M Setyawati¹, N Chamidah2 and A Kurniawan2

 

¹PhD Student, Faculty of Science and Technology, Airlangga University, Indonesia

²Department of Mathematics, Faculty of Science and Technology, Airlangga University, Indonesia

Corresponding author:  nur-c@fst.unair.ac.id

 

ABSTRACT

 

Scholastic aptitude test (SAT) is one of the tests to enroll the State Islamic Colleges (SIC) in Indonesia. The scholastic aptitude test score is influenced by many factors. They are the percentage of prospective students from public schools that has linear pattern over SAT score, and the percentage of prospective student graduating on the year of registration that has no specific pattern over SAT score. So, in this case SAT score is as response variable, the percentage of prospective students from public schools as parametric component and the percentage of prospective student graduating on the year of registration as nonparametric component are as predictor variables. Therefore, in this paper we model SAT score  affected by both the percentage of prospective students from public schools and the percentage of prospective student graduating on the year of registration by using semiparametric regression model based on truncated spline estimator for longitudinal data. The expected result of this study is to analyze the change behavior pattern of SAT score over time that useful for the Ministry Religious Affair, especially the Directorate General of Islamic Education in improving the quality of SIC as reference for making decision regarding student admission.

 

Keywords: scholastic aptitude test score, State Islamic Collages, semiparametric regression model, truncated spline, longitudinal data.