Graduate Students and Postdoctorates in Science and Engineering: Fall 2006
Appendix A. Technical Notes
The data collected in the 2006 Survey of Graduate Students and Postdoctorates in Science and Engineering represent national estimates of graduate enrollment and postdoctoral employment as of fall 2006 in all U.S. academic institutions that granted master's degrees or research doctorates in any science, engineering, or selected health field. The survey collects data for all branch campuses, affiliated research centers, and separately organized components, such as graduate or medical schools. The survey universe consisted of 707 reporting units at 586 graduate institutions: 495 reporting units at 374 doctorate-granting institutions and 212 reporting units at 212 master's-granting institutions.
Data on graduate science and engineering (S&E) enrollment and postdoctoral appointees have been collected annually since 1966. However, data from 1966 to 1974 are not directly comparable with data from 1975 to 2006 due to changes in both the S&E fields and the types of institutions covered in the survey. From fall 1966 through fall 1971, the National Science Foundation (NSF) Graduate Traineeship Program collected data from a limited number of doctorate-granting institutions and requested data only on S&E fields supported by NSF. The NSF Universities and Nonprofit Institutions Studies Group began collecting these data with the fall 1972 survey. Between 1972 and 1974, eligibility definitions were changed to include selected health fields and to increase the number of S&E fields surveyed; the survey was also broadened to include all institutions known to have programs leading to a doctorate or master's degree in science and engineering.
Table A-1 shows the number of institutions, reporting units, and departments by degree level covered by the GSS, as well as the estimated total enrollment for each year between 1966 and 2006.
The GSS survey instruments (paper and Web versions) consist of NSF Form 811 and NSF Form 812. Form 811 is a list of departments, programs, research centers, or health-care facilities specific to each institution in the survey. Form 812 is a series of questions that obtains counts of students and data on key characteristics of interest, such as race/ethnicity, sex, citizenship, and source of funding.
There were no significant changes to the content of the 2006 survey from previous survey years. However, a number of changes were made to the format of the survey instruments. These changes include the following:
The GSS forms are sent to the school coordinator. In that package are two sets of materials: one for the school coordinator's completion and another that may be completed by the school coordinator or delegated to departmental respondents for completion.
The school coordinator package consists of a booklet that incorporates the following:
In addition, the school-coordinator package contains a crosswalk showing representative National Center for Education Statistics Classification of Instructional Program (CIP) codes corresponding to each science, engineering, and selected health field as defined by NSF.
The departmental respondent package consists of a booklet that incorporates the following:
Each fall the GSS (both paper and the Web version) is sent to a school coordinator appointed by the educational institution. The survey packets were mailed by 11 November 2006 with a requested due date of 31 January 2007. The Web survey was opened on 26 October 2006. The survey procedures used in the 2006 GSS were the same as those used in previous cycles.
School coordinators are requested to review the departmental listing provided in the survey packet on NSF Form 811 and indicate any changes in their school structure, such as departments newly formed, phased out, split, or merged, and to check off any departments that had neither graduate students nor postdoctorates (for which survey forms would therefore not be submitted). School coordinators submit revised Form 811s via the Web survey or by mail to the survey contractor for use as a checklist in tracking departmental responses.
Form 812 is completed by either the school coordinator or departmental respondents and returned to the survey contractor for data entry, editing, and tabulation. The survey contractor refers arithmetic errors, inconsistencies between items, and sharp year-to-year fluctuations to the school coordinators for correction or clarification.
The majority of coordinators indicate they use a combination of sources to provide the data they report on the GSS. Over the years, the use of computerized systems has shown a small but gradual increase.
School coordinators and departmental respondents have had the option of providing data using the Web-based data collection system since the 1998 survey. In 2006, 644 of the 707 reporting units used the online option.
The 2004, 2005, and 2006 response rates are not directly comparable with response rates reported for prior years. Response rates from 1975 through 2003 were calculated for reporting units (schools) and departments but not for institutions. For schools, the response rate was calculated as the total number of responding schools divided by the total number of eligible schools. A school was considered responding if one or more of its eligible departments responded. The departmental response rate was calculated as the number of departments not requiring full imputation divided by the total number of eligible departments. A department was considered responding if it reported at least one data item.
In 2004 the response-rate calculations were changed for schools and departments, and a response-rate calculation was developed for institutions. These new response-rate calculations adhere to the American Association for Public Opinion Research's (AAPOR) standards for computing response rates.
Criteria for distinguishing categories of response (complete, partial, nonresponse) for 2004 forward are as follows:
Department. A department is considered a complete respondent if it reports complete row and column totals in Items 5, 6, 7, and 8 of the survey. A department is considered a partial respondent if it reports only grand totals for Items 5, 6, 7, and 8. A department is classified as a nonrespondent if it does not meet the criteria for complete or partial respondents.
Reporting Unit. A reporting unit is considered a complete respondent if 90% or more of its departments provide data (are not nonrespondents, as defined above for departments). Response is considered partial if more than 50% but less than 90% of its departments provide data. A reporting unit is considered a nonrespondent if less than 50% of its departments provide data. The same criteria are used to categorize institutional response.
In 2006, 10,814 (87.8%) of the total 12,320 eligible departments were considered complete respondents. An additional 1,177 (9.6%) were considered partial respondents, reporting only grand totals to items 5, 6, 7 and 8. A total of 329 departments (2.7%) were considered nonrespondents.
Of the 707 reporting units surveyed in 2006, 665 (94.0%) provided complete responses, 14 (2.0%) provided partial responses, and 28 (4.0%) were nonrespondents.
Of the 586 institutions surveyed in 2006, 547 (96.3%) were complete respondents, 12 (2.0%) were partial respondents, and 27 (4.6%) were nonrespondents.
Table A-4 shows departmental response rates for 1975–2006. For comparison purposes, two sets of response rates are shown for 2004–06. The first set follows the response-rate calculation used from 1975–2003. The second set follows the response-rate calculation introduced in 2004, which adheres to AAPOR standards. For example, in 2006, 329 departments were considered nonrespondents under the new response-rate calculations, whereas only 302 would have been considered nonrespondents under the older method.
Imputation techniques were used to fill in missing data for departments in 2006. Tables A-5 and A-6 show the total number of departments in doctorate- and master's-granting institutions, the imputed number of full- and part-time graduate students enrolled, the imputed number of postdoctoral appointees, and imputation rates for 2004, 2005, and 2006. Tables A-7 through A-12 provide imputation rates and imputed data by specific data items for 2006.
Changes in Data Items
Over time, changes have been made to the content of the survey to keep it relevant to the needs of data users. Such changes prevent precise maintenance of trend data; therefore, some data items are not available for all institutions in all years. Major changes in the data collected (with the year changes became effective) include the following:
Graduate Student Support
During the fall 1988 survey cycle, a review of the survey universe and of the S&E definition resulted in the exclusion of departments that were not primarily oriented toward granting research degrees. A number of departments—mostly those in the field of "Social sciences, not elsewhere classified"—were found to be primarily engaged in training teachers, practitioners, administrators, or managers rather than researchers; thus, they were no longer eligible for the survey. During the 1989–2006 survey cycles, this process continued, and all ineligible departments identified were removed to ensure trend consistency for the entire 1975–2006 period. These changes resulted in a reduction in total enrollments and social science enrollments for all years. Table A-13 shows the net effect on enrollment data of these adjustments over the years.
Each survey cycle since fall 1992, the classification of an institution's previous-year enrollment data has been changed to reflect the institution's degree-granting status (master's or doctorate) in the current survey cycle. Over the years, a number of master's-granting institutions have become doctorate-granting institutions, and their enrollment data were reclassified from master's- to doctoral-degree status. This shifted numerous institutions (and students) from master's-granting to doctorate-granting categories for years before 1992. Shifting enrollment to doctorate-granting institutions partially offsets decreases in enrollment that occur when ineligible departments are removed in the survey universe review process; thus reductions in enrollment have been smaller at doctorate-granting institutions than at master's-granting institutions.
Since the 1992 survey cycle, the definition of medical schools has included only those institutional components with membership in the Association of American Medical Colleges. Data collected before 1992 are not comparable with data collected for the fall 1992 and subsequent surveys.
 The research doctorate is a research degree that (1) requires an original contribution of knowledge to a science, engineering, or health-related field (typically, but not always, in the form of a written dissertation) and (2) is not primarily intended for the practice of a profession. For additional survey information and available data related to graduate student enrollment and postdoctoral appointees in science and engineering, see http://www.nsf.gov/statistics/srvygradpostdoc/.
 In this report, the term "reporting unit" is essentially equivalent to a school (such as a graduate school, medical or dental school, nursing school, or school of public health), an affiliated research center, a branch campus, or any other organizational component within an academic institution that grants a science, engineering, or selected health degree.
 See response rate 3 calculation, p. 29. American Association for Public Opinion Research. 2004. Standard Definitions: Final Dispositions of Case Codes and Outcome Rates for Surveys. 3rd ed. Lenexa, Kansas: AAPOR.