The post hoc procedure in survival analysis for undergraduate students performance

• Main Authors: Khamis, Azme, Che Hamat, Che Azmeeza, Abdullah, Mohd Asrul Affendi
• Format: Article
• Language: English
• Published: UTHM Publisher 2018
• Subjects: TA168 Systems engineering
• Online Access: http://eprints.uthm.edu.my/5912/1/AJ%202018%20%28650%29.pdf; http://eprints.uthm.edu.my/5912/

Survival analysis is a term used to describe the analysis of data in the form of times from a welldefined time origin until the occurrence of any specific event. In an academic research, the time origin often corresponds to the recruitment of an individual into an experimental study. There are the unmeasured chance of finding a falsely significant difference between two or more groups. Compared more than two groups simultaneously increased the chance of making type 1 error. This paper proposed survival analysis with multiple comparison studies to came up with this issue which is to identify the best undergraduate student performance based on the three certificates of qualification which Diploma, Matriculation and STPM. The undergraduate student achievement data are taken to explain this methodology. Kaplan-Meier plotted with survival comparison test, Log-rank test is used to elaborate the application of the Scheffe test. The result reveals that the undergraduates’ students from STPM have performed better in Degree. The Kaplan-Meier curve shows a significant difference in survival plot among three certificates of qualification. However, p-value adjusted by Scheffe test for paired Matriculation and Diploma was found an insignificant difference. So, this study shows the importance of p-value adjustment with Scheffe test in comparing more than two groups to draw a right conclusion.