Scribd
Upload
80 views4 pages

Student Performance Regression

The document presents a study analyzing factors that influence academic performance. [1] Descriptive statistics and scatter plots are used to summarize the data and examine relationships between variables like performance index, hours studied, and previous scores. [2] Correlation analysis finds the strongest relationship is between performance index and previous scores. [3] Regression analysis builds a model where performance index is most significantly predicted by hours studied, followed by previous scores, extracurricular activities, sleep, and sample papers practiced. More time spent studying and better previous performance are most important for academic success according to this analysis.

Uploaded by

thinkestan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
80 views4 pages

Student Performance Regression

The document presents a study analyzing factors that influence academic performance. [1] Descriptive statistics and scatter plots are used to summarize the data and examine relationships between variables like performance index, hours studied, and previous scores. [2] Correlation analysis finds the strongest relationship is between performance index and previous scores. [3] Regression analysis builds a model where performance index is most significantly predicted by hours studied, followed by previous scores, extracurricular activities, sleep, and sample papers practiced. More time spent studying and better previous performance are most important for academic success according to this analysis.

Uploaded by

thinkestan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

Business Analytics (BA)

Project Report – Unveiling the Dynamics of


Academic Success

Section – B
Study Group – 4

Report Prepared By:

P23090 – HARKIRAT SINGH

P23106 – NEHA YADAV

P23115 – RAJAT MALI

P23105 – MANISH JAIN

P23085 – DEEPIKA S K
Step 1) Descriptive Stats - Descriptive statistics summarizes or describes the characteristics of a data set.
The main purpose of descriptive statistics is to provide information about a data set. It summarizes the
large amount of data into several useful bits of information. You can refer the excel sheet for the
descriptive analysis of our data.

Step 2) Scatter plot -

Performance Index
120

100
Performance Index

80 f(x) = 1.01383670158306 x − 15.1817994271269


R² = 0.837571164218801
60

40

20

0
30 40 50 60 70 80 90 100 110
Previous Score

In our dataset, we have plotted 2 scatter plots namely, a) PI vs Hours studied, and b) PI vs Previous score.
The regression line is a trend line we use to model a linear trend that we see in a scatterplot, but realize
that some data will show a relationship that isn’t necessarily linear. As you can see in the figure above,
the regression line is given by y = 1.0138x - 15.182 and R² = 0.8376

Step 3) Correlation -

Sample
Question Extra
Hours Previous Sleep Papers Curricular Performanc
Studied Scores Hours Practiced activities e Index
Hours
Studied 1
Previous
Scores -0.01239 1
0.00124 0.00594
Sleep Hours 5 4 1
Sample
Question
Papers 0.01746 0.00788 0.003990
Practiced 3 8 2 1
Extra -
Curricular 0.00387 0.00836 0.023283
activities 3 9 6 0.013102781 1
Performanc 0.91518 0.048105
e Index 0.37373 9 8 0.043268327 0.024524947 1
Step 4) Regression -

4 Checks:

1) R^2 = 0.988 (Very good)


2) Standard Error = 2.03 (Very less comparatively)
3) Significance F = 0
4) P value < 0.05 for every parameter

We also attempted to combine a categorical variable with a continuous variable, such as pairing
extra-curricular studies with hours studied and extra-curricular activities with previous scores, in
an effort to enhance the significance of our models. The exact values can be found in the Excel
sheet. However, it was observed that the p-value was not significant (p-value > 0.05). As a result,
we decided to discard this model.

Interpretation  PI = -34 + 2.85 * Hrs_Studied + 1.02 * Prev_score + 0.48 * Sleep_hrs + 0.19 *


Sample_papers + 0.61 * Extra_curriculars

In the regression model, we interpreted that the Performance Index (PI) is most affected by the
no. of hours studied. It means more you will study, more marks you will get. After no. of hours
studied, Previous scores has the most effect on PI. It means people who scored good in their
past will generally tend to do good in the next exams. After all these, we see that extra curricular
activities also has an effect on PI. It means a person should also do extracurricular activities in
order to have good PI. After extracurriculars, sleep also has an effect on PI. If you have an
adequate amount of sleep you will perform better. Also, we see that sample papers solved has
the least effect on PI according to the data.

Interpretation: In the regression model represented by the equation PI = -34 + 2.85 * Hrs_Studied + 1.02
* Prev_score + 0.48 * Sleep_hrs + 0.19 * Sample_papers + 0.61 * Extra_curriculars, we observe the
following impact on the Performance Index (PI).

The variable with the most significant effect on PI is the number of hours studied. This implies that an
increase in study hours is associated with a higher PI, suggesting that more dedicated study time
contributes to better performance.

Following study hours, the next influential factor is the previous score. Individuals who achieved higher
scores in their previous examinations tend to exhibit better performance in subsequent exams.

Moreover, engagement in extracurricular activities also has a discernible effect on PI. The data suggests
that individuals involved in extracurricular activities tend to have a higher PI.

Additionally, the amount of sleep influences PI, indicating that having an adequate sleep duration is
correlated with better performance.

Lastly, the analysis reveals that the impact of solving sample papers on PI is comparatively lower than
other factors considered in the model.

In summary, the regression model highlights the relative importance of various factors in determining
the Performance Index, with study hours and previous scores playing more substantial roles, followed by
extracurricular activities, sleep, and sample papers.

You might also like