The sample for the 2008 long-term trend assessment was selected using a complex multistage sampling design that involved sampling students from selected schools within selected geographic areas across the country. The sampling design had the following stages:
Each selected school that participated in the assessment and each student assessed represents a portion of the population of interest. Some smaller populations were oversampled to ensure sufficient representation. Therefore, sampling weights are needed to make valid inferences between the student samples and the respective populations from which they were drawn. Sampling weights adjust for disproportionate representation due to such oversampling.
The target population consisted of 9-, 13-, and 17-year-old students. Eligibility for the age 9 and age 13 samples was based on calendar year: students in the age 9 sample were 9 years old on January 1, 2008, with birth months January 1998 through December 1998; and students in the age 13 sample were 13 years old on January 1, 2008, with birth months January 1994 through December 1994. Students eligible for the age 17 sample had to be 17 years old on October 1, 2008, with birth months October 1990 through September 1991.
See a table summarizing the sample size and target population for the long-term trend assessment.