An Empirical Unraveling of Lord's Paradox     

ZhiMin Xiao  Steve Higgins  Adetayo Kasim 《Journal of Experimental Education》2019,87(1):17-32

Lord's Paradox occurs when a continuous covariate is statistically controlled for and the relationship between a continuous outcome and group status indicator changes in both magnitude and direction. This phenomenon poses a challenge to the notion of evidence-based policy, where data are supposed to be self-evident. We examined 50 effect size estimates from 34 large-scale educational interventions and found that impact estimates are affected in magnitude, with or without reversal in sign, when there is substantial baseline imbalance. We also demonstrated that multilevel modeling can ameliorate the divergence in sign and/or magnitude of effect estimation, which, together with project specific knowledge, promises to help those who are presented with conflicting or confusing evidence in decision-making.  相似文献   

comparison of three growth modeling techniques in the multilevel analysis of longitudinal academic achievement scores: Latent growth modeling, hierarchical linear modeling, and longitudinal profile analysis via multidimensional scaling     

Tacksoo Shin 《Asia Pacific Education Review》2007,8(2):262-275

This study introduces three growth modeling techniques: latent growth modeling (LGM), hierarchical linear modeling (HLM), and longitudinal profile analysis via multidimensional scaling (LPAMS). It compares the multilevel growth parameter estimates and potential predictor effects obtained using LGM, HLM, and LPAMS. The purpose of this multilevel growth analysis is to alert applied researchers to selected analytical issues that are required for consideration in decisions to apply one of these three approaches to longitudinal academic achievement studies. The results indicated that there were no significant distinctions on either mean growth parameter estimates or on the effects of potential predictors to growth factors at both the student and school levels. However, the study also produced equivocal findings on the statistical testing of variance and covariance growth parameter estimates. Other practical issues pertaining to the three growth modeling methods are also discussed.  相似文献   

学校效能的增值评价——对河北省保定市普通高中学校的实证研究   总被引：14，自引：0，他引：14  

马晓强  彭文蓉  萨丽·托马斯 《教育研究》2006,(10)

学校评价在教育评价体系中处于核心地位,它直接影响着对教师评价和学生评价的原则以及学校的发展方向。运用增值评价学校效能是当前学校评价研究的重要内容。对河北省保定市普通高中学校效能进行实证研究结果表明60%~80%的高考成绩校际差距都不是学校本身所导致的,在提高学生进步幅度方面,不同学校间存在明显差异。增值评价结果与高考分数评价结果存在较大差异;学校效能在不同学科间没有显著差异;学校对不同学生群体的效能无差异。学校效能的增值评价对于创新学校评价体系具有重要的参考价值。  相似文献   

Long‐term effects of primary schools on mathematics achievement of students at age 17          下载免费PDF全文

Griet Vanwynsberghe  Gudrun Vanlaar  Jan Van Damme  Bieke De Fraine 《British Educational Research Journal》2017,43(6):1131-1148

In the field of educational effectiveness research, school effects are generally studied in the short term (i.e. during the same phase of schooling). The aim of this study is to investigate long‐term primary school effects on students’ achievement in mathematics at the end of secondary education. We also investigate which primary school characteristics are of importance in the long term. Data from the longitudinal SiBO project, in which a cohort of 6,000 Flemish pupils were intensively followed from kindergarten to grade 7, was used. At the age of 17, the same cohort participated in follow‐up data collection. Cross‐classified multilevel models showed small continuing effects of primary school on the mathematics achievement of students (i.e. over and above what had been reached at the end of primary education). No long‐term effect was found of the proportion of high‐risk students at primary school. Students coming from a primary school with a higher effectiveness obtained higher mathematics results at age 17, but when the mathematics achievement of students at the end of primary school was taken into account, this effect disappeared. We also observed that students coming from Catholic primary schools performed better in mathematics at age 17 compared with students coming from public schools. The implications of the findings are discussed.  相似文献   

Who benefits from dyadic teacher–student interactions in whole-class settings?     

André Flieller  Annette Jarlégan  Youssef Tazouti 《The Journal of educational research》2016,109(3):311-324

To what extent can teacher–student dyadic interactions modify the hierarchy of student performances within a single class? To answer this insufficiently researched question, the authors conducted two parallel studies involving 33 Grade 5 classes in France (759 students) and 15 Grade 5 classes in Luxembourg (243 students). Interactions were observed during whole-class lessons. Posttest scores were analyzed using multilevel models controlling for five level-1 variables and two level-2 variables. The authors did not find any effect of dyadic interactions on relative student performance in mathematics or in language (French or German), in France or in Luxembourg. This result is interpreted in terms of both the public character of dyadic interactions in whole-class settings and the class management functions of these interactions.  相似文献   

A healthy start: promoting mental health and well-being in the early primary school years     

Carmel Cefai  Liberato Camilleri 《Emotional and Behavioural Difficulties》2013,18(2):133-152

Mental health problems in children represent a significant international health concern, with up to one in five children using mental health services during the course of any given year. Identifying the processes of what prevents social, emotional and behaviour difficulties (SEBD) and promotes healthy development from an early age can make a significant contribution to the promotion of positive mental health in children. This article describes a longitudinal study which sought to identify the risk and promotive factors as young children move from the early to junior years in primary school. Multilevel analysis was used to identify the individual, classroom, school, home and community factors that predict change in SEBD and in prosocial behaviour in the early school years. It also calculated the cumulative effect of the various risk and promotive factors on the pupils’ well-being and mental health. The article presents the windows of vulnerability and opportunity for young children’s healthy development, proposing a trajectory for healthy development in early and middle childhood.  相似文献   

Trajectories of math achievement and perceived math competence over high school and postsecondary education: effects of an all-girl curriculum in high school     

Jennifer D. Shapka 《Educational Research and Evaluation》2013,19(6):527-541

This study investigated the benefits of all-girls' classroom instruction in math and/or science during Grades 9 and/or 10, within the context of a public co-educational high school. There were 118 participants in this longitudinal investigation: 26 girls in the all-girl classes, as well as 42 girls and 50 boys in the regular co-educational program. A range of pre-existing achievement, background, and psychological characteristics were included as covariates to ensure comparability of the groups. Individual growth curve modeling was used to examine how math achievement and perceived math competence changed over the course of high school and postsecondary education. Change was found to be nonlinear for both constructs (with math achievement starting high, dipping, and then recovering; and with perceived competence doing the opposite). The all-girl intervention appeared to act as a protective mechanism against the temporary decline in math achievement experienced by both co-ed boys and co-ed girls.  相似文献   

A Note on Cluster Effects in Latent Class Analysis     

David Kaplan  Bryan Keller 《Structural equation modeling》2013,20(4):525-536

This article examines the effects of clustering in latent class analysis. A comprehensive simulation study is conducted, which begins by specifying a true multilevel latent class model with varying within- and between-cluster sample sizes, varying latent class proportions, and varying intraclass correlations. These models are then estimated under the assumption of a single-level latent class model. The outcomes of interest are measures of bias in the Bayesian Information Criterion (BIC) and the entropy R ² statistic relative to accounting for the multilevel structure of the data. The results indicate that the size of the intraclass correlation as well as between- and within-cluster sizes are the most prominent factors in determining the amount of bias in these outcome measures, with increasing intraclass correlations combined with small between-cluster sizes resulting in increased bias. Bias is particularly noticeable in the BIC. In addition, there is evidence that class separation interacts with the size of the intraclass correlations and cluster sizes in producing bias in these measures.  相似文献   

The Theory of Planned Behavior Within the Stages of the Transtheoretical Model: Latent Structural Modeling of Stage-Specific Prediction Patterns in Physical Activity     

Sonia Lippke  Claudio R. Nigg  Jay E. Maddock 《Structural equation modeling》2013,20(4):649-670

This is the first study to test whether the stages of change of the transtheoretical model are qualitatively different through exploring discontinuity patterns in theory of planned behavior (TPB) variables using latent multigroup structural equation modeling (MSEM) with AMOS. Discontinuity patterns in terms of latent means and prediction patterns for the different stage groups were examined. Adults (n = 3,462) were assessed on their physical activity stages of change and TPB variables. The TPB was separately examined within the five stage groups. The TPB measurement model fit was acceptable. Latent mean analyses with post-hoc contrast and MSEM indicated discontinuity patterns. Results underscore the qualitative differences between the stages that may guide further research and the design of interventions integrating the approaches.  相似文献   

An Expansion of the Trait-State-Occasion Model: Accounting for Shared Method Variance     

Beth LaGrange  David A. Cole 《Structural equation modeling》2013,20(2):241-271

This article examines 4 approaches for explaining shared method variance, each applied to a longitudinal trait–state–occasion (TSO) model. Many approaches have been developed to account for shared method variance in multitrait-multimethod (MTMM) data. Some of these MTMM approaches (correlated method, orthogonal method, correlated method minus one, correlated uniqueness) were therefore borrowed in these analyses such that their effectiveness could be evaluated in conjunction with a TSO model. To this end, datasets were generated according to 4 different covariance matrices (each created according to specifications of a model built with 1 of the 4 approaches) and each model was crossed with each type of data. Whereas the correlated method and correlated method minus one approaches encountered many difficulties in convergence, fit, or parameter estimates, the correlated uniqueness and orthogonal method approaches proved to be quite versatile.  相似文献