MAT-300
Final Project: Topic and Introduction
John Doe
12/21/2024
Topic: Analyzing Factors Affecting High School Academic Performance
Dataset Location and Description: The dataset is sourced from [Link] (Khaoura, 2024)
and contains comprehensive educational data on high school students. The raw dataset consists
of 2,392 observations, providing a robust sample size for multiple regression analysis. Each
observation represents an individual student and includes measurements across various
academic, demographic, and behavioral dimensions.
Research Aim: The primary research objective is to determine which factors most strongly
predict high school students' academic performance (GPA) and to understand how these factors
interact with each other. This analysis will help identify the relative importance of various
quantitative and qualitative predictors in determining academic success, with particular attention
to the interplay between study habits and support systems.
Variables for Analysis:
Response Variable (Y):
Grade Point Average (GPA): A quantitative measure ranging from 2.0 to 4.0,
representing the student's academic performance
Quantitative Predictors:
Weekly Study Time (hours)
Student Age (years)
Number of Absences (count)
Qualitative Predictors:
Parental Education Level (5 levels: Less than High School, High School, Some College,
Bachelor's Degree, Graduate Degree)
Parental Support Level (5 levels: Very Low, Low, Medium, High, Very High)
Extracurricular Activity Participation (binary: Yes/No)
Sports Participation (binary: Yes/No)
Music Program Participation (binary: Yes/No)
Volunteering Activity (binary: Yes/No)
Tutoring Participation (binary: Yes/No)
This selection of variables will enable a comprehensive analysis that meets the project
requirements while maintaining a manageable scope. The mixture of quantitative and qualitative
predictors will allow for the exploration of both direct effects and potential interactions,
providing insights into the complex relationships between academic performance and various
student characteristics and activities.
The analysis will begin with a first-order main effects model and systematically evaluate the
need for higher-order terms and interactions, ultimately developing a refined model that best
explains the variation in student GPA while maintaining interpretability and practical
significance.
References
Rabie El Kharoua. (2024). 📚 Students Performance Dataset 📚 [Data set]. Kaggle.
[Link]