Skip to main content
IES
NCES
NCES
National Assessment of Educational Progress
NAEP Sample Design, Weights, Variance Estimation, IRT Scaling, and Plausible Values
NAEP Sample Design, Weights, Variance Estimation, IRT Scaling, and Plausible Values
Start
TOC
Help
Resources
Previous
Next
Table of Contents
×
Close
×
NAEP Sample Design, Weights, Variance Estimation, IRT Scaling, and Plausible Values
Module Objectives
Overview of NAEP
Main NAEP
NAEP Long-Term Trend (LTT)
NAEP Reporting
Key Design Features of NAEP
NAEP Assessment Design
A Representative Sample is Required
Defining the Target Populations
Included in NAEP’s Target Populations
NOT Included in NAEP’s Target Populations
Sample Designs Used in NAEP
Sample Designs Used in NAEP (Continued)
Sample Designs Used in State Assessment Years
Sample Designs Used in National-Only Assessment Years
Sampling Schools Across All NAEP Assessment Years
Providing Data that are Representative on a National and Regional Basis
Procedure for Selecting Schools and Students in State Assessment Years
Combining the Samples in State Assessment Years
Combining the Samples in State Assessment Years (Continued)
Sampling Schools in National-Only Assessment Years
Sampling Schools and Students in National-Only Assessment Years
Use of Weights: Review
Calculating Standard Errors Using NAEP Data
Standard Error Calculation in NAEP: Replication Techniques
Standard Error Calculation in NAEP: Taylor Series Linearization
Sample Design Implications for NAEP Analysts
NAEP Assessment Design: Review
NAEP IRT Models
Plausible Values
Assessment Design Implications for NAEP Analysts
Summary of Implications for NAEP Analysts
Summary of Implications for NAEP Analysts (Continued)
Module Summary
Module Resources
