Multiple Linear Regression with Applications in College Admission Rate

Abstract

The relevance of comprehending the factors influencing admission rates has increased due to the intensifying rivalry for college admissions. The goal of this research is to use multivariate linear regression analysis to identify and quantify the variables that significantly affect college admission rates. Using information from Kaggle, this study examines several variables, such as the cumulative grade point average (CGPA), the letter of recommendation, the statement of purpose, the university rating of the undergraduate school, the scores on the Graduate Record Examination (GRE) and the Test of English as a Foreign Language (TOEFL). This essay will use python to complete the multiple linear regression model, get the basic dataset as well as preliminary conclusions, and produce and analyze the residuals and fit tables, correlation heatmaps, plot each independent variable's relationship to the dependent variable can help to better understand how these factors affect people’s response or the dependent variable, and evaluate the findings in the results. Ultimately, the results of this study indicate that the chance of admission was mostly predicted by CGPA, GRE, letter of reference, and research experience scores; the likelihood of admission was most significantly influenced by CGPA and GRE scores. By using this information to optimize their admission approach, the institution may utilize the model to assist them determine which factors are most essential in influencing an applicant's chances of being admitted.