National Survey of Recent College Graduates

The first stage of the sample was selected with probability proportional to size (PPS). A composite size measure was related to the number of eligible graduates, controlling for sample size domains defined by degree level, field of major, race, ethnicity, and sex. Institutions that produce relatively large numbers of bachelor's or master's degrees were selected with certainty. Institutions selected proportionately to a measure of size reflected the maximum percentage of graduates in each of the degree fields within level-of-degree categories. The measure of size was adjusted to increase the probability of selection of institutions with relatively high percentages of graduates in targeted minority groups.

To maintain the efficiency of the institution sample, 301 institutions selected for the NSRCG in 2008 were retained for the 2010 sample. To reflect the population of schools newly eligible for the NSRCG, a supplemental sample of one institution was added to the existing sample. Consequently, the 2010 NSRCG school sample consisted of 302 institutions.

The second-stage sampling consisted of selecting 18,000 bachelor's or master's degree recipients (9,000 for each AY) who received science, engineering, or health degrees from the institutions selected in the first stage. Composite size measures were used to incorporate differential sampling rates for domains subject to over- or under-sampling [1] to satisfy various analytical interests, including minority representation in SEH fields. To formulate the composite size measure for institutions, 222 domains were identified and used, which consisted of combinations from the following four variables:

Degree types (2): bachelor's, master's Major fields of study: bachelor's (20 fields), master's (17 fields) Race and ethnicity groups (3): white, not Hispanic; Asian or Pacific Islander, not Hispanic; and underrepresented minorities (Hispanic; black, not Hispanic; American Indian or Alaska Native, not Hispanic) Sex (2): male, female Institution-level sample sizes of the graduates were calculated separately for certainty and non-certainty institutions to achieve equal weights within key NSRCG domains across institutions. A proportional allocation of the total sample to 85 certainty institutions resulted in institution-level sample sizes from 40 to 240 for those institutions. The noncertainty institutions were implicitly stratified by sorting the list by type of control (public, private), geographic region (northeast, northwest, southeast, southwest), and the percentage of degrees awarded in SEH fields of study. An equal sample allocation was constructed for each of 205 responding non-certainty institutions. However, not all non-certainty institutions had enough numbers of students, thus the sample allocation resulted in institution-level sample sizes from 7 to 153 for those institutions. The 290 participating institutions provided the total sample of 18,000 graduates (9,874 bachelor's and 8,126 master's recipients).

In 2010, Mathematica Policy Research, Inc., under contract to the National Center for Science and Engineering Statistics, conducted the first-stage data with the sampled institutions and the second-stage survey data collection with the sampled individuals. The first-stage data collection began with contacting the 302 sampled institutions to obtain their lists of graduates for AY 2008 and AY 2009. Of the 302 sampled institutions, 290 provided a list of graduates.

The second-stage survey data collection for sampled individuals used three data collection modes — paper, Web, and computer-assisted telephone interviewing (CATI). Paper and Web were the primary modes in the initial stage of data collection, followed by CATI. The 2010 CATI and Web survey instruments were modeled after, and were very similar to the 2008 paper questionnaire used in the mail phase. The NSRCG questionnaire instruments were designed to be as similar as possible to the survey instruments used in the 2010 National Survey of College Graduates (NSCG) and the 2010 Survey of Doctorate Recipients (SDR) to facilitate combining results into estimates of the total SEH population. A few questions in the NSRCG, however, obtain information of special interest for the population of recent graduates. For example, the NSRCG had more information related to education history than did the NSCG or SDR.

The NSRCG has the ability to link with other data sources by IPEDS educational institution indicator and FIPS state code.