Areas of Expertise
Survey Methodology and Data Quality
AIR’s survey methodologists combine knowledge from statistics, sociology, psychology, political science, economics, computer science, and business management to provide high quality data for research. Emphasis is placed on:
- the statistical foundations of sampling and estimation in complex surveys;
- questionnaire design;
- data collection and the impact of different modes of data collection on data quality;
- analysis of survey data properly reflecting the complex survey design features; and
- total survey error perspectives on survey design and analysis.
The publication aims to provide users of NCES data with the information necessary to evaluate the suitability of the statistics for their needs, with a focus on the methodologies for survey design, data collection, and data processing.
Airline Pilots' Experiences in and Reactions to Their Check Rides: Results from a Nationwide, Representative Survey
The purpose of this study was to assess the relative effectiveness of different approaches to checking pilot performance at the end of training: the maneuver validation (MV) and the Line Operational Evaluation (LOE). Because the LOE provides greater contextual cues and integrates CRM skills with technical skills, it should simulate typical line operations more accurately than a traditional maneuver validation. Therefore, we hypothesized that pilots would rate the LOE as more useful than the MV. The results presented below are part of a much larger survey of airline pilots’ experiences in and reactions to their professional training (Baker et al., 2002).
Often we think of evaluation research happening at the end of a program or intervention’s lifespan in order to determine whether the program worked – program impact. However, an equally important function served by evaluation research is monitoring program implementation. Evaluations of implementation are essential because they help identify problems with program implementation before the program ends, so that changes in programs or interventions can still have an impact. It doesn’t do us a lot of good to talk about results of an intervention if we find out the intervention was not really in place to begin with! You may find cases where the intervention changes a good bit as schools and teachers make it fit their particular circumstances or the needs of their students. Documenting and understanding these changes are important when you start to talk about how the intervention is affecting the problem or situation it was brought in to address. Without this information it may be difficult to replicate elsewhere.
The Schools and Staffing Survey (SASS), sponsored by the National Center for Education Statistics (NCES), is an integrated sample survey of public and private schools, school districts, principals, teachers, and public school libraries. SASS data, which are collected every four years, inform decision makers and provides researchers with a wealth of relevant data on the nation’s elementary and secondary schools. AIR provides support for all aspects of SASS.
AIR assisted the Veterans Health Administration’s (VHA’s) Office of Quality Performance (OQP) when they changed the content of their Survey of Healthcare Experiences of Patients to surveys modeled on the CAHPS Inpatient and Clinician-Group surveys.
On behalf of the Centers for Medicare and Medicaid Services (CMS), AIR studied the reasons why Medicare beneficiaries without creditable coverage do not enroll in Part D and how they can be encouraged to do so. The project consisted of a survey of beneficiaries without creditable coverage or Part D plans and interviews with health professionals.