Question 1: Multivariate Regression Analysis Objective: Investigate the factors that significantly predict a student's mathematics score. Tasks: 1. Data Preprocessing: . Load the mathnew.csv dataset into R. • Check for missing values and handle them appropriately. • • Convert categorical variables (Gender, Parental Education, SocioEconomic Status) into suitable numerical formats using dummy variables or factor encoding. Standardize the continuous variables (Age, StudyHours, AttendanceRate, Extracurricular) to have a mean of zero and a standard deviation of one. 2. Model Building: . . Construct a multiple linear regression model with MathScore as the dependent variable and the other variables as independent predictors. Include interaction terms between StudyHours and Attendance Rate, and between Socio Economic Status and Parental Education. 3. Model Diagnostics: • . Assess the assumptions of linear regression (linearity, independence, homoscedasticity, normality of residuals). Detect and address multicollinearity among predictors using Variance Inflation Factor (VIF). 4. Model Selection: • Perform stepwise model selection (both forward and backward) based on Akaike Information Criterion (AIC) to identify the most parsimonious model. 5. Interpretation: • Interpret the coefficients of the final model. • Identify which predictors are statistically significant and discuss their practical implications on MathScore. Expected R Tasks: • Data cleaning and transformation using packages like dplyr and tidyr. . Regression modeling using Im(). • Model diagnostics using packages like car for VIF and diagnostic plots. . Stepwise selection using step() function.