Student Performance Measurement on Psychometric Parameters

Introduction

The differences in students’ behavior impact their intellectual performance. Students differ in their learning styles like kinesthetic learners referring to learning by immersing in projects, aural learners, analytical learners and global learners adopting stimulations. Evidences have shown that non-intellectual parameters are highly associated with academic performance of students. The relationship between intelligence, personality, and interests; have been depicted by (Ackerman & Heggestad, 1997), also the impact of personality five factor model on intellectual performance is discussed by (Poropat, 2009). Factors involving self-regulatory learning strategies, motivation and style of learning also impact academic performance of students (Chamorro-Premuzic & Furnham, 2008). (Hamsa, Indiradevi & Kizhakkethottam, 2016) worked on scholastic parameters of undergraduate and graduate students like admission time, submission date of assignment, daily attendance, conduction of examination on scheduled time; to predict their academic performance. Self-regulatory learning strategies (SRLS) and motivation accentuate in recent years. In current era SRLS have become core skill (Anderson Koenig, 2011). Also, SRLS and motivation are not ordinarily included in classroom teaching or lecture and henceforth becomes an important aspect in students learning (Cleary, Gubi, & Prescott, 2010; Wehmeyer, Agran, & Hughes, 2000). The data mining in the field of education is useful at all stages of learning. In schools the students often find challenges while transiting from elementary studies as they differ in expectations and demands (Grolnick & Raftery-Helmer, 2015). In (Shahiri & Husain, 2015) the data mining approaches are applied on psychometric parameters comprising of personality, motivation and learning strategies. The contribution of extracurricular activities and soft skills is discussed in addition to psychometric parameters by (Mishra, Kumar & Gupta, 2014) to measure the scholastic performance of students.

Students lacking in motivation, SRLS and cognitive abilities are incapable of facing academic challenges especially during absenteeism in classes or lectures, in completing multiple assignments and preparing for examination (Blackwell, Trzesniewski & Dweck, 2007; Butler, Beckingham & Lauscher, 2005; Dignath & Büettner, 2008). Learners belonging to low socio-economic status ordinarily deficit in motivation constructs and interpretations (Byrnes, 2003; Steele, 1997). This leads to development of a system that incorporates these constructs in order to enhance learning. Learning style of students involves psychometric parameters, cognitive abilities and emotions; this describes the way students comprehend and react to the training environment (Keefe, 1979). Moreover, the way students opt for a learning environment puts an impact on their intellectual performance (Cassidy, 2004). This raises an interest in studying the relationship of students’ learning behavior with academics (Debdi, Paredes-Velasco & Velázquez-Iturbide, 2016). Further strategies for self-regulation and analysis of data retrieved from online educational environments can be used to predict intellectual performance of students (Pardo, Han & Ellis, 2016).