Name : BitsID :
Note : As checked in the server, course resources folder is empty not able to find any csv files so
taking statics as mentioned in assignment doc and using the same.
TASK 1: 2020wa
Per
son
al -
Ind
ivid
ual
Us
e
Name : BitsID :
TASK2 : 2020WA
TASK3 : 2020WA
Per
son
al -
Ind
ivid
ual
Us
e
Name : BitsID :
Task4: 2020wa
Per
son
al -
Ind
ivid
ual
Us
e
Name : BitsID :
Task 5 : 2020wa
Per
son
al -
Ind
ivid
ual
Us
e
Name : BitsID :
Task 6 : 2020wa
Report: Analysis of Linear Regression Model for Student Performance in Statistics Courses
Introduction:
In this report, we present the analysis of a linear regression model aimed at understanding the
relationship between mid-semester exam scores and comprehensive exam outcomes among
statistics students. The dataset includes mid-semester exam scores (independent variable) and
comprehensive exam scores (dependent variable) for a random sample of 25 statistics students.
Data Preprocessing:
1. We imported the necessary libraries including numpy, pandas, scikit-learn, and matplotlib.
2. The dataset was loaded from an Excel file and initial exploration was conducted.
3. Missing values were removed from the dataset as part of the data preprocessing phase.
4. The dataset was split into training and test sets following the 70-30 policy.
Model Implementation:
1. We implemented a linear regression model using scikit-learn's `LinearRegression` class.
2. The model was trained on the training data, and predictions were made on the test data.
3. A summary DataFrame was created to provide insights into the actual values, predicted values,
and residuals of the model.
4. Mean Squared Error (MSE) and R-squared value were calculated to evaluate the performance of
the model.
Results:
1. The linear regression model produced predictions for comprehensive exam scores based on mid-
semester exam scores.
2. The Mean Squared Error (MSE) was calculated to be [613.973], indicating the average squared
difference between predicted and actual values.
3. The R-squared value was calculated to be [0.508], indicating the proportion of variance in the
dependent variable that is predictable from the independent variable.
4. The summary DataFrame provided a concise overview of the model's predictions, including actual
values, predicted values, and residuals.
Discussion:
1. The linear regression model showed a [positive/negative] correlation between mid-semester exam
scores and comprehensive exam outcomes.
2. The MSE and R-squared value suggest that the model [performs well/needs improvement] in
predicting comprehensive exam scores based on mid-semester exam scores.
3. Further analysis could include exploring additional factors that may influence student performance
in statistics courses, such as attendance, study habits, and prior academic background.
4. The insights from this analysis can be valuable for academic advisors in identifying students who
may require additional support or intervention to improve their performance in statistics courses.
Conclusion:
The analysis of the linear regression model provides valuable insights into the factors influencing
student performance in statistics courses. By understanding the relationship between mid-semester
exam scores and comprehensive exam outcomes, academic advisors can better support students in
achieving academic success. Further research and analysis can enhance our understanding of
student performance and inform targeted interventions to improve outcomes in statistics education.
Per
son
al -
Ind
ivid
ual
Us
e
