M E T H O D O L O G Y
Student Sample
School Survey
A total of 1067 public school students in grades 7 through 12 were surveyed during
an English class using a self-administered questionnaire. Interviews averaged 25
minutes in length and were conducted between March 16, 2000 and April 27, 2000.
The Harris national probability sample of schools and students is based on a highly
stratified two-stage sampling design. This design employs features similar to the
sample designs used in various national surveys of students and schools that are con-
ducted by the U.S. National Center of Education Statistics. Sample is drawn from a
list of approximately 80,000 public, private and parochial schools in the United
States. It is selected to account for differences in grade enrollment, region and the
size of the municipality where schools are located. For this study, only public schools
were selected. A random selection of schools is drawn on the basis of the number of
students in each cell proportionate to the number of students in the universe, creat-
ing a cross section of young people in a set of designated grades.
After sending a letter to principals soliciting their participation, Harris
Interactive Inc. contacted the principals in selected schools by telephone to request
their participation in the survey. An eligible grade was randomly assigned to each
school. If the principal agreed to participate, a random selection process was then
used to select a particular class to complete the survey. The principal was asked to
alphabetize all classes for the grade assigned by the Harris firm. Using a random
number selection grid, an interviewer identified an individual class. For junior and
senior high school, where students attend different classes for each subject, only
English classes were used to make the selection. Since all students in all grades must
study English, this ensures a more representative sample of students by academic
track and level of achievement.
A number of steps were included in the consent process in order to maximize
response rates. The alert letter contained a brief description of the survey process
and some background information on the Harris organization and schools were
offered an incentive to participate. In addition, at a principal's request, calls were
made to local boards or district offices to gain approval from the appropriate officials.
If necessary, copies of the introductory letters and other materials were mailed or sent
via fax to the principal and/or other school officials.
If a particular school could not participate, it was replaced by a school with sim-
ilar demographic characteristics so as to preserve the integrity of the primary selec-
tion. Another randomly drawn school was chosen within the same region, with
similar grade enrollment and size of municipality, and in the same or the nearest zip
code to the original school.
Harris Interactive Inc. mailed instructions, a set of questionnaires and materials
for return mail to the teacher of the selected class. In addition, teachers were provid-
ed with guidelines for administering the survey. By providing teachers with educa-
117
