Computer-based tests facilitate the collection of problem-solving processes, also known as process data. Response processes recorded in computer log files provide a new venue for investigating and understanding human behaviors. This thesis focuses on the development of statistical learning methods for process data and considers the following three problems. The first problem is feature extraction. Response processes are noisy and of non-standard formats. To exploit information in process data, we propose two generic methods that summarize response processes to vectors so that standard statistical tools such as regression models are applicable. In Chapter 2, features are extracted using multidimensional scaling and a pairwise dissimilarity measure of response processes. Chapter 3 utilizes autoencoder and recurrent neural network to explore the latent structure of process data. For both methods, empirical studies show that the extracted features preserve a substantial amount of information in the observed processes and have greater predictive power for many variables than the traditional item responses. The second problem is assessment based on process data. We present a statistical procedure in Chapter 4 that incorporates process information to improve the latent trait estimation of item response theory models. The procedure is data-driven and can be easily implemented by means of regression models. Theoretical guarantee is established for the mean squared error reduction. Application of this new process-data-based estimator to a real dataset shows that it achieves higher reliability than the traditional item-response-theory-based estimator. The third problem is identification of problem-solving strategies for exploratory analysis. The approach presented in Chapter 5 segments individual process into a sequence of more homogeneous subprocesses using action predictability. Each subprocess is associated with a subtask whereby long and complex response process can be transformed into shorter and more interpretable subtask sequence. Using this approach, problem-solving strategies can be visualized and compared among groups of respondents and process information can be decomposed for further analysis.

Submitted to the Faculty of Education in fulfilment of the requirements for the Degree of Master of Education, in the Department of Mathematics, Science and Technology Education at the University of Zululand, 2008. / The present study is about the problem solving and the use of computer in teaching and learning of mathematics. The study was conducted to grade eight learners where basic mathematics concepts are introduced. The reason is that lack of knowledge of basic mathematics concepts, irrelevant approaches and methods used in teaching mathematics are perceived as the cause of poor performance in mathematics. Therefore if learners could master these concepts and acquire problem solving skills at elementary level they can do better in upper levels especially in grade 12. In this regard the effects of problem solving involving the use of computer at grade eight level have been investigated. The first aim was to test the effects of multidimensional approach using computer in algebra problem solving. The second aim was to determine the effects multiple representations in computer environment have on mathematics problem solving. The third aim was to determine the effects of computer assisted collaborative learning on mathematics problem solving. To achieve these aims an unstandardised achievement test and a questionnaire was administered to a sample of grade eight learners from three high schools in KwaZulu Natal. The results revealed that if problem solving is integrated with other components (dimensions) such as the teaching of facts and skills, teaching for understanding and the use of technology (computer) learners are likely to achieve better results in mathematics. The results also revealed that the use of multiple representations in expressing the mathematical concept or idea and collaboration among learners in problem solving improve learners' understanding of mathematics. The discussion of the results of this study leads to the discussion of implications of the findings and recommendations. / University of Zululand.

No description available.

No description available.

No description available.

No description available.

No description available.

With over 60 years of education reform, including the National Defense Education Act (NDEA) in 1958, Individuals with Disabilities Education Act (IDEA) in 1975, and No Child Left Behind (NCLB) in 2002, the achievement gap still existed at the beginning of the 21st century, and the effectiveness of the U. S. public school system continued to be questioned. This study was conducted to examine the effect of the use of a computer-assisted instruction curriculum, Achieve 3000, among select secondary reading students in a central Florida school district and their implications for student achievement. This study showed significant difference existed in the type of students rather than the reading program. The ANCOVA performed on all students and the ANOVAs performed for exceptional education students, males and females, free/reduced lunch and ethnic subgroups did not show a significant statistical difference in the 2012-2013 reading achievement scores. The Achieve 3000 reading program did not close the achievement gap any more than the non-Achieve 3000 reading program. Conversely, the ANOVA performed for English language learners did show a significant statistical difference between the 2012-2013 reading achievement scores. However, the effect size each question was small indicating the practical implication was also small. Ultimately, this study made a strong argument for the need for further research.

No description available.

No description available.