ERIC Number: ED167571
Record Type: RIE
Publication Date: 1975-Oct
Reference Count: 0
Efficiency Study of the NLS Sample Design. 22U-884-3.
Moore, R. P.; Shah, B. V.
An efficiency study was conducted of the sampling design used for the National Longitudinal Study of the High School Class of 1972 (NLS), and the change variables used in the first followup. Nine alternative designs were compared, using a cost model based upon the number of schools and students sampled. Fourteen change variables and eight domains defined by race, sex, and father's education were chosen for the analysis. Variance components and efficiency were calculated for each of the 238 statistics defined by the above variables and domains, for each of the nine sample designs. The average efficiencies of each design were calculated for all of the statistics, national statistics, and domain statistics. The optimal designs--those with the highest efficiencies--were defined as follows: (1) for national statistics, 12 students sampled per school; (2) 15 white students per school; 18 for blacks, other races, males, and females; and 21-27 for the domains defined by father's occupation; and (3) for all statistics, the current NLS design of 18 students per school. Designs which sampled nine to 27 students per school all had high efficiencies for national and domain statistics. Base-year NLS and first followup questions used to define change variables are appended. (Author/GDC)
Descriptors: Attitude Change, Cost Effectiveness, Data Analysis, Efficiency, Followup Studies, Graduate Surveys, High School Graduates, High Schools, Longitudinal Studies, National Surveys, Participant Characteristics, Predictor Variables, Questionnaires, Research Design, Sample Size, Sampling, Statistical Studies
Publication Type: Reports - Research; Tests/Questionnaires
Education Level: N/A
Authoring Institution: Research Triangle Inst., Durham, NC. Statistics Research Div.
Identifiers: National Longitudinal Study High School Class 1972
Note: Some pages marginally legible due to print quality