Knowledge Discovery from the Programme for International Student Assessment

Abstract

The Programme for International Student Assessment (PISA) is a worldwide study that assesses the proficiencies of 15-year-old students in reading, mathematics, and science every three years. Despite the high quality and open availability of the PISA data sets, which call for big data learning analytics, academic research using this rich and carefully collected data is surprisingly sparse. Our research contributes to reducing this deficit by discovering novel knowledge from the PISA through the development and use of appropriate methods. Since Finland has been the country of most international interest in the PISA assessment, a relevant review of the Finnish educational system is provided. This chapter also gives a background on learning analytics and presents findings from a novel case study. Similar to the existing literature on learning analytics, the empirical part is based on a student model; however, unlike in the previous literature, our model represents a profile of a national student population. We compare Finland to other countries by hierarchically clustering these student profiles from all the countries that participated in the latest assessment and validating the results through statistical testing. Finally, an evaluation and interpretation of the variables that explain the differences between the students in Finland and those of the remaining PISA countries is presented. Based on our analysis, we conclude that, in global terms, learning time and good student-teacher relations are not as important as collaborative skills and humility to explain students' success in the PISA test.

Towards Evidence-Based Academic Advising Using Learning Analytics

“…The algorithm stops when the centroids remain the same over two iterations. The most popular and most applied partitional clustering algorithm is the k-means [31], also in learning analytics studies [52]. This algorithm works very well for full and approximately normally distributed data since the sample mean is the most efficient estimator for samples that are drawn from the normal distribution.…”

“…Therefore, the purpose of this article is to propose an automated AA system based on a learning analytics method [9]. While generally concerned with student models to improve learning, learning analytics methods have shifted from the traditional statistical techniques to the more sophisticated data mining techniques that can also cope with a large amount of unstructured data [21,26,45,50,52]. Here, we propose to use one of these techniques, more precisely robust clustering [6,47], to create groups of actual profiles of students concerning their studies.…”

“…Individual student's perspective, from selfregulated learning and study planning point of view without AA interface, was thoroughly addressed in [4]( s e ea l s o [ 5]). By utilizing general student profiles of a higher educational institution we also follow the current trend in learning analytics of not only tackling learning problems of students within a single class-or school-level but to learning analytics problems on an educational organizational level [52]. Such a focus was, for example, recently also addressed by de Freitas et al [22] and Daniel [16].…”

Supporting Institutional Awareness and Academic Advising using Clustered Study Profiles

“…The algorithm stops when the centroids remain the same over two iterations. The most popular and most applied partitional clustering algorithm is the k-means (Jain, 2010), also in learning analytics studies (Saarela and Kärkkäinen, 2017). This algorithm works very well for full and approximately normally distributed data since the sample mean is the most efficient estimator for samples that are drawn from the normal distribution.…”

A Design Methodology for Learning Analytics Information Systems: Informing Learning Analytics Development with Learning Design

“…A substantial volume of literature has been published on using LA as a method to gain insights into learners and their learning [14,30,33]. Although the previous research has significantly contributed to the understanding in the education domain, the studies usually conducted using ad-hoc analyses to answer a specific research question, not gain information that could be used for widespread development and implementation of learning analytics information systems (LAIS).…”