Scribd
Upload
42 views6 pages

Data Analysis of Internet Use & Academic Performance

This chapter analyzes and interprets data from a study on the relationship between internet use and academic performance among 52 university students. Descriptive statistics are provided on respondents' gender, hours of internet use per week, and general weighted average (GWA). A correlation analysis shows a weak positive relationship (0.05) between hours of internet use and GWA. A regression analysis also indicates a weak relationship, with internet use explaining only 0.4% of the variation in GWA. The regression model shows that for every 1 hour increase in internet use, GWA increases by 0.001.

Uploaded by

Raymond Faeldoña
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
42 views6 pages

Data Analysis of Internet Use & Academic Performance

This chapter analyzes and interprets data from a study on the relationship between internet use and academic performance among 52 university students. Descriptive statistics are provided on respondents' gender, hours of internet use per week, and general weighted average (GWA). A correlation analysis shows a weak positive relationship (0.05) between hours of internet use and GWA. A regression analysis also indicates a weak relationship, with internet use explaining only 0.4% of the variation in GWA. The regression model shows that for every 1 hour increase in internet use, GWA increases by 0.001.

Uploaded by

Raymond Faeldoña
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

Chapter 4: presentation, Analysis, and Interpretation of Data

The data gathered were organized, computed, analyzed and interpreted in this

chapter to arrive at the answers sought for the problems in this study.

The areas of investigation considered in this study are 1.) the profile of

respondents 2.) Descriptive analysis of Internet use and Academic performance

3.) Significance difference of Internet use, profile 4.) Significance difference of

Academic performance profile 5.) Correlation of Internet use and Academic

performance 6.) Regression Analysis of Internet use and Academic

performance.

A.) Descriptive Analysis

1.) Profile of Respondents

Table 1: Gender

Gender Frequency Relative


Frequency,%
Male 28 53.85
Female 24 46.15
TOTAL 52 100.00

The table shows the profile of respondents in term of gender. There are 28 Male respondents and a
relative frequency of 53.85 and there are 24 counts of female and a a relative frequency of 46.15. There
are 52 total numbers of respondents in University of the East Caloocan.
2.)Descriptive Analysis of Internet Use

Table 2: Internet Use

Hours

Mean 35.65

Standard Error 4.40

Median 26

Mode 12

Standard Deviation 31.70

Sample Variance 1004.62

Kurtosis 1.81

Skewness 1.41

Range 137

Minimum 3

Maximum 140

Sum 1854

Count 52

The table 2 shows the result of a descriptive analysis of Internet use. The mean rating of internet
use of the respondents of University of the East Caloocan was 35.65 and a standard deviation of 31.70. It
measures the level of hours surfing the internet of the respondents. The median of the internet use was
26 with a kurtosis of 1.81 it’s a normal distribution. The minimum value of internet use was 3 with a
maximum value of 140 with the range of 137 and a total count of 52 respondents.
3.)Descriptive Analysis of

Table 3: General Weighted Average

GWA

Mean 2.14

Standard Error 0.07

Median 2

Mode 2

Standard Deviation 0.54

Sample Variance 0.29

Kurtosis 2.05

Skewness 1.253906

Range 2.66

Minimum 1.34

Maximum 4

Sum 111.53

Count 52

The table 3 shows the result of descriptive analysis in General weighted Average of the respondents of
University of the East Caloocan. The mean rating of their general weighted average was 2.14 and a
standard deviation of 0.54. It measures the level of their academic performance. The median of general
weighted average was 2, with a kurtosis of 2.05 it’s a normal distribution. The minimum value is 1.34
and a maximum of 4, with the range of 2.66 and a total count of 52.
3. Correlation of Internet use and Academic performance

Table12

Hours GWA
Hours 1
GWA 0.05 1

Table 12 gives the coefficients of the one-to-one correlation analysis

between the dependent and independent variables. The correlation coefficient

between the Hours and the General weighted average rating was 0.05. This

tells us that the relationship between the Internet use and the academic

performance of the respondents of University of the East Caloocan it is

substantial relationship.

[Link] Analysis of Internet use and Academic performance

Table 13

Regression Statistics
Multiple R 0.060
R Square 0.004
Adjusted R Square -0.017
Standard Error 0.546
Observations 51
The table shows the regression statistics of the extent of the influence of

computer use to the academic performance of students. The multiple R value is

0.060 which means that there is very weak relationship between the internet

use and academic performance of students.

The R- square is equal to 0.004 which explains that only about 0.40% in

the academic performance of students can be attributed to the variation of the

hours of internet use of respondents. The analysis also yields an adjusted r-

square value of -0.017 and a standard error score of 0.546

Table 14

Standard
Coefficients Error t Stat P-value
Intercept 2.112 0.115 18.398 1.20E-23
84 0.001 0.002 0.418 6.78E-01

The table presents the causal relationship model between the internet

use and academic performance of students. The linear relationship has an

intercept of 2.112 and a slope of 0.001. Therefore the regression model of the

change of the dependent variable, that is, the academic performance of

students as to the change in the independent variable, that is, the time of

internet use of respondents is: Academic performance = 0.001 Internet use

+ 2.112
The figure shows the line-of-best fit that approximates the linear equation

model of the variation in the performance of students based on the time of

students’ usage of internet.

Common questions

Powered by AI

Given the descriptive statistics showing variability in Internet use and the regression analysis revealing a minimal impact on academic performance, an alternative hypothesis could be that 'The impact of Internet use on academic performance is mediated by the purpose and quality of use rather than the quantity of hours used.' This hypothesis acknowledges the potentially nuanced role of Internet engagement in learning, proposing a deeper investigation into how students use the internet academically could reveal different impacts on performance .

The correlation coefficient between Internet use and academic performance is 0.05, indicating a very weak relationship between the two variables. This suggests that the amount of time spent on the internet by students has negligible impact on their academic performance at the University of the East Caloocan .

The skewness value for the general weighted average (GWA) scores is 1.253906, indicating a right-skewed distribution. This suggests that a larger number of respondents have lower GWA scores, which means better academic performance, as the scale likely inverses higher numeric values with lower performance .

The gender composition of the respondents includes 28 males (53.85%) and 24 females (46.15%), totaling 52 participants. This relatively balanced gender distribution suggests that the findings may be somewhat generalizable across different genders, though it is still a limited sample size for making broad claims about the entire population .

The standard error value of 0.546 in the regression statistics indicates the average distance that the observed values fall from the regression line. This suggests a relatively large unexplained variance, highlighting the weak predictive power of Internet use on academic performance. This means that predictions based on this model are likely to have substantial error margins, reducing the reliability of the model for practical applications .

The distribution of Internet use among respondents is characterized by a mean of 35.65 hours and a standard deviation of 31.70, indicating variability in usage. The median is 26, and the mode is 12 hours, suggesting skewness in the distribution. The high kurtosis value of 1.81 indicates a distribution with heavier tails and sharper peak compared to a normal distribution. Skewness is 1.41, implying a right-skewed distribution, meaning more respondents have below-average Internet usage hours .

The descriptive statistical data shows a high range of Internet use (3 to 140 hours), a mean of 35.65, and a standard deviation of 31.70. These figures indicate considerable variability in how respondents use the internet—some may use it sparingly while others extensively. Despite the weak correlation and regression impact on academic performance, this variability could suggest different Internet use patterns (e.g., for study, socialization, or leisure) that might affect learning outcomes differently. Thus, future studies should explore qualitative aspects of Internet use to clarify these patterns' roles .

The adjusted R Square value of -0.017 suggests that the model does not explain any variation in the academic performance data when accounting for the potential complexity of the model. This negative value can occur when the predictor (Internet use) is too weakly related to the dependent variable (academic performance), leading to a poorly fitting model that performs worse than a simple average .

The R-square value of 0.004 indicates that only 0.40% of the variation in academic performance can be explained by the variation in Internet use among the respondents. This minimal explanatory power underscores the limited direct impact of Internet usage on academic outcomes, suggesting that other factors likely play a more significant role in influencing academic performance .

The regression analysis reveals a multiple R value of 0.060, indicating an extremely weak linear relationship between Internet use and academic performance. The R-squared value of 0.004 suggests that only 0.40% of the variation in academic performance can be explained by Internet use, implying that other factors contribute more significantly to academic performance. The intercept of the regression equation is 2.112 with a slope of 0.001, further indicating the minimal impact of internet usage hours on academic performance .

You might also like