Accessing Individual Students Academic Performance Using Random Effect Analysis(Multilevel Analysis)

作     者：Ekow Ewusi Amissah Nana Kena Frempong Emmanuel DeGraft Johnson Owusu-Ansah 

作者机构：Institute of Statistical Social and Economic Research(ISSER)University of GhanaLegonGhana Department of MathematicsKwame Nkrumah University of Science and Technology(KNUST)KumasiGhana 

出 版 物：《Communications in Mathematics and Statistics》 (数学与统计通讯（英文）)

年 卷 期：2016年第4卷第3期

页      面：341-357页

学科分类：0401[教育学-教育学] 04[教育学] 

基　　金：lt is a pleasure to thank Dr.Rev.William Obeng-Denteh Department of Mathematics Kwame Nkrumah University of Science and'Technology(KNUST)and also Mr.Kojo Ankar-Brewoo ofthe Quality Assurance and Planning Unit(QUAPU)for providing me with the data for my analysis.Mythanks also go to the Department of Mathematics KNUST for permitting me to carry out my research inthe department.I owe my deepest gratitude to my mother Miss Nancy Apagya-Bonney for supporting andfinancing me throughout my tertiary education.I thank my all Mr.Emmanuel Kwesi Sam Aba Apagya-Bonney and family for all the kind words finance and continuous encouragement that always pushed meto work harder 

主　　题：Random effect Random intercept model Random intercept and slopemodel Standard deviation SWA Estimate 

摘      要：Sometimes,people with interest in measuring quality of education take intoaccountlevel in academic performance and various associated ***,an aver-age academic performance is an accustomed way of assessment;however,this studyexamines on individual basis different factors that might have an impact on the acad-emic performance of undergraduate *** on the semester weighted averageof class of 2012 mathematics students were acquired from the Quality Assurance andPlanning Unit and the Examination Office of the Department of Mathematics,KwameNkrumah University of Science and *** main factors considered for thisresearch were entry age,gender,entry aggregate,Ghana education service gradedlevel of senior high school attended and geographical *** statistical methodconsidered was random *** the interaction or variation around the slope washighly insignificant,the random intercept model was the better alternative ahead ofthe random intercept and slope ***,not all the parameter estimatesare significant at a=0.05 level of *** was observed that the differencein geographical location was not significant in the main effect *** where astudent comes from has no influence on their academic ***,entryaggregate,entry age and gender were all ***,the geographical location with regard to the Northern Belt was significant in the linear trend with astandard deviation of approximately 0.712.