Estimating the Efforts of Mobile Application Development in the Planning Phase Using Nonlinear Regression Analysis

Sergiy Prykhodko,Natalia Prykhodko,Kateryna Knyrik

doi:10.2478/acss-2020-0019

Sergiy Prykhodko, Natalia Prykhodko + Show 1 more

Open Access

https://doi.org/10.2478/acss-2020-0019

Copy DOI

Abstract

Abstract The authors consider the construction of a nonlinear multiple regression model, its confidence and prediction intervals to evaluate the efforts of mobile application development in the planning phase based on the multivariate normalizing transformation and outlier detection. The constructed model is compared to the linear regression model and nonlinear regression models based on the univariate transformations, such as the decimal logarithm, Box–Cox, and Johnson transformation. This model, in comparison with other regression models, has better prediction accuracy.

Highlights

Evaluating software development efforts is one of the important problems during the planning phase for the software project manager to be able to successfully plan the software project
A regression equation does not include random variables [2]–[4] and the effort estimation model based on the function point analysis method [5]
In [8], the authors built a nonlinear multiple regression model to evaluate the efforts of mobile application development in the planning phase based on the multivariate normalizing transformation and outlier detection

Summary

INTRODUCTION

Evaluating software development efforts is one of the important problems during the planning phase for the software project manager to be able to successfully plan the software project. In [8], the authors built a nonlinear multiple regression model to evaluate the efforts of mobile application development in the planning phase based on the multivariate normalizing transformation and outlier detection. As in [8], to improve the nonlinear regression model for estimating the efforts of developing mobile apps in the planning phase, we shall further use the method based on the multivariate normalizing transformation and outlier detection. If the outliers are detected, they are removed, and we repeat all the steps, starting with the first, for new data

CONSTRUCTION OF THE MODEL

COMPARISON OF REGRESSION MODELS

Findings

CONCLUSION