AB 109 and AB 117 by the California State Legislature and governor -- to reduce the number of inmates housed in state prisons starting October 1, 2011.
Since the enactment of the two laws in recent years, the California jail population has experienced changes in size that cannot be compared to the changes of any other state in the United States. For this reason, the California jail jurisdictions were put in separate strata so that they could represent only California jurisdictions.
In the sampling design, the jail jurisdictions nationwide were grouped into 10 strata. The 10 strata were defined by the interaction of two variables: the jail jurisdiction average daily population (ADP) in 2005, and whether in 2005 the jurisdiction held at least one juvenile. For 8 of the 10 strata, a random sample of jail jurisdictions was selected. For the remaining two strata, all jurisdictions were included in the sample. One stratum consisted of all jails that were operated jointly by two or more jurisdictions (referred to as multi-jurisdictional jails). The other stratum (referred to as certainty stratum consisted of all jail jurisdictions that:
- held juvenile inmates at the time of the 2005 Census of Jail Inmates and had an average daily
population (ADP) of 500 or more inmates during the 12 months ending June 30, 2005.
- held only adult inmates and had an ADP of 750 or more.
Certainty jails jurisdiction in the survey received forms CJ-9A/5 (Certainty Jurisdictions-Central data reporter) or CJ-10A/5 (Multi-Jurisdiction facilities and privately operated facilities in jurisdictions included with certainty in the Annual Survey of Jails).
Cross-sectional
All active jail jurisdictions (i.e., counties, municipalities, boroughs, etc.) in the United States as of December 31, 2016, excluding jails in Indian countries.
jail facilities
Item response rates ranged from 94% to 100%.