Statistical approach on grading the student achievement via mixture modelling

Abstract

The purpose of this study is to compare results obtained from assigning letter grades to student achievement. These methods referred as assessment which is takes place at the end of semester period to measure the The conventional and the most popular method to assign grades is the Statistical approaches which used the Standard Deviation and conditional considered to assign the grades. In the conditional Bayesian model, we assume the Normal Mixture distribution where the grades are distinctively separated means and proportions of the Normal Mixture distribution. The problem posterior density of the parameters which is analytically intractable. A solution using the Markov Chain Monte Carlo approach namely Gibbs sampler algorithm. Scale, Standard Deviation and Conditional Bayesian methods are applied to scores of 560 students. The performances of these methods are measured using Loss, Lenient Class Loss and Coefficient of Determination. The results showed Bayesian performed out the Conventional Methods of assigning grades.