The Law Enforcement Management and Administrative Statistics (LEMAS) survey collects data from a nationally representative sample of publicly funded state and local law enforcement agencies in the United States. The 2003 LEMAS sample design called for the survey questionnaire to be mailed to 3,179 state and local law enforcement agencies. Twenty-five agencies were determined to be out-of-scope for the survey because they had closed, outsourced their operations, or were operating on a part-time basis, resulting in a final mailout total of 3,154 agencies. The initial mailing of the questionnaire was conducted in December 2003. The pay period containing June 30, 2000 was used as the reference date for all questions, unless otherwise noted. 

Allowing for the exclusion of special jurisdiction agencies and Texas constables, 955 law enforcement agencies in the United States with 100 or more sworn officers as of June 30, 2000, were included in the sample as self-representing (SR) agencies. This included 574 local police departments, 332 sheriffs' offices, and the 49 primary state law enforcement agencies.

The self-representing (SR) agencies were supplemented by a nationally representative sample of agencies with fewer than 100 sworn personnel. These nonself-representing (NSR) agencies were chosen using a stratified random sample with cells based on the type of agency (local police or sheriff), size of population served, and number of sworn personnel. The 2,199 NSR agencies selected included
1,539 local police departments and 660 sheriffs' offices.

A total of 2,859 agencies responded to the LEMAS questionnaire for a response rate of 90.6%. This included 904 SR agencies (94.7%) and 1,955 NSR agencies (88.9%). The final database includes responses from 1,947 local police departments, 863 sheriffs' offices, and the 49 primary state law enforcement agencies. The overall response rate for local police departments was 92.1%, for sheriffs' offices, 87.0%, and for the state law enforcement agencies, 100%.