A two-stage sampling process was used to select teachers for the FRSS Methodology Kindergarten Teacher Survey on Student Readiness. At the first stage, a stratified sample of 860 schools was drawn from the 1990-91 list of And Data public schools compiled by the National Center for Education Statistics Reliability (NCES). This complete file contains about 85,000 school listings, including over 47,000 schools with kindergartens, and is part of the NCES Common Core of Data (CCD) School Universe. Regular schools with kindergartens in the 50 states and the District of Columbia were included in the sampling frame. Special education and alternative schools, schools in ,the outlying territories, and those without kindergartens were excluded from the frame prior to sampling. With these exclusions, the final sampling frame consisted of approximately 47,000 eligible schools.
The sample was stratified by size of school, region (Northeast, Central, Southeast, and West) and metropolitan status (city, urban fringe, town, rural). Within each of the major strata, schools were sorted by enrollment size, percentage of students eligible for free or reduced-price lunch, and percentage of minority students. The allocation of the sample to the major strata was made in a manner that was expected to be reasonably efficient for national estimates, as well as for estimates for major subclasses. Schools within a stratum were sampled with probabilities proportionate to the estimated number of kindergarten teachers in the school.
It should be noted that the number of kindergarten teachers is not available in the CCD school file; for sampling, the estimates for this figure were derived by applying an overall student-to-teacher ratio to the school-level kindergarten enrollment counts to derive a rough measure of size for each school in the frame.
The 860 schools in the sample were contacted during fall 1992, and asked to provide a list of all kindergarten teachers in each school for sampling purposes. Eligible teachers included all persons teaching a regular kindergarten class, a transitional or readiness kindergarten class, or a transitional first grade. Teachers employed full or part time at the school were included. Excluded from the list were itinerant teachers (unless homebase school), substitute teachers, teachers" aides, special education teachers, special subject teachers (those teaching only physical education, music, etc.), prekindergarten teachers, regular first grade teachers, and any other teachers who did not teach a regular kindergarten, transitional kindergarten, or transitional first grade class. A list of 2,900 kindergarten teachers was compiled, and a final sample of 1,448 teachers was drawn. The selection of teachers was designed to permit separate estimates of teachers" responses by major subclasses. However, analysis by race/ethnicity, sex, or type of kindergarten class taught (regular versus transitional) is limited since special efforts were not taken to oversimple rare populations (e.g., males, minorities, and transitional teachers). On average, one or two teachers were sampled from each school. The survey data were weighted to reflect these sampling rates (probability of selection) and were adjusted for nonresponse. In addition, class weights, which provided national estimates of kindergarten classes, were calculated for items dealing with kindergarten classes and students. Since most public school kindergarten teachers taught only one class, the class weight and teacher weight were identical in most instances. However, for the 28 percent of teachers who taught two kindergarten classes, the teacher weight was multiplied by two to obtain the class weight.
At the first stage of sampling of 860 schools, 17 schools were found to be out of the scope of the study (because of closings or because they no longer offered kindergarten). Of the remaining 843 eligible schools, 825 provided complete lists of kindergarten teachers. The school-level response was 98 percent (825 responding schools divided by the 843 eligible schools in the sample).
In February 1993, questionnaires (see appendix A, Survey Questionnaire) were mailed to 1,448 kindergarten teachers at their schools. Teachers were asked to complete the questionnaire in reference to the full-or half-day kindergarten class they taught. Those teaching both a morning and afternoon class were asked to report for only one of these classes. The sample was randomly split in two, with half receiving instructions to select their morning class and the other half asked to report for their afternoon class. Thirty-two teachers were found to be out of scope (no longer at the school or otherwise not eligible), leaving 1,416 eligible teachers in the sample. Telephone followup of nonrespondents was initiated in late February; data collection was completed by mid-April with 1,339 teachers completing the survey. Of these, 779 teachers (58 percent) completed the mailed questionnaire; telephone interviews were conducted with the remaining 560 teachers (42 percent). The teacher-level response was 95 percent (1,339 teachers who completed the questionnaire divided by the 1,416 eligible teachers in the sample). The overall study response rate was 92 percent (97.8 percent rate of school response multiplied by the 94.5 percent response rate at the teacher level). The weighted overall response rate was 95 percent (98 percent weighted school response rate multiplied by the 97 percent weighted teacher response rate). Item nonresponse ranged from 0.0 percent to 0.9 percent.
The response data were weighted to produce national estimates. The weights were designed to adjust for the variable probabilities of selection and differential nonresponse. A final poststratification adjustment was made so that the weighted teacher counts equaled the corresponding estimated teacher counts from the CCD frame within cel 1s defined by size of school, region, and metropolitan status. 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 collection of the data. These errors can sometimes bias the data. Nonsampling errors may include such problems as the differences in the respondents" interpretation of the meaning of the questions; memory effects; 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 kindergarten teachers like those who 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 staff of the National Education Goals Panel. 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. Imputations for item nonresponse were not implemented, as item nonresponse rates were less than 1 percent (for nearly all items, nonresponse rates were less than 0.5 percent). 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 teachers reporting that they have activity centers in their classes is 97 percent, and the estimated standard error is 0.7 percent. The 95 percent confidence interval for the statistic extends from [97 - (0.7 times 1.96)] to [97 + (0.7 times 1.96),] or from 95.6 to 98.3 percent.
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 variance of the statistic (see Wolter 1985, Chapter 4). To construct the replications, 30 stratified subsamples of the full sample were created and then dropped one at a time to define 30 jackknife replicates (see Wolter 1985, page 183). A proprietary 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 survey was performed under contract with Westat, Inc., using the Fast Response Survey System (FRSS). Established in 1975 by NCES, FRSS was designed to collect small amounts of policy-oriented data quickly and with minimum burden on respondents. Over 45 surveys have been conducted through FRSS. Recent FRSS reports (available through the Government Printing Office) include the following:
Westat's Project Director was Elizabeth Farris, and the Survey Manager was Sheila Heaviside. Judi Carpenter was the NCES Project Officer. The data were requested by John Burkett, Data Development Division, NCES.
This report was reviewed by the following individuals:
For more information about the Fast Response Survey System or the Kindergarten Teacher Survey on Student Readiness, contact Judi Carpenter, Elementary/Secondary Education Statistics Division, Special Surveys and Analysis Branch, Office of Educational Research and Improvement, National Center for Education Statistics, 555 New Jersey Avenue, NW, Washington, DC 20208-5651, telephone (202) 219-1333.
Milbum, S. 1992. "Parents" Beliefs and Behaviors Related to Teaching Basic Skills to Young Children." Paper presented at the Annual Meeting of the American Educational Research Association.
Stipek, D., Daniels, D., Galluzzo, D., and Milbum, S. 1992. "Characterizing Early Childhood Education Programs for Poor and Middle-Class Children, Early Childhood Research Quarterly, 7, 1-19.
The WESVAR Procedures. 1989. Rockville, MD: Westat, Inc.Wolter, K. 1985. Introduction to Variance Estimation. Springer- Verlag.
A data tape containing 85,000 records, one for each public elementary and secondary school in the 50 states, District of Columbia, and 5 outlying areas, as reported to the National Center for Education Statistics by the State Education Agencies for 1990-91. Records on this file contain the state and federal identification numbers, name, address, and telephone number of the school, county name and FIPS code, school type code, enrollment size, and other codes for selected characteristics of the school.
The traditional year of school primarily for 5-year-olds prior to first grade.
An extra year of school for kindergarten-age eligible children who are judged not ready for kindergarten.
An extra year of school for children who have attended kindergarten and have been judged not ready for first grade.
A central city of a Standard Metropolitan Statistical Area (SMSA).
A place within an SMSA of a large or mid-size central city and defined as urban by the U.S. Bureau of Census.
A place not within an SMSA, but with a population greater than or equal to 2,500, and defined as urban by the U.S. Bureau of Census.
A place with a population less than 2,500 and defined as rural by the U.S. Bureau of Census.
Connecticut, Delaware, District of Columbia, Maine, Maryland, Massachusetts, New Hampshire, New Jersey, New York, Pennsylvania, Rhode Island, and Vermont.
Illinois, Indiana. Iowa, Kansas, Michigan, Minnesota, Missouri, Nebraska, North Dakota, Ohio, South Dakota, and Wisconsin.
Alabama, Arkansas, Florida, Georgia, Kentucky, Louisiana, Mississippi, North Carolina, South Carolina, Tennessee, Virginia, and West Virginia.
Alaska, Arizona, California, Colorado, Hawaii, Idaho, Montana, Nevada, New Mexico, Oklahoma, Oregon, Texas, Utah, Washington, and Wyoming.