Search

Omitted prior achievement bias is pervasive in international assessment studies and precludes causal inference. For example, reported negative associations between student-oriented teaching strategies and student performance are against expectations and might actually reflect omitted prior achievement bias. Namely, that these teaching strategies are negatively correlated with unobserved prior achievement performance, because teachers offer more support to lower performing students, and not that these strategiescauselower performance. This paper examines omitted prior achievement bias in teaching effects with prior achievement data available for students in England participating in the Progress in International Reading Literacy Study. Further, it proposes an analytical approach to account for omitted prior achievement bias in international estimates. The paper argues that the bias is not simply a technical artefact, but reflects educational mechanisms unobserved in international assessment studies, which can be captured with matched assessment data-sets or with evidence from previous studies. Estimates of these mechanisms can be used to postulate scenarios of the bias across education systems and thereby adjust international estimates of teaching effects as if prior achievement were observed. Potentials and limitations of this approach for studying educational effectiveness with international assessment data are discussed. [ABSTRACT FROM PUBLISHER]

The main objective of this study was to quantify the impact of failing to account for measurement error on school compositional effects. Multilevel structural equation models were incorporated to control for measurement error and/or sampling error. Study 1, a large sample of English primary students in Years 1 and 4, revealed a significantly negative compositional effect associated with school-average achievement that became more negative after controlling for measurement error. Study 2, a large study of Cypriot primary students in Year 4, showed a small, positive but statistically significant compositional effect that became non-significant after controlling for measurement error. Our findings have important methodological, substantive, and theoretical implications for on-going debates on the school compositional effects on students’ outcomes, because nearly all previous research has been based on traditional approaches to multilevel models, which are positively biased, due to the failure to control for measurement error. [ABSTRACT FROM PUBLISHER]