Law Enforcement Management and Administrative Statistics (LEMAS), 2020 (ICPSR 38651)

Version Date: Mar 7, 2023 View help for published

Principal Investigator(s): View help for Principal Investigator(s)
United States Department of Justice. Office of Justice Programs. Bureau of Justice Statistics

Series:

https://doi.org/10.3886/ICPSR38651.v1

Version V1

Slide tabs to view more

LEMAS 2020

The Law Enforcement Management and Administrative Statistics (LEMAS) survey collects data from a nationally representative sample of general-purpose agencies (i.e., local and county police departments, sheriffs' offices, and primary state police agencies). The 2020 LEMAS sample design called for the survey questionnaire to be sent to 3,499 general purpose law enforcement agencies, including 2,631 local and county police departments, 819 sheriffs' offices, and the 49 primary state police departments (Hawaii does not have a primary state police agency). The design called for all agencies employing 100 or more full-time equivalent sworn personnel to be included with certainty (self-representing), and for smaller agencies to be sampled from strata based on number of full-time equivalent sworn officers and type of agency. A total of 37 local police departments were determined to be out-of-scope for the survey because they had closed, had less than one full-time equivalent sworn officer, had contracted out their services with another law enforcement agency, or only had special enforcement responsibilities. The final mail out total of 3,462 agencies included 2,611 local police departments, 802 sheriffs' offices, and the 49 state agencies.

United States Department of Justice. Office of Justice Programs. Bureau of Justice Statistics. Law Enforcement Management and Administrative Statistics (LEMAS), 2020. Inter-university Consortium for Political and Social Research [distributor], 2023-03-07. https://doi.org/10.3886/ICPSR38651.v1

Export Citation:

  • RIS (generic format for RefWorks, EndNote, etc.)
  • EndNote
United States Department of Justice. Office of Justice Programs. Bureau of Justice Statistics

city

Inter-university Consortium for Political and Social Research
Hide

2020
2020
  1. Actions to minimize losses:

    For six local police departments that did not report the number of full-time sworn officers in the 2020 LEMAS survey, the number of full-time sworn officers they reported in the 2018 CSLLEA was used.

    Multiple responses for overall operating budget were out of the expected range and edited using data acquired from public sources. Cases were examined if the ratio of operating budget and FTE sworn officers count was less than $35,000 per officer or greater than $400,000 per officer. These thresholds represented natural breaks in outlier ratio values covering approximately 10% of responding agencies. Also included in this review were agencies that either did not provide or were missing budget information in their 2020 LEMAS response, as their ratio would be less than $35,000 per officer. The thresholds resulted in 299 agencies being reviewed. Public sources used to edit the budget data for 140 general-purpose agencies included agency and government budgets reported on public websites and prior survey data (from the 2016 LEMAS survey and 2018 CSLLEA). No other variables were edited or imputed.

  2. Estimates of sampling error:

    The accuracy of the estimates presented in the accompanying BJS reports (Local Police Departments Personnel, 2020 and Sheriffs' Offices Personnel, 2020) depends on two types of error: sampling and nonsampling error. Sampling error is the variation that may occur by chance due to the collection of a sample rather than a complete enumeration of all agencies. Nonsampling error can be attributed to many sources, such as the inability to obtain information about all cases in the sample, the inability to obtain complete and correct information from the administrative records, and processing errors. The full extent of the nonsampling error is difficult to measure in any survey.

    Standard error is an important and minimum baseline indicator of the quality of estimates. Standard error is driven primarily by sample size. Variance and standard error estimates for the 2020 LEMAS survey were generated using the IBM SPSS statistical software package. The Taylor linearization method for a "stratified without replacement" design was used for these calculations. (See the appendix tables in the accompanying reports for estimates of standard errors.)

    Standard error estimates may be used to construct confidence intervals around the percentages in the accompanying reports. For example, the 95% confidence interval around the percentage of local police departments with bilingual or multilingual staff was 43.3% ± 1.96 ∗ 0.98% (or approximately 41.4% to 45.2%).

    Standard error estimates may also be used to construct confidence intervals around numerical variables such as personnel counts. For example, the 95% confidence interval around the number of full-time sworn officers was approximately 708,153 ± 1.96 ∗ 17,417 (or 674,017 to 742,290).

    BJS conducted statistical significance testing based on the Student's t-statistic. A difference between two estimates is statistically significant if it exceeds a threshold. The threshold is based on the range of differences BJS would expect based on sampling error. All comparisons stated in the accompanying BJS reports reflect a statistically significant result. BJS encourages readers to exercise caution when carrying out statistical significance testing not included in the BJS reports.

Hide

The sample for the 2020 LEMAS survey was derived from the Law Enforcement Agency Roster (LEAR) database, a list of all publicly funded law enforcement agencies operating in the United States. The LEAR is compiled from a variety of sources, including the 2008, 2014, and 2018 Census of State and Local Law Enforcement Agencies (CSLLEA), in addition to the 2013 and 2016 LEMAS surveys. The LEAR undergoes periodic updates to capture newly created agencies and to remove closed agencies and agencies that are no longer in scope.

The full 2020 LEMAS sample included 3,499 state and local law enforcement agencies. The sample represented all general-purpose state and local law enforcement agencies in the United States with the equivalent of at least one full-time sworn officer, with separate samples drawn for local police departments and sheriffs' offices. General-purpose law enforcement agencies include municipal, county, and regional police departments; most sheriffs' offices; and primary state and highway patrol agencies. They are distinct from special-purpose agencies, sheriffs' offices with jail and court duties only, and federal law enforcement agencies. Full-time sworn officers are those with general arrest powers. Employees who are regularly scheduled to work 35 or more hours per week are considered full-time. All 49 primary state police agencies were included. Hawaii does not have a primary state police agency. Agencies serving special jurisdictions (such as tribal lands, schools, airports, or parks) or with special enforcement responsibilities (such as enforcing conservation or alcohol laws) were out of scope for the survey. Sheriffs' offices without primary law enforcement jurisdiction in the counties they served and federal law enforcement agencies were also ineligible for the LEMAS survey. This includes sheriffs' offices with jail and court duties only.

After completing the 2020 LEMAS survey, if an agency did not report having at least one full-time-equivalent (FTE) sworn officer (either one full-time sworn officer or two part-time sworn officers) as of December 31, 2020, the agency was considered ineligible. After removing out-of-scope agencies, the final sample size for the survey was 3,462.

Consistent with previous LEMAS administrations, agencies with 100 or more FTE sworn officers were considered self-representing (SR) and included with certainty. Agencies with fewer than 100 FTE sworn officers were considered non-self-representing (NSR) and sampled to determine inclusion. The final sample included 1,079 SR agencies and 2,383 NSR agencies. Agencies were further categorized by strata derived from SR classification and general-purpose agency type (either local police department, sheriff's office, or state police). The SR agencies included 669 local police departments, 361 sheriffs' offices, and 49 state law enforcement agencies. Overall, the NSR sample included 1,942 local police departments and 441 sheriffs' offices.

Cross-sectional

Publicly funded state and local law enforcement agencies in the United States in 2020.

agency

Data were collected using two self-administered modes: web and paper surveys. Agencies chose the mode to use. Among responding agencies, 88% responded via web and 12% submitted paper surveys.

Submitted surveys were considered complete if at least 60% of the questionnaire was complete (flagged as COMPLETE=1). A total of 2,704 agencies completed their LEMAS questionnaire for an over-all response rate of 78.1%. This included 914 SR agencies (84.7%) and 1,900 NSR agencies (78.7%). The response rate for local police departments was 79.5%; for sheriffs' offices it was 72.4%; and for primary state law enforcement agencies it was 98.0%. The final database includes completed responses from 2,075 local police departments, 581 sheriffs' offices, and 48 state agencies.

An adjustment factor unique to each stratum was used to account for nonresponse. These nonresponse adjustments were multiplied by the base weight in order to create the final analytical weight for each stratum. For state law enforcement agencies, the final weight is 1.0208. For SR sheriffs' offices it is 1.303 and for SR local police departments the final weight is 1.136. For NSR sheriffs' offices with 50-99 deputies, the final weight is 9.570; with 25-49 deputies, 8.769; with 10-24 deputies, 7.511; with 5-9 deputies, 8.147; and with 1-4 deputies, 9.795. For NSR local police departments with 50-99 officers, the final weight is 6.837; with 25-49 officers, 7.151; with 10-24 officers, 7.090; with 5-9 officers, 7.466; with 2-4 officers, 8.660; and with 1 officer, 8.694.

Hide

2023-03-07

2023-03-07 ICPSR data undergo a confidentiality review and are altered when necessary to limit the risk of disclosure. ICPSR also routinely creates ready-to-go data files along with setups in the major statistical software formats as well as standard codebooks to accompany the data. In addition to these procedures, ICPSR performed the following processing steps for this data collection:

  • Standardized missing values.
  • Performed recodes and/or calculated derived variables.
  • Checked for undocumented or out-of-range codes.
Hide

For the 2020 LEMAS survey, the base weight for all SR local police departments was 1.00 (table 16). For NSR departments, the base weights were calculated by dividing the number of agencies on the sampling frame within each stratum by the number of sampled agencies in the same stratum. The remaining strata and their corresponding base weights are as follows. For NSR sheriffs' offices with 50-99 deputies, the base weight is 5.742; with 25-49 deputies, 5.712; with 10-24 deputies, 5.716; with 5-9 deputies, 5.775; and with 1-4 deputies, 5.742. For NSR local police departments with 50-99 officers, the base weight is 5.721; with 25-49 officers, 5.721; with 10-24 officers, 5.724; with 5-9 officers, 5.731; with 2-4 officers, 5.723; and with 1 officer, 5.738.

Hide

Notes

  • The public-use data files in this collection are available for access by the general public. Access does not require affiliation with an ICPSR member institution.