Paper Example on Regression Analysis of Defective Flash Drives in Manufacturing Co.

Regression analysis is a method used to model and explain the relationship between independent and dependent variables (Faul, Erdfelder, Buchner, & Lang, 2009). In the given dataset, the independent variable is the number of weeks while the dependent variable is the number of defective flash drives produced by a small manufacturing company. The sample consists of thirty observations. Excel Analysis ToolPak was used to perform the regression analysis.

Is your time best spent reading someone else’s essay? Get a 100% original essay FROM A CERTIFIED WRITER!

Save 25%

The regression equation is given by:

number of flashdrives=1.873+1.938 weeks

Where 1.873 is the intercept and 1.938 is the slope of the equation.

The coefficient estimate of the intercept is 1.873 with a test statistic of 0.227 and a p-value of 0.822. The p-value is greater than 0.05 and hence we fail to reject the null hypothesis and conclude that the coefficient of the intercept is not significant at 95% level of significance (Watson, 1955). The 95% confidence is given by [-15.023 18.769]. It is clear that 0 lies in the confidence interval and hence it can be confirmed that the coefficient of the intercept is not significant (Ezekiel, & Fox, 1959).

The coefficient estimate of the slope is 1.938 with a test statistic of 1.682 and a p-value of 0.104. The p-value is greater than 0.05 and hence we fail to reject the null hypothesis and conclude that the coefficient of the slope is not significant at 95% level of significance. The 95% confidence interval is given by [-0.421 4.297]. It is clear that 0 lies in the confidence interval and hence it can be confirmed that the coefficient of the slope is not significant (Kuh, & Meyer, 1955).

The correlation coefficient is given by 0.303 which indicates a weak positive relationship. This means that an increase in the number of weeks leads to an increase in the number of flash drives while a decrease in the number of weeks leads to a decrease in the number of flash drives. The coefficient of determination is given by 0.0918 which means that only 9.18% of the variation in the number of flash drives is explained by the estimated regression equation. This means that the model does not fit the data well (Bewick, Cheek, & Ball, 2003).

In conclusion, it is clear that the number of weeks is not a good predictor of the number of flash drives produced. The number of flash drives produced could be influenced by several other factors.

References

Bewick, V., Cheek, L., & Ball, J. (2003). Statistics review 7: Correlation and regression. Critical care, 7(6), 451. Retrieved from: https://link.springer.com/article/10.1186/cc2401

Ezekiel, M., & Fox, K. A. (1959). Methods of correlation and regression analysis: linear and curvilinear. Retrieved from: https://psycnet.apa.org/record/1960-06763-000

Faul, F., Erdfelder, E., Buchner, A., & Lang, A. G. (2009). Statistical power analyses using G* Power 3.1: Tests for correlation and regression analyses. Behavior research methods, 41(4), 1149-1160. Retrieved from: https://link.springer.com/article/10.3758/BRM.41.4.1149

Kuh, E., & Meyer, J. R. (1955). Correlation and regression estimates when the data are ratios. Econometric, Journal of the Econometric Society, 400-416. Retrieved from: https://books.google.com/books?hl=en&lr=&id=VkY5DQAAQBAJ&oi=fnd&pg=PP1&dq=Correlation+and+Regression&ots=jsR5zDq3P6&sig=6bdi7ztubqzSlY94hm95kJjkQIo

Watson, G. S. (1955). Serial correlation in regression analysis. I. Biometrika, 42(3/4), 327-341. Retrieved from: https://www.jstor.org/stable/2333382