National Survey of Ambulatory Surgery Sample Design
2006 Sample Design
The universe definition for hospitals for the 2006 NSAS was the same as in the earlier NSAS surveys. For the 2006 NSAS, the hospital sample frame was constructed from the products of Verispan, L.L.C., specifically their “Healthcare Market Index, Updated June 15, 2005” and their “Hospital Market Profiling Solution, Second Quarter, 2005”. These products were formerly known as the SMG Hospital Market Database. In 2006, the sample consisted of 224 hospitals. Of the 224 hospitals, 35 were found to be out-of-scope (ineligible) because they went out of business or otherwise failed to meet the criteria for the NSAS universe. Of the 189 in-scope (eligible) hospitals, 142 hospitals responded to the survey.
The universe of freestanding facilities included FSASCs that were regulated by the States or certified by the Centers for Medicare and Medicaid Services (CMS) for Medicare participation. The sampling frame consisted of facilities listed in the 2005 Verispan Freestanding Outpatient Surgery Center Database and Medicare-certified facilities included in the CMS Provider-of-Services (POS) file. Facilities specializing in dentistry, podiatry, abortion, family planning, or birthing were excluded. However, procedures in these categories were not excluded from in-scope locations. In 1994-1996, pain block locations were excluded; however, they were included in the 2006 NSAS at the recommendation of experts in the field.. In 2006, the sample consisted of 472 freestanding ASCs. Of the 472 FSASCs, 75 were found to be out-of-scope (ineligible) because they failed to meet the criteria for the NSAS universe. Of the 397 in-scope (eligible) FSASCs, 295 FSASCs responded to the survey.
The 2006 NSAS sampled facilities were selected using a multi-stage probability design with facilities having varying selection probabilities. Independent samples of hospitals and freestanding ambulatory surgery centers were drawn. Unlike the 1994-1996 NSAS, which used a three-stage stratified cluster design, with the first stage consisting of geographic primary sampling units or PSUs, the 2006 NSAS used a two-stage list-based sample design. Facilities were stratified by facility type (hospital versus freestanding), ambulatory surgery status of hospitals (i.e. whether or not the hospital performed such surgery), facility specialty, and geographic region.
The first stage of the design consisted of selection of facilities using systematic random sampling with probabilities proportional to the annual number of ambulatory surgeries performed. For the stratum of hospitals which, according to the sampling frame data, did not have ambulatory surgery, a national sample of 25 hospitals was selected to permit estimates of surgery in hospitals that either added ambulatory surgery since the frame was selected or differed from the frame.
At the second stage, within sampled facilities, a sample of ambulatory surgery visits was selected using a systematic random sampling procedure. Selection of visits within each facility was performed separately for each location where ambulatory surgery was performed. These locations included main operating rooms, dedicated ambulatory surgery units, cardiac catheterization laboratories, laser procedure rooms, endoscopy and laparoscopy rooms, etc. Locations within hospitals dedicated exclusively to abortion, dentistry, podiatry, or small procedures are not included. The exclusion of these specialty locations, as well as the exclusion of facilities exclusively devoted to these specialties, were recommended based on the feasibility study for the NSAS that was conducted in 1989-1991. The 2006 NSAS includes pain block facilities, whereas the 1994-1996 NSAS did not. Since NSAS data are collected from a sample of visits, persons with multiple visits during the year may be sampled more than once. NSAS estimates are of the number of visits to or procedures performed in ambulatory surgery facilities, not the number of persons served by these facilities.
There were 696 hospitals and freestanding ambulatory surgery centers in the 2006 NSAS sample. Of these, 110 were found to be out of scope (ineligible) because they went out of business or failed to meet the criteria for the NSAS. Of the 586 in-scope (eligible) facilities, 437 responded to the survey, for an overall response rate of 74.6 percent. The response rate was 75.1 percent for hospitals and 74.3 percent for freestanding facilities. In all the response rate was 74.4 percent. Data for the 2006 NSAS was collected for approximately 52,000 ambulatory surgery visits.
For more information about the 2006 NSAS sample design, see the 2006 NSAS public-use data file documentation Cdc-pdf[PDF – 375 KB].
1994-1996 Sample Design
The universe of eligible facilities for the 1994-1996 National Survey of Ambulatory Surgery (NSAS) consists of hospitals and freestanding ambulatory surgery centers. The hospital universe includes noninstitutional hospitals exclusive of Federal, military, and Department of Veterans Affairs hospitals, located in the 50 States and the District of Columbia. Only short-stay (hospitals with an average length of stay for all patients of less than 30 days) or those whose specialty is general (medical or surgical) or children’s general are included in the survey. Those hospitals must also have six beds or more staffed for patient use. The universe definition is the same as that used for the National Hospital Discharge Survey and the National Hospital Ambulatory Medical Care Survey. The sampling frame for the hospital universe consists of eligible hospitals listed in the 1993 SMG Hospital Market Database.
The 1994-1996 universe of freestanding facilities includes the freestanding ambulatory surgery centers listed in the 1993 SMG Freestanding Outpatient Surgery Center Database and/or Medicare-certified facilities included in the Health Care Financing Administration Provider-of-Services file. Facilities specializing in dentistry, podiatry, abortion, family planning or birthing are excluded.
The 1994-1996 NSAS uses a multistage probability design with independent samples of hospitals and freestanding ambulatory surgery centers. A three-stage stratified cluster design is used to select the samples of facilities and visits.
The first stage consists of a selection of a subsample of the primary sampling units (PSU’s) used in the 1985-94 National Health Interview Survey. PSU’s are counties, a group of counties, county equivalents (such as parishes or independent cities), or towns and townships (for some PSU’s in New England). The second stage consists of a selection of facilities from the sample PSU’s.
At the third stage, a systematic random sample of ambulatory surgery visits is selected. Sampled visits are drawn from all locations within a facility where ambulatory surgery is performed, including main or general operating rooms, all dedicated ambulatory surgery rooms, cystoscopy and endoscopy units, cardiac catheterization labs, and laser procedure rooms (in-scope locations). However, locations within hospitals dedicated exclusively to abortion, dentistry, podiatry, pain block, or small procedures (sometimes referred to as “lump and bump” rooms) are not included. The exclusion of these specialty locations, as well as the exclusion of specialty facilities, were recommended based on the feasibility study for the NSAS. A detailed description of the design and development of the NSAS is included in “The Plan and Operation of the National Survey of Ambulatory Surgery,” Cdc-pdf[PDF – 3.9 MB] Vital and Health Statistics Series 1, Number 37.