This section provides a brief discussion of the methodology used in the conduct of the Survey of Research and Development Expenditures at Universities and Colleges. For a more in-depth discussion of the methodology used in conducting this survey, please see the full report.
The Survey of Research and Development Expenditures at Universities and Colleges is the primary source of information on separately budgeted research and development expenditures within academia in the United States and outlying areas. The results of the survey are used to assess trends in R&D expenditures. This information is vital for planners within the Federal and State governments and in academia.
The survey is completed by institutional representatives at U.S. universities, colleges, and federally funded research and development centers.
The target population covers institutions that have doctoral programs in the sciences or engineering and/or are other institutions that annually perform at least $150,000 in separately budgeted R&D. All HBCUs with R&D programs are included, regardless of the level of R&D. Academically administered FFRDCs are also included. The FY 1998 survey returned to a full population and will continue as a census every year. The frame for the population survey was constructed through screening of institutions identified as receiving Federal funds in the Federal Science and Engineering Support to Universities, Colleges, and Nonprofit Institutions and from institutions identified in the Survey of Graduate Students and Postdoctorates in Science and Engineering and institutions listed in the Higher Education Directory. All institutions on the compiled list that are not known to be in-scope are contacted by phone to determine whether they are in fact in-scope. More detail may be obtained from the full Methodology Report.
The FY 1997 survey was the last sample frame. Refer to the FY 1997 Methodology Report for previous design, sampling techniques, and additional detail.
The FY 1998 survey was conducted by QRC Division of Macro International Inc. under contract to the Division of Science Resources Studies. Respondents were offered the option of reporting their survey data via the survey instruments mailed to institutions or responding online using the World Wide Web. A Web User ID and Password were included in each mailout packet. The full survey instrument with instructions and built in help aids designed to replicate the printed forms were used to ease reporting. Each institution's web form included 2 preceding years data for arithmetical and trend checks. Respondents were also asked to explain and reconcile any survey-collected information on expenditures for prior submissions. Data collection took place between November 1998 and July 1999.
Information for nonrespondents is estimated using information from prior years figures derived from the data of respondent institutions that have similar characteristics, including highest degree granted and type of institutional control (public or private). Estimated values account for less than 1 percent of the total R&D expenditures in the survey. When an institution fails to report in a given year, but reports in the next year, the data for the missing year are re-estimated to reflect the new information if it appears likely that the new information will have a significant impact on the original estimate.
Missing information for partial submissions is imputed. When available, information from prior years' surveys for the institution is used in making this imputation. Otherwise, estimates are based on figures derived from data of respondent institutions that have similar characteristics, including highest degree granted and type of institutional control (public or private). Imputed values account for less than 1 percent of the total R&D expenditures in the survey.
Since the FY 1998 survey returned to a full population and was distributed to all institutions on the sample frame, there was no sampling error.
Coverage at the institutional level is believed to be quite good, given that it is relatively easy to identify schools that grant master's or doctoral degrees. However, coverage problems could arise through incorrect classification of universities as granting S&E degrees. It is also possible that some universities that do not offer master's or doctoral degrees but belong in the target population (either because they have separately budgeted R&D expenditures of $150,000 or more or because the are HBCUs) are inadvertently excluded. Further, for individuals interested in all separately budgeted R&D funds without the $150,000 minimum requirement, there is an additional undercoverage problem related to the exclusion of small institutions. We estimate that these institutions account for less than 5 percent of the Nation's academic R&D funds.
(1) Unit nonresponse - 548 Universities and colleges and 17 FFRDCs, a total of 565, responded in FY 1998 out of a grand total of 573 for a response rate of 98.6.
(2) Item nonresponse - Item nonresponse was under 1 percent for the national estimate of separately budgeted R&D expenditures. The effect of item nonresponse was further reduced through imputation techniques. Item nonresponse is, therefore, not viewed as a problem for this survey.
One possible source of measurement error is that respondents may not have the desired information requested in the survey. For example, in requesting industry R&D, the survey requests the institution to include only grants and contracts from profit-making organizations; research funded through unrestricted accounts and from corporate foundations, endowments, or fellowships is excluded. Most major academic institutions make this distinction in their records; however, the failure of some institutions to make the needed classifications contributes to an unknown amount of measurement error. Further, even when records are kept in a way that is consistent with the information requested in the survey, the records may be less than 100 percent accurate.
This survey has been conducted annually since FY 1972. The FY 1978 survey used a different population and different questions than preceding or subsequent surveys, resulting in a lack of comparable information for that year. When the review of data for consistency between each year's data and submissions for prior years reveals discrepancies, it is sometimes necessary to modify prior years' data. This is especially likely to affect trends for specific institutions that fail to report every year, since current-year data are used to impute prior-year data. Individuals wishing to analyze trends other than those published in SRS's most recent publication or included in SRS's most recent multiyear computer tape are encouraged to contact the project officer listed below for more information about comparability over time.
The data from this survey are published annually in Detailed Statistical Tables in the series Academic Science and Engineering: R&D Expenditures, available on the SRS Web site. Data for major data elements are available starting in 1972. Information from this survey is also included in Science and Engineering Indicators and National Patterns of R&D Resources.
Data from this survey are available on the SRS Web site and on WebCASPAR. Selected aggregate data are available in public use data files upon request.
Additional information about this survey can be obtained by contacting:
