Introduction:

The connection between the chosen dependent variable (Y) and some of the independent variables (X) we decided to use will be explored with the help of the regression analysis conducted. These factors were built into a regression model which we carefully chosen based on their perceived significance to the dependent variable, with the ultimate aim to find the underlying drivers behind the reported data. The class-specific inputs of these variables are Class Demands, Personal Time, and Major Type(-s).

Analysis:

Regression Statistics:

With regard to the regression parameters, it can be shown that the model has a moderate place as a predictive tool – as shown by the Multiple R value of 0.8098. Thus, it is seen that there is a moderately positive association between the cause and effect. Apart from that, the R Square value of 0.6557 reflects the roughly 65.57% explanation of the dependent variable's variation on the basis of the independent variables. However, the 0.6450 Adjusted R^2 value holds a more conservative estimate when taking into account the number of predictors in the given model. The standard error, a constant that represents the average deviation of the real results from the calculated ones, is rather small (standard error equals 0.9445) which illustrates a good fit of the model to the data.

ANOVA:

The ANOVA table shows that the attribution of main significance was given to the regression model. The F-statistic comes to be 60.9514, and the p-value is 0.0000, therefore, the model is determined to be statistically significant. In essence, this states that one or more predictors in the model shown a strong correlation to the dependent variable. This null hypothesis claims that none of the independent variables have any impact on the dependent variables; however, it is discarded.

Coefficients:

The role of each coefficient is examined by taking a closer look at the effect that each independent variable has on the dependent variable. The variable "the intercept" whose value equals 1.7413 reflecting the average of dependent variable when the independent variables equal to zero is found. The values for Class Demands and Personal Time say that the other factors aside, if there is an increase in Class Demands, then there will be a decrease in the dependent variable, whereas with Personal Time an increase will cause the dependent variable to increase. Yet, despite being expected non-significant statistically, the coefficient for Major Type is still a categorical variable and hence appears to be not statistically significant.

Correlation Matrix:

The Correlation matrix manifest the relationships among different pairs of independent variable. However, among the revealed correlations, Class Demands and Personal Time present a weak negatively correlation (-0.098), which mean their values tends to reverse slightly when one of the variables increases. On the other side, Small Time and Major Time have a small positive correlation (0.091), sprouting a slight time tendency to increase or decrease among the two variables together.

Conclusion:

The concluding insights reveal that the variables of Class Demands and Personal Time are the predictors of the independent variable. Yet, deeper research should be done to understand other factors associated with the dependent variable's fluctuations, with a special attention to Major Type. Through the conclusions of analysis, this study contributes to the knowledge and the future projects focused on factors research. Moreover multifactor approach is of great importance when analyzing complicated data sets.