SLP/BUS520 Business Analytics And Decision Making Business Analytics & Intelligence Reporting Final Analysis **Complete Module 4 SLP before Module 4 Case** We have been working with survey data

BUS520 Case 3

Trident University International

BUS520 Business Analytics and Decision Making

June 9, 2024

BUS520 Case 3

Evaluation of employee performance determinants is essential for efficient leadership. This paper will quantitatively evaluate the relationship between job satisfaction and performance through regression analysis. Through analysis of issues relating to job performance, the results could be used to boost employee performance.

Simple Regression 1

Selected variables and outputs

For this analysis, the selected variables are job performance, which is a response, and job satisfaction, which is the independent variable. The reason for selecting these variables is based on the hypothesis that when job satisfaction increases, performance increases relatively. Job satisfaction is an essential issue in the determination of worker’s performance of their duties. When employees are more satisfied, they are more productive and motivated. Below is the regression output after excel analysis showing the relationship between variables.

Interpretation of variables

The R-square result is 0.0002383, which is a determination coefficient that shows the variance proportion of the dependent variable, which could be elaborated using the independent one. The r-square of 0002383 means that 0.024% of job performance could be explained using job satisfaction which is a relatively low variably. Therefore, the relationship between the two variables is poor.

The Adjusted r square is -0.000439, which is essential when there are many variables involved in the process. The r-squared in this case is negative, meaning it is not significant for the data provided and does not improve the data model given.

The standard error is 1.06045, which evaluated the distance between the regression line and observed values. The stand error of 1.06045 shows that the observed job performance reduces from the predicted scores on the regression line by 1.0604 units.

The ANOVA table helps in evaluating the significance of the model. The regression was one which is the total number of predictors. The residual was 216, which is the total number of observations subtracting the predictors. The f-statistic is 0.0515, which is low, meaning that the model does not predict the dependent variable. The significance p-value of 0.8207 means that the data model provided is not statistically significant when a 95% confidence level is used. (Lichtenberg & Şimşek 2017).

Coefficients table

Based on the coefficient table, the intercept is 4.836, which is a statistically significant significant variable. While the job satisfaction of -0.01307 is negative means that when job satisfaction increases, the job performance is reduced. Since the p-value is 0.0820, it means that job satisfaction is not a significant variable.

Implications for management

Since there is a poor relationship between the two variables, management should not use job satisfaction to increase performance when making decisions. There are other factors that could be used to boost performance. For example, extrinsic rewards and recognition for great performance could be used to improve performance. Leaders should actively collect employee’s feedback and use open communication approaches to solve organizational issues. There are also organization predictors for great performance, which are training, and the working environment that could be more engaging to solve performance issues.

Multiple Regression

The variables selected for this section include the dependent as job performance while the independent are the extrinsic, intrinsic and job satisfaction. The variables are essential determinants of how employees perform their jobs. The regression output is as follows;

Interpretation of the results.

The R-square result was 0.02859, which shows that 28.5% of the job performance could be elaborated using other variables like extrinsic, intrinsic, and job satisfaction. Therefore there is a moderate explanation power between the dependent and independent variables.

Secondly, the adjusted R-square is 0.2759, which changes the predictors used in the model. The 27.5% percent is lower than the square, showing that since there are more variables, the fit is better, although it is not substantial.

A standard error of 0.9004 shows that there is a deviation of job performance scored from the predictive score by 0.900 units.

The ANOVA table helps in checking the model’s significance. The regression was 3, which showed the number of predictors. The f-statistic was 28.56, which evaluates the null hypothesis, which is a coefficient of the independent variables. Since the score is higher, it means that the model was significant. The p-value was 1.426E-15, which is very low, meaning that the statistical significance of the model is high. (Kelley & Bolin 2013).

The coefficient table helps in estimating the values of the regression equation. The intercept of 8.581 could be used to show the value of job performance if all predictors were zero. The intercept is statistically significant since the 95% confidence interval. In contrast, the job satisfaction is 0.023 which is positive although not statistically significant with the internal level. The intrinsic motivation is -0.2200, which is a negative variable but statistically significant due to the p-value of 2.685E-17. Finally, the extrinsic motivation value is -0.723, which is a negative value, but it is statistically significant due to the p-value of 3.245E-17. (Bland, 2014).

Implications for the management

Based on the results, the extrinsic and intrinsic motivators have negative relationships with job performance, although they are statistically significant. In contrast, job satisfaction is not a predictor of job performance. Their results have different implications for the management; firstly, the managers should reassess their motivation methods to understand methods that could be used to improve extrinsic and intrinsic motivation. Focusing on intrinsic rewards is essential for management to engage employees. There could also be job satisfaction programs in the organization although it was not a significant variable. These could include professional development and supporting working environments to boost performance.

Conclusion

Simple and multiple regression help identify relationships between different variables provided in case studies. For example, extrinsic and intrinsic motivation negatively affect job performance, while job satisfaction is not significant. The results could be used in an organization’s reevaluating its motivation methods to ensure they are consistent with expected performance.

References

Bland, M. (2014). Multiple regression.

Kelley, K., & Bolin, J. H. (2013). Multiple regression. In Handbook of Quantitative Methods for Educational Research (pp. 69-101). Brill.

Lichtenberg, J. M., & Şimşek, Ö. (2017, August). Simple regression models. In Imperfect decision-makers: Admitting real-world rationality (pp. 13-25). PMLR.