Large-scale education data are collected via complex sampling designs that incorporate clustering and unequal probability of selection. Multilevel models are often utilized to account for clustering effects. The probability weighted approach (PWA) has been frequently used to deal with the unequal probability of selection. In this study, we examine…

Many national and international educational data collection programs offer researchers opportunities to investigate contextual effects related to student performance. In those programs, schools are often used in the first-stage sampling process and students are randomly drawn from selected schools. However, the "incidental" dependence of…

When selecting a multilevel model to fit to a dataset, it is important to choose both a model that best matches characteristics of the data's structure, but also to include the appropriate fixed and random effects parameters. For example, when researchers analyze clustered data (e.g., students nested within schools), the multilevel model can be…

This study proposes a new model, termed the multiple membership piecewise growth model (MM-PGM), to handle individual mobility across clusters frequently encountered in longitudinal studies, especially in educational research wherein some students could attend multiple schools during the course of the study. A real data set containing some…

This study is focused on the threat of retention associated with test-based promotion in Grade 3. Through analyzing the Early Childhood Longitudinal Study Kindergarten Class of 1998-1999 data, we found that schools having such a policy apparently increased math instructional time but not reading instructional time in Grade 3. On average, the…

School-average achievement is often reported to have positive effects on individual achievement (peer spillover effect). However, it is well established that school-average achievement has negative effects on academic self-concept (big-fish-little-pond effect [BFLPE]) and that academic self-concept and achievement are positively correlated and…

Conventional multilevel modeling works well with purely hierarchical data; however, pure hierarchies rarely exist in real datasets. Applied researchers employ ad hoc procedures to create purely hierarchical data. For example, applied educational researchers either delete mobile participants' data from the analysis or identify the student only with…

The author used the concepts of academic intensity and sense of responsibility to examine whether children with low school readiness may be moderated by the amount of exposure to learning activities and the attitudes that teachers hold toward these children. Analysis of the Early Childhood Longitudinal Study-Kindergarten Cohort revealed that…

This article examines the relationship between parental networks and parental school involvement during the elementary school years. Using a large, nationally representative data set of elementary school students--the Early Childhood Longitudinal Study-Kindergarten Cohort--and contextual data from the 2000 U.S. Census, our multilevel analysis…

This study used a multilevel mediation model to test the theory that former early childhood education (ECE) attendees' 5th grade achievement is mediated by the aggregate school-wide achievement of their elementary school. Aggregate school-wide achievement was defined as the percentage of 5th graders in a school who were at/above academic…

Policymakers view parental involvement (PI) as a crucial component of school reform efforts, but evidence of its effect on student achievement is equivocal. Using the Early Childhood Longitudinal Study-Kindergarten Cohort dataset, we examined the long-term impact on student- and school-level achievement of three types of school-based PI: PI to…

This study considers whether children who have kindergarten and first grade teachers with certification in early childhood education experience greater gains in reading and math achievement compared to children whose teachers have only elementary education certification. Using data from the Early Childhood Longitudinal Study (ECLS-K), the study…

This study uses a large nationally representative data set (ECLS-K) of 5,181 students to examine the extent to which exposure to content and instructional practice contributes to mathematics achievement in fifth grade. Using hierarchical linear modeling, results suggest that more exposure to content beyond numbers and operations (i.e., geometry,…

This study employed the concept of teachers' sense of responsibility for students' learning to examine the extent to which the gap in math learning growth is reduced and whether such attitudes can improve children's learning outcomes to a degree that is above and beyond their expected achievement relative to their initial academic skills. Analysis…

This paper extends single-level missing data methods to efficient estimation of a "Q"-level nested hierarchical general linear model given ignorable missing data with a general missing pattern at any of the "Q" levels. The key idea is to reexpress a desired hierarchical model as the joint distribution of all variables including…