Examining the Benefit of L2 Language Proficiency on Academic Performance Using Bayesian Logistic Modeling

Taocheng Jiang¹ZhiYi Zheng²Feng Wang^3*

• ¹Hunan Normal University, Changsha, Hunan Province, China
• ²Newcastle University, Newcastle upon Tyne, North East England, United Kingdom
• ³Shanghai University of Sport, Shanghai, China

The Hanyu Shuiping Kaoshi (HSK), a standardized L2 test, is a mandatory requirement for graduate students in China whose L1 is not Chinese. This study explores theThe potential impactbenefits of higher HSK scores on theinternational students' academic performance during their first year of international graduate students studying study in China. Academic performance may be influenced by multiple factors, including average undergraduate scores and HSK test results remain largely unexplored. Data from 666 graduate students, including their HSK listening, reading, and writing scores as well as their average undergraduate scores, were collected from universities in southern China. Academic performance in the first year of graduate school was represented as a binary variable, with a value of 1 indicating an average score of 85 or above (B+ or higher) and 0 otherwise. Analysis revealed statistically significant correlations among the three HSK test components. A robust Bayesian logistic regression model was developed to estimate the likelihood of achieving good academic performance in the first year based on L2 test scores and undergraduate academic records. The dataset was divided into 80% for model training and 20% for validation. The results demonstrate that the proposed model accurately predicts the probability of achieving a B+ or higher grade in the first year of graduate school. Key Words: L2 standard test, L2 test score, academic performance, Bayesian method