Overview
Survey Design
Survey Quality Measures
Trend Data
Availability of Data
Overview (FY 2005 survey cycle) ![Top of Page.](https://webarchive.library.unt.edu/web/20081106055317im_/http://nsf.gov/statistics/graphics/uparrow6.gif)
Purpose
The Survey of Science and Engineering Research Facilities is a congressionally mandated, biennial survey. It is the primary source of information about science and engineering research facilities located at U.S. research-performing colleges and universities and nonprofit biomedical research organizations and hospitals. The survey is the basis of public data used by Congress, higher education associations, state governments, academia, and architecture and engineering firms. The survey is cosponsored by the National Institutes of Health.
Respondents
The research facilities survey is an establishment-based survey completed by institutional coordinators at academic and biomedical research organizations. These staff coordinate the collection of information from various institutional offices.
Key variables
The facilities survey collects information on the status of research facilities at academic institutions and nonprofit biomedical research organizations and hospitals including data on:
- Amount and type of science and engineering research space
- Condition of research facilities
- Current expenditures for projects to construct and repair/renovate research facilities
- Planned construction and repair/renovation of research facilities
- Research animal facilities
- Source of funds (Federal, state and local, institutional) for construction and repair/renovation of research facilities
Information technology:
- Bandwidth and networking
- Dark fiber
- High performance computing
- Wireless connections
Survey Design ![Top of Page.](https://webarchive.library.unt.edu/web/20081106055317im_/http://nsf.gov/statistics/graphics/uparrow6.gif)
Target population and sample frame
The research facilities survey is an establishment-based survey with two target populations: (1) research-performing colleges and universities in the United States that expended at least $1 million in research and development funds in the prior fiscal year and (2) nonprofit, biomedical research organizations and hospitals in the U.S. that received at least $1 million in NIH research funding in the prior fiscal year. The frame for the academic institutions is the FY 2004 NSF Survey of Research and Development Expenditures at Universities and Colleges. The frame for the biomedical institutions is an administrative list of institutions receiving NIH research funding in the FY 2004.
Sample design
The survey is a census of all eligible institutions as defined above. In the FY 2005 survey cycle there were 477 academic institutions and 191 biomedical institutions.
Data collection techniques
Surveys are distributed to institutional coordinators at each institution. Institutional coordinators are individuals knowledgeable about the requested information who collect the responses from various offices and submit the information to an NSF contractor. For the 2005 survey, data collection period was from October 2005 through February 2006.
Respondents may report their data using either a paper or Web-based version of the survey. Approximately 85 percent of the respondents submit a Web-based survey. For both methods, telephone and email followup is used.
Several procedures were used to clean and edit the data. For example, the web survey contained numerous programmed edit checks that alerted the respondents to inconsistent or missing data using edit messages. These included alerting respondents if their individual data did not sum to their total data. Once the respondents submitted their final data, a second set of edit checks was conducted.
Estimation techniques
This survey is a census and therefore only nonresponse weights are calculated to make population estimates. The nonresponse weights are the ratio of the number of eligible institutions in the population to the number of responding eligible institutions. These weights are adjusted using a raking technique. The weights for academic institutions were adjusted for the known number of academic institutions by: R&D expenditure category (quintiles of the distribution), geographic region of the country, control of institution (i.e. public or private), whether the institution was a historically black college or university, and whether the institution granted doctorate degrees. The weights for the biomedical institutions used the auxiliary variables of dollar amount of research grant received from the NIH (quintiles of the distribution) and geographic region of the country. The minimum weights for both types of institutions were constrained to be at least 1.0.
Data missing as a result of item nonresponse are imputed using a regression-model approach. Different predictor variables are used for the academic and biomedical institutions. The predictors for the academic linear regressions are: (1) private/public, (2) doctorate-granting/nondoctorate-granting, (3) existence of a medical school, (4) R&D expenditures for the prior fiscal year, and (5) total net assignable square feet (NASF) for the prior fiscal year. The predictors for the biomedical linear regressions are: (1) hospital/nonhospital, (2) NIH research grant amounts for the prior fiscal year, and (3) total NASF for the prior fiscal year.
Survey Quality Measures ![Top of Page.](https://webarchive.library.unt.edu/web/20081106055317im_/http://nsf.gov/statistics/graphics/uparrow6.gif)
Sampling variability
This survey is a census and therefore there is no sampling variation.
Coverage
Institutions meeting the population requirements can be easily identified. However, it is possible that some institutions are inadvertently excluded. Institutions were individually investigated to ensure there was no duplication.
Nonresponse
1. Unit nonresponse – For the FY 2005 cycle, 95 percent (455 out of 477) of the academic institutions responded to the survey and 94 percent (179 out of 191) of the biomedical institutions responded to the survey.
2. Item nonresponse – The FY 2005 survey had limited item nonresponse. Nonresponse ranged from 0 to 6 percent. Most items had 2 percent or less missing.
Measurement
The most likely source of measurement error results from institutions estimating the requested data. Respondents may estimate their data for several reasons. These include estimating for data that are not included in the institution's database and estimating because some figures are estimates by their nature (e.g., outyear budget figures).
Measurement error may also occur because institutions may define their database elements differently from the definitions used on the survey. For example, an institutional database may identify research space based on a primary-use criterion while the survey requests that space be prorated according to all uses. Finally, the survey question on the condition of research space is a judgemental question that may be subject to measurement error.
Trend Data ![Top of Page.](https://webarchive.library.unt.edu/web/20081106055317im_/http://nsf.gov/statistics/graphics/uparrow6.gif)
This survey was first conducted in 1988. Small improvements were made to the survey questions over time, but these changes did not likely affect data comparability.
The FY 2001 survey was very limited and comprised only two questions. However, the data for these two questions should be comparable to the corresponding questions in the prior survey cycles.
The FY 2003 survey cycle used an extensively redesigned survey. For the survey questions requesting data on the traditional "bricks and mortar" section of the survey, some questions were modified, some questions were eliminated, and several new questions were added. To the extent possible, the FY 2003 survey was redesigned for comparability over time. In addition, an entire new set of questions addressing networking and computing was added and then significantly modified for the FY 2005 survey. A more comprehensive description of the redesigned survey can be found in Redesign of Survey of Science and Engineering Research Facilities:
2003.
Beginning with the FY 2003 cycle and continuing with the FY 2005 cycle, respondents were requested to provide data on their institution’s individual, new construction projects. Respondents provided several types of data for each project including name, gross square feet, net assignable square feet, and cost of project. Using this information, it was possible to compare the new construction projects reported by each institution in FY 2003 to the projects the same institution reported in FY 2005 to determine if any appeared to be duplicates.
This comparison identified 36 projects at academic institutions with the same or similar characteristics. Contact with the relevant institutions indicated that 9 projects should not have been reported in the FY 2003 survey. With the approval of each institution, these projects were eliminated from their new construction data.
Also, the data on the source of funding of new construction projects was revised to reflect the deletion of these projects. The nine new construction projects that were removed from the FY 2003 data affected the records of eight institutions. For three institutions, the removal eliminated all new construction projects reported; as a result, all funds reported by source for new construction were also deleted.
For the remaining five institutions, at least one other reported construction project remained. Costs associated with the deleted projects(s) were subtracted from the sources of funds total for each institution. The remaining funds were reallocated to source by distributing
the remaining funds across sources using the same allocation that had been initially reported by each institution.
Finally, the regression models used to impute the FY 2003 new construction and source of funding data were rerun with the new data. The FY 2003 data related to new construction and source of funding for new construction shown in the FY 2005 tables reflect the revised data.
Individuals wishing to analyze trends other than those published in SRS's most recent publications are encouraged to contact the project director below for more information about comparability over time.
Availability of Data ![Top of Page.](https://webarchive.library.unt.edu/web/20081106055317im_/http://nsf.gov/statistics/graphics/uparrow6.gif)
Publications
The data from this survey are published biennially in detailed statistical tables in the series Scientific and Engineering Research Facilities.
Information from this survey is also included in Science and Engineering Indicators.
Electronic access
To make the survey data most useful to survey respondents, microdata beginning with the FY 2003 survey are available in the NSF WebCASPAR data system. Due to a confidentiality pledge, microdata from this survey for the years 1988 through 2001 are not available.
Contact for more information
Additional information about this survey can be obtained by contacting:
Leslie Christovich
Director, Academic Infrastructure Project
Research and Development Statistics Program
Division of Science Resources Statistics
National Science Foundation
4201 Wilson Boulevard, Suite 965
Arlington, VA 22230
Phone: (703) 292-7782
Internet: lchristo@nsf.gov