PDF & Related InfoThe Postsecondary Education Quick Information System (PEQIS) was established in 1991 by the National Center for Education Statistics, U.S. Department of Education. PEQIS is designed to conduct brief surveys of postsecondary institutions or state higher education agencies on postsecondary education topics of national importance. Surveys are generally limited to two or three pages of questions, with a response burden of about 30 minutes per respondent. Most PEQIS institutional surveys use a previously recruited, nationally representative panel of institutions. The sampling frame for the PEQIS panel recruited in 1992 was constructed from the 1990-91 Integrated Postsecondary Education Data System (IPEDS) Institutional Characteristics file. Institutions eligible for the PEQIS frame for the panel recruited in 1992 included 2-year and 4-year (including graduate-level) institutions (both institutions of higher education and other postsecondary institutions), and less-than-2-year institutions of higher education located in the 50 states, the District of Columbia, and Puerto Rico: a total of 5,317 institutions.
The PEQIS sampling frame for the panel recruited in 1992 was stratified by instructional level (4-year, 2-year, less-than-2-year), control (public, private nonprofit, private for-profit), highest level of offering (doctor's/first professional, master's, bachelor's, less than bachelor's), total enrollment, and status as either an institution of higher education or other postsecondary institution. Within each of the strata, institutions were sorted by region (Northeast, Southeast, Central, West), whether the institution had a relatively high minority enrollment, and whether the institution had research expenditures exceeding $1 million. The sample of 1,665 institutions was allocated to the strata in proportion to the aggregate square root of full-time-equivalent enrollment. Institutions within a stratum were sampled with equal probabilities of selection. During panel recruitment, 50 institutions were found to be ineligible for PEQIS, primarily because they had closed or offered just correspondence courses. The final unweighted response rate at the end of PEQIS panel recruitment in spring 1992 was 98 percent (1,576 of the 1,615 eligible institutions). The weighted response rate for panel recruitment was 96 percent.
Each institution in the PEQIS panel was asked to identify a campus representative to serve as survey coordinator. The campus representative facilitates data collection by identifying the appropriate respondent for each survey and forwarding the questionnaire to that person.
As suggested in the background section, precollegiate programs are extremely diverse in their organizations, in the students that they reach, and in the services that they provide. In fact, while this study focuses on precollegiate programs designed to improve the access of disadvantaged students to college, there are a number of programs that are targeted towards precollegiate students for other reasons, such as to promote students' interest or skills in particular subject areas or to reach special groups of students (e.g., minorities, women, or low achievers) who are not necessarily disadvantaged. Results from a pretest of this questionnaire indicated that essentially every institution has at least one program for precollegiate students if a broader definition of precollegiate programs is used, and that many higher education institutions have multiple programs. Since programs with substantially different goals may be too different to provide useful comparisons, this study intentionally is limited only to precollegiate programs for the disadvantaged--a topic of particular interest to the U.S. Department of Education.
This study also focuses more specifically on only the largest precollegiate programs for the disadvantaged, defined as the largest precollegiate program at each institution based on funding. Thus, it is not able to provide the total number of extant precollegiate programs for the disadvantaged or the total number of precollegiate students involved in them, although the information presented in table 1 suggests that most of the precollegiate students and funding are probably included. The decision to focus on the largest precollegiate program was made because of a desire to limit the respondent burden of completing the questionnaires, and because the pretest showed that respondents often do not know the total number of programs at the institution. Precollegiate programs often are run in a highly decentralized manner, perhaps by a single department or even by an individual faculty member, without the involvement of the college's central administration. The pretest suggested that the largest program was generally sufficiently visible that it could be identified, but identifying all programs was a much more difficult task.
Because of the lack of a centralized information source about precollegiate programs, some institutions failed to properly identify their largest precollegiate programs. One indication of this failing is that after the data collection was completed, eight responding institutions were externally identified as having Upward Bound programs, although on the survey they reported having no precollegiate programs for the disadvantaged; it is probable that other non-Upward Bound precollegiate programs were also omitted.32 Since large programs tend to be more visible than small ones, the failure to report having a precollegiate program may be most likely when an institution has only small programs; thus, in those cases where the size of the program is related to other program characteristics, this report may understate the relative frequency of those characteristics that are typical of small programs. For similar reasons, some respondents with multiple precollegiate programs may have misidentified the largest program. Special attention was devoted to this issue during data collection, and numerous such errors were detected and resolved; for this reason the misidentification of the largest precollegiate programs should be a relatively infrequent error.
Another implication of the decentralized structure of precollegiate programs is that institutional respondents had little sense of how the largest program compared to the totality of all programs. While they were asked to describe (in percentages) how the largest program compared to all other precollegiate programs in size, they at best could compare the largest program only to others that they were aware of. To minimize this problem, this report focuses on percentages more than on actual numbers of programs, and it treats respondents' answers about the relative size of the largest precollegiate program as providing only very general information rather than precise numerical estimates.
The sample for this survey consisted of two-thirds of the 2-year and 4-year (including graduate-level) higher education institutions in the PEQIS panel, for a sample of 852 institutions. In early September 1994, questionnaires (see appendix B) were mailed to the PEQIS coordinators at the institutions. Coordinators were told that the survey was designed to be completed by the person at the institution most knowledgeable about the largest (in terms of funding) precollegiate program for disadvantaged students. Coordinators were also told that they might need to contact another office on campus to assist in identifying the largest program and responding to the first three questions.
Two institutions were found to be out of the scope of the survey because they were closed, leaving 850 eligible institutions. These 850 institutions represent the universe of approximately 3,470 2- year and 4-year (including graduate-level) higher education institutions in the 50 states, the District of Columbia, and Puerto Rico. Telephone followup of nonrespondents was initiated in late September; data collection was completed in early December. For the eligible institutions that received surveys, an unweighted response rate of 96 percent (813 responding institutions divided by the 850 eligible institutions in the sample) was obtained. The weighted response rate for this survey was 97 percent. The unweighted overall response rate was 93 percent (97.6 percent panel recruitment participation rate multiplied by the 95.6 percent survey response rate). The weighted overall response rate was 93 percent (96.1 percent weighted panel recruitment participation rate multiplied by the 96.9 percent weighted survey response rate).
Weighted item nonresponse rates ranged from 0 percent to 2.8 percent; for most items, nonresponse rates were less than 1 percent. Because the item nonresponse rates were so low, imputation for item nonresponse was not implemented.
The response data were weighted to produce national estimates (see table 19). The weights were designed to adjust for the variable probabilities of selection and differential nonresponse. The findings in this report are estimates based on the sample selected and, consequently, are subject to sampling variability.
The survey estimates are also subject to nonsampling errors that can arise because of nonobservation (nonresponse or noncoverage) errors, errors of reporting, and errors made in data collection. These errors can sometimes bias the data. Nonsampling errors may include such problems as misrecording of responses; incorrect editing, coding, and data entry; differences related to the particular time the survey was conducted; or errors in data preparation. While general sampling theory can be used in part to determine how to estimate the sampling variability of a statistic, nonsampling errors are not easy to measure and, for measurement purposes, usually require that an experiment be conducted as part of the data collection procedures or that data external to the study be used.
To minimize the potential for nonsampling errors, the questionnaire was pretested with respondents at institutions like those that completed the survey. During the design of the survey and the survey pretest, an effort was made to check for consistency of interpretation of questions and to eliminate ambiguous items. The questionnaire and instructions were extensively reviewed by the National Center for Education Statistics and the Office of the Under Secretary, U.S. Department of Education. Manual and machine editing of the questionnaire responses were conducted to check the data for accuracy and consistency. Cases with missing or inconsistent items were recontacted by telephone. Data were keyed with 100 percent verification.
The standard error is a measure of the variability of estimates due to sampling. It indicates the variability of a sample estimate that would be obtained from all possible samples of a given design and size. Standard errors are used as a measure of the precision expected from a particular sample. If all possible samples were surveyed under similar conditions, intervals of 1.96 standard errors below to 1.96 standard errors above a particular statistic would include the true population parameter being estimated in about 95 percent of the samples. This is a 95 percent confidence interval. For example, the estimated percentage of institutions reporting that the institution had precollegiate programs for disadvantaged students is 32.4 percent, and the estimated standard error is 1.6 percent. The 95 percent confidence interval for the statistic extends from [32.4 - (1.6 times 1.96)] to [32.4 + (1.6 times 1.96)], or from 29.3 to 35.5 percent. Tables of standard errors for each table and figure in the report are provided in appendix A.33
Estimates of standard errors were computed using a technique known as jackknife replication. As with any replication method, jackknife replication involves constructing a number of subsamples (replicates) from the full sample and computing the statistic of interest for each replicate. The mean square error of the replicate estimates around the full sample estimate provides an estimate of the variances of the statistics.34 To construct the replications, 51 stratified subsamples of the full sample were created and then dropped one at a time to define 51 jackknife replicates.35 A computer program (WESVAR), available at Westat, Inc., was used to calculate the estimates of standard errors. The software runs under IBM/OS and VAX/VMS systems.
The test statistics used in the analysis were calculated using the jackknife variances and thus appropriately reflected the complex nature of the sample design. In particular, an adjusted chi-square test using Satterthwaite's approximation to the design effect was used in the analysis of the two-way tables.36 Finally, Bonferroni adjustments were made to control for multiple comparisons where appropriate. For example, for an "experiment-wise" comparison involving g pairwise comparisons, each difference was tested at the 0.05/g significance level to control for the fact that g differences were simultaneously tested.
The survey was performed under contract with Westat, Inc., using the Postsecondary Education Quick Information System (PEQIS). This is the third PEQIS survey to be conducted. Westat's Project Director was Elizabeth Farris, and the Survey Managers were Laurie Lewis and Bradford Chaney. Bernie Greene was the NCES Project Officer. The data were requested by David Goodwin, Planning and Evaluation Service, Office of the Under Secretary, U.S. Department of Education.
This report was reviewed by the following individuals:
Outside NCES
Inside NCES
For more information about the Postsecondary Education Quick Information System or the Survey on Precollegiate Programs for Disadvantaged Students at Higher Education Institutions, contact Bernie Greene, Education Surveys Division, National Center for Education Statistics, Office of Educational Research and Improvement, 555 New Jersey Avenue, NW, Washington, DC 20208-5651, telephone (202) 219-1366.
32
Probably at least some of the eight respondents were aware that their institutions had
Upward Bound programs, so the problem in identifying precollegiate programs is not just a
lack of knowledge, but the manner in which people think of such programs.
33 Standard errors for figures 1 and 5 are not provided in separate tables because the same
statistics are also included in tables 2 and 13, respectively.
34 K. Wolter. Introduction to Variance Estimation, Springer-Verlag, 1985.
35 Ibid, 183.
36 For example, see D. Rao and A. Scott. "On Chi-square Tests for Multi-way Contingency
Tables with Cell Proportions Estimated from Survey Data," Annals of Statistics 12
(1984): 46-60.
){kind=link}