NONLINEAR REGRESSION MODEL FOR ESTIMATING THE SIZE OF WEB-APPLICATIONS CREATED USING THE LARAVEL FRAMEWORK
DOI:
https://doi.org/10.31649/1999-9941-2021-50-1-115-121Keywords:
nonlinear regression model, prediction interval, size estimation, web application, normalizing transformation, non-Gaussian dataAbstract
The three-factor nonlinear regression model to estimate the size of development of web applications created using the Laravel framework, is constructed on the basis of normalization of the four-dimensional non-Gaussian data set (actual size in KLOC; number of classes, sum of average afferent coupling and average efferent coupling; average number of methods) by the Johnson multivariate transformation for SB family. Comparison of the constructed model with the linear regression model and nonlinear regression models based on the decimal logarithm and the Johnson univariate transformation is performed. Thе constructed model, in comparison with other regression models, has a smaller value of the mean magnitude of the relative error and smaller widths of the prediction intervals of nonlinear regression.
References
B. W. Boehm, C. Abts, A. W. Brown, S. Chulani, B. K. Clark, E. Horowitz, R. Madachy, D. J. Reifer, and B. Steece, Software Cost Estimation with COCOMO II. Upper Saddle River, NJ: Prentice Hall PTR, 2000.
H. Zhu, Software Design Methodology: From Principles to Architectural Styles. 1st Edition. Butterworth-Heinemann, Elsevier, 2005.
H. B. K. Tan, Y. Zhao, and H. Zhang, «Estimating LOC for information systems from their conceptual data models», in Proc. of the 28th International Conference on Software Engineering (ICSE '06), Shanghai, China, рp. 321-330, 2006. DOI: doi.org/10.1145/1134285.1134331.
H. B. K. Tan, Y. Zhao, and H. Zhang, «Conceptual data model-based software size estimation for information systems», Transactions on Software Engineering and Methodology, vol. 19, issue 2, article No. 4, October, 2009. DOI: https://doi.org/10.1145/1571629.1571630.
N. V. Prykhodko, and S. B. Prykhodko, «Constructing the non-linear regression models on the basis of multivariate normalizing transformations», Electronic modeling, vol. 40, No. 6, pр. 101−110, 2018.
S. B. Prykhodko, N. V. Prykhodko, T. A. Farionova, M. V. Vorona, «Trokhfaktorna neliniina rehresiina model dlia otsiniuvannia rozmiru Php-zastosunkiv z vidkrytym kodom», Naukovyi zhurnal «Vcheni zapysky Tavriiskoho natsionalnoho universytetu imeni V. I. Vernadskoho. Seriia: Tekhnichni nauky», Tom 31 (70), № 1, s. 124−131, 2020. DOI: doi.org/10.32838/2663-5941/2020.1-1/23.
Olkin, and A. R. Sampson, «Multivariate Analysis: Overview», in International encyclopedia of social & behavioral sciences / N. J. Smelser, P. B. Baltes (eds.) 1st edn. Elsevier, Pergamon, 2001, p. 10240−10247.
K. V. Mardia, «Measures of multivariate skewness and kurtosis with applications», Biometrika, Vol. 57, 1970, p. 519–530. doi.org/10.1093/biomet/57.3.519.
S. Chatterjee, and B. Price, Regression analysis by example. New York USA: John Wiley & Son, 2012.
T. Foss, E. Stensrud, B. Kitchenham, and I. Myrtveit, «A simulation study of the model evaluation criterion MMRE», IEEE Transactions on software engineering, 11(29), pр. 985–995, 2003.
R. A. Johnson, and D. W. Wichern, Applied Multivariate Statistical Analysis. Pearson Prentice Hall, 2007.
Downloads
-
PDF (Українська)
Downloads: 363
