Assessing students' performance in online learning could be executed not only by the traditional forms of summative assessments such as using essays, assignments, and a final exam, etc. but also by more formative assessment approaches such as interaction activities, forum posts, etc. However, it is difficult for teachers to monitor and assess…

We introduce DeepPerfEmb, or DPE, a new deep-learning model that captures dense representations of students' online behaviour and meta-data about students and educational content. The model uses these representations to predict student performance. We evaluate DPE on standard datasets from the literature, showing superior performance to the…

Before an assessment is used to make decisions, the validity of the intended interpretation must be evaluated. The purpose of this paper is to describe how the argument-based approach and an interpretation/use argument (IUA) (Kane, 2013) were used to validate the interpretations made from the new Early Grade Mathematics Assessment (EGMA)…

Determining which students are at risk of poorer outcomes -- such as dropping out, failing classes, or decreasing standardized examination scores -- has become an important area of research and practice in both K-12 and higher education. The detectors produced from this type of predictive modeling research are increasingly used in early warning…

This study investigates the issue of the goodness of fit of different skills assessment models using both synthetic and real data. Synthetic data is generated from the different skills assessment models. The results show wide differences of performances between the skills assessment models over synthetic data sets. The set of relative performances…

Effective mining of data from online submission systems offers the potential to improve educational outcomes by identifying student habits and behaviours and their relationship with levels of achievement. In particular, it may assist in identifying students at risk of performing poorly, allowing for early intervention. In this paper we investigate…

We are using stealth assessment, embedded in "Plants vs. Zombies 2," to measure middle-school students' problem solving skills. This project started by developing a problem solving competency model based on a thorough review of the literature. Next, we identified relevant in-game indicators that would provide evidence about students'…

The past few years has seen the rapid growth of data mining approaches for the analysis of data obtained from Massive Open Online Courses (MOOCs). The objectives of this study are to develop approaches to predict the scores a student may achieve on a given grade-related assessment based on information, considered as prior performance or prior…

In early childhood settings narratives that capture children's learning as they go about their day-to-day activities are promoted as a powerful assessment tool. However, in the New Zealand context there is increasing concern that learning stories currently downplay domain knowledge. Data from teacher interviews and samples of learning stories…

Educational reform is not easy. As school leaders search for a format that leads to improvement on many fronts concurrently, data teams is one such promising practice. The data team design not only involves sensemaking of data as evidence of effective teaching and learning, but also builds a professional learning community, distributes leadership,…

A key component to the new wave of performance-based pay initiatives is the use of student achievement data to evaluate teacher performance. As greater amounts of student achievement data are being collected, researchers have been developing and applying innovative statistical and econometric models to longitudinal data to develop measures of an…

Since 1969 the National Assessment of Educational Progress (NAEP) has conducted annual assessments to determine, in the language of the current legislation, "the performance of children and young adults in the basic skills of reading, mathematics and communications" and to "report data periodically on changes in the knowledge and…

Keiser College is a private, for-profit Level II institution with thirteen branch campuses throughout Florida. Most of its academic programs are offered at multiple sites. A major concern has been to establish and maintain the consistency of its academic offerings at all campuses as the College expands. Building on a pre- posttesting mechanism…

Curriculum-based assessment (CBA) represents a shift from use of standardized tests as quantifiers of student achievement toward traditional data-based instructional management. The role of assessment in educational programs is explored through presentation of three contrasting perspectives: assessment for placement versus assessment for…

The serious problems faced in the ESAA (Emergency School Aid Act) data collection effort (magnitude of the data to be collected, many kinds of respondents, and sensitivity of much of the data) are discussed. Procedures for overcoming obstacles are described. These include limiting collection to essential data, tailoring instruments to respondents,…