Digital Education: An In-Depth Case Study on Online Learning
Remote learning has effectively emerged due to the global lockdown of educational activities caused by the COVID-19 pandemic. As a result, colleges and universities are turning to digital education (Biwer, 2021). Although online learning has undergone significant changes, it is clear that the students either accept or reject this new approach to teaching. Therefore, online course instructors examine the elements that affect students' perception of digital learning (Bollinger, 2004).
Statistical analysis will be completed using the E.O.C. survey dataset to answer the above research questions and establish whether the results are sufficient to form conclusions.
Online learning presents a unique set of challenges to instructors and students. Therefore, the E.O.C. questionnaires are employed to determine if students are satisfied with various aspects of online courses.
The standard deviations of Q1, a measure of the variability in the dataset, were mixed. For example, the standard deviation of Age Group 1 is 6.41, indicating that the data points are closely clustered around the mean with low variability. Nevertheless, the standard deviations of Age Groups 2, 3, and 4 are slightly more significant than that of Age Group 1, suggesting that the data points are more spread out.
The one-way ANOVA method was used to analyze the data, as there were four age groups (1, 2, 3, and 4) and one continuous dependent variable (Q2). As the mean values among the four age groups could be calculated with the ANOVA test, a determination could be made if there is a significant difference in the means of dependent variable values among the four age groups. The one-way ANOVA analysis results indicate no significant difference in the means of Q2 values among the four age groups.
The results show that the number of hours studied per week (Q2) correlates with the student’s age. The p-value is 0.037, less than the typical threshold of 0.05, suggesting that the relationship between the number of hours studied and the student’s age is statistically significant. However, the R-squared value of 0.047 indicates that the student’s age can explain less than 5% of the variation in the number of hours studied. The R-squared number ranges from 0 to 1, with higher values indicating a better fit.
Model adequacy is crucial because if the model is flawed, the conclusions drawn from the model may not be accurate or reliable. As shown above, the differences between the observed and anticipated values are known as residuals. In this residual analysis, the pattern of the residuals is examined to determine whether or not they are typically distributed and have a constant variance.
According to the analysis results, student engagement is significantly and positively predicted by the number of hours studied per week and the student’s age. Predictive analysis is a robust statistical method that offers insightful information about future trends. The one-way ANOVA analysis results of the E.O.C. survey dataset suggest no connection between the student’s age and motivation (hours studied per week). The simple linear regression analysis results of the E.O.C. satisfaction survey dataset found significant correlations, confirming student engagement’s importance and its affecting variables.
As with any study, some limitations affect the statistical results and conclusions that may be made. First, there is an imbalance in the gender ratio, which might skew the analysis findings. Second, the E.O.C. satisfaction survey dataset only evaluates student satisfaction in one class. As a result, further research might expand to cover multiple online courses. Given these constraints, more research is recommended to explore the variables influencing learner satisfaction.