We investigate encoder-decoder GRU networks with attention mechanism for solving a diverse array of elementary math problems with mathematical symbolic structures. We quantitatively measure performances of recurrent models on a given question type using a test set of unseen problems with a binary scoring and partial credit system. From our…

In adaptive learning systems, various models are employed to obtain the optimal learning schedule and review for a specific learner. Models of learning are used to estimate the learner's current recall probability by incorporating features or predictors proposed by psychological theory or empirically relevant to learners' performance. Logistic…

Understanding students' misconceptions and how they change is an essential part of supporting students in their science learning. This paper presents results from distractor-driven multiple-choice assessments that target students' misconceptions about energy. Over 20,000 elementary, middle and high school students from across the U.S. participated…

Can student performance on computer-based tests (CBT) and paper-and-pencil tests (PPT) be considered equivalent measures of student knowledge? States and school districts are grappling with this question, and although studies addressing this question are growing, additional research is needed. We report on the performance of students who took…

In this paper, we introduce a mathematical model for collaborative learning and the answering process for multiple-choice questions. The collaborative learning model is inspired by the Ising spin model and the model for answering multiple-choice questions is based on their difficulty level. An intensive simulation study predicts the possibility of…

2009 was the final year of parallel implementation for Mathematical Methods Units 3 and 4 and Mathematical Methods (CAS) Units 3 and 4. From 2006-2009 there was a common technology-free short answer examination that covered the same function, algebra, calculus and probability content for both studies with corresponding expectations for key…

One challenge associated with computerized adaptive testing (CAT) is the maintenance of test and item security while allowing for daily testing. An alternative to continually creating new pools containing an independent set of items would be to consider each CAT pool as a sample of items from a larger collection (referred to as a VAT) rather than…

A study investigated the effectiveness of the Rasch procedure in measuring response appropriateness, especially for the detection of cheating on multiple-choice language tests. The report gives background information on appropriateness measurement and its potential uses, reviews recent research on cheating and its detection, and describes three…

Procedures for determining cutting scores have been proposed by Angoff and by Nedelsky. Nedelsky's approach requires that a rater examine each distractor within a test item to determine the probability of a minimally competent examinee answering correctly; whereas Angoff uses a judgment based on the whole item, rather than each of its components.…

This pamphlet reprints three papers and an invited discussion of them, read at a Division 5 Symposium at the 1975 American Psychological Association Convention. The first paper describes a Bayesian tailored testing process and shows how it demonstrates the importance of using test items with high discrimination, low guessing probability, and a…