Using Linear Programming to Design Samples for a Complex Survey

Abstract

In the summer of 2005, a RAND Corporation study team was asked to assist the Air Force in assessing Air Force culture and its relationship to a range of behaviors it deemed aberrant. We developed a questionnaire for a survey of Air Force personnel on cultural attitudes (henceforth called the CULTURE survey), and designed a sample of the population to receive email invitations to participate in the survey. The design needed to meet a number of goals that may concern other survey researchers as well: (1) minimize the number of people asked to participate so as to reduce the survey burden on a population already frequently invited to take surveys; (2) reflect response rates we could anticipate from previous surveys of the population; (3) ensure adequate representation of a number of minorities of interest (rank, job type, race and ethnicity, gender, religion, and component); (4) sample enough people in each of the overlapping subset categories of interest (e.g., black female noncommissioned officers [NCOs]) to allow for statistically meaningful comparisons; and (5) minimize (to zero, if possible) the number of service members invited to take both this survey and another survey (the HEALTH survey) on an overlapping set of topics scheduled for the same time period. We describe here the method we developed for designing joint samples for the CULTURE and HEALTH surveys. The Air Force personnel inventory consists of approximately 350,000 active, 105,000 Air National Guard, 75,000 Air Force Reserve, and 150,000 civilian personnel. While our survey drew samples from all these groups, in this report we illustrate the method for the Guard and Reserve only. We wish to select a sample of these individuals that is large and diverse enough to allow us to draw conclusions about how their attitudes are related to their various personal and professional characteristics.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2007
Accession Number
ADA473189

Entities

People

  • James H. Bigelow

Organizations

  • RAND Corporation

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Air Force
  • Air Force Personnel
  • Air National Guard
  • Algorithms
  • Civilian Personnel
  • Computer Programming
  • Health Services
  • Health Surveys
  • Linear Programming
  • Military Personnel
  • Military Science
  • National Guard
  • National Security
  • Operations Research
  • Personnel Management
  • Statistical Samples
  • Warfare

Readers

  • Military Mobilization and Reserve Forces Studies.
  • Organizational Psychology.
  • Regression Analysis.