Regression Models of Software Development Effort Estimation Accuracy and Bias

  title={Regression Models of Software Development Effort Estimation Accuracy and Bias},
  author={Magne J{\o}rgensen},
  journal={Empirical Software Engineering},
  • M. Jørgensen
  • Published 2004
  • Computer Science
  • Empirical Software Engineering
This paper describes models whose purpose is to explain the accuracy and bias variation of an organization’s estimates of software development effort through regression analysis. We collected information about variables that we believed would affect the accuracy or bias of estimates of the performance of tasks completed by the organization. In total, information about 49 software development tasks was collected. We found that the following conditions led to inaccuracies in estimates: (1… Expand
Reasons for software effort estimation error: impact of respondent role, information collection approach, and data analysis method
It is recommended that software companies combine estimation error information from in-depth interviews with stakeholders in all relevant roles, estimation experience reports, and results from statistical analyses of project characteristics. Expand
Expert Estimation of Software Development Cost: Learning through Feedback
Four guidelines for improved learning are described and validated that extend the general software experience learning frameworks, e.g., the “experience factory” framework, with estimation specific learning guidelines and made the estimation accuracy feedback significantly more useful for improvement of estimation performance through feedback. Expand
Software Effort Estimation with Multiple Linear Regression: Review and Practical Application
The stepwise Multiple Linear Regression (MLR) technique was selected and used for the software development and software testing processes and the results achieved with MLR were compared with the estimates provided by the area expert. Expand
A Systematic Mapping of Factors Affecting Accuracy of Software Development Effort Estimation
The results provide a useful map to check the assumptions that undergird their estimates, to build comprehensive experience databases, and to adequately staff design projects and the need to argue for specific design decisions is emphasized. Expand
Software Development Effort Estimation - Demystifying and Improving Expert Estimation
The main determinant of many types of software-related investments is the amount of development effort required. The ability of software clients to make investment decisions based on cost estimatesExpand
A Current Assessment of Software Development Effort Estimation
  • Dirk Basten, Werner Mellis
  • Engineering, Computer Science
  • 2011 International Symposium on Empirical Software Engineering and Measurement
  • 2011
The results show that this assumption that inaccurate estimates are the main reason for software development effort estimation is not reasonable in many cases and research needs to find new measures to assess the actual estimation accuracy. Expand
Software Effort Estimation Models Incorporating Expert Judgment
Project management is important to avoid software development failure. Effort estimation is the basis of the management. A mathematical model estimates development effort based on software size andExpand
From origami to software development: a review of studies on judgment-based predictions of performance time.
An integrative review of the literature on judgment-based predictions of performance time, often described as task duration predictions in psychology and as expert-based effort estimation in engineering and management science, challenges earlier results regarding the effects of factors such as complexity/difficulty and experience. Expand
Duration Estimation Models for Open Source Software Projects
For software organizations that rely on Open Source Software (OSS) to develop customer solutions and products, it is essential to accurately estimate how long it will take to deliver the expectedExpand
An Empirical Analysis of Metrics to Predict the Software Defect Fix-Effort
An empirical study which aims to construct defect fix-effort estimation model for a large object-oriented system using a set of product and process metrics as input variables to predict the fix-time/effort (person-hours). Expand


Factors systematically associated with errors in subjective estimates of software development effort: the stability of expert judgment
This paper examines a set of expert-derived estimates for the effort required to develop a collection of modules from a large health-care system and finds distinct relationships that suggest that the estimation process being examined was not unbiased to such characteristics. Expand
A review of studies on expert estimation of software development effort
An extensive review of studies related to expert estimation of software development effort suggests that expert estimation is the most frequently applied estimation strategy for software projects, that there is no substantial evidence in favour of use of estimation models, and that there are situations where the authors can expect expert estimates to be more accurate than formal estimation models. Expand
An effort prediction interval approach based on the empirical distribution of previous estimation accuracy
A software development effort PI approach that is based on the assumption that the estimation accuracy of earlier software projects predicts the effort PIs of new projects is introduced. Expand
A Simulation Tool for Efficient Analogy Based Cost Estimation
This paper presents a statistical simulation tool, namely the bootstrap method, which helps the user in tuning the analogy approach before application to real projects, and shows how measures of accuracy and in particular, confidence intervals, may be computed for the analogy-based estimates, using thebootstrap method with different assumptions about the population distribution of the data set. Expand
An assessment and comparison of common software cost estimation modeling techniques
This paper assess and compare a selection of common cost modeling techniques fulfilling a number of important criteria using a large multi-organizational database in the business application domain and shows that the performances of the modeling techniques considered were not significantly different, with the exception of the analogy-based models which appear to be less accurate. Expand
Better sure than safe? Over-confidence in judgement based software development effort prediction intervals
Results from four studies on human judgement (expert) based PIs of software development effort suggest that the PIs were generally much too narrow to reflect the chosen level of confidence, i.e., that there was a strong over-confidence. Expand
Robust regression for developing software estimation models
A new consistent and robust method called the least-squares of inverted balanced relative errors (LIRS) is proposed and its superiority to the ordinary least-Squares method is demonstrated by use of five actual data sets. Expand
Uncertainty Intervals versus Interval Uncertainty: An Alternative Method for Eliciting Effort Prediction Intervals in Software Development Projects (ProMAC2002予稿集) -- (Risk Management(1))
The observed improvement using this alternative elicitation process can be explained through a simplified interpretation of historical prediction accuracy data, less “conflicting estimation goal”, and less influence from the “anchoring effect”. Expand
Decomposed versus holistic estimates of effort required for software writing tasks
It is suggested that the best level of decomposition at which to elicit work-time estimates may depend on task, judge, and elicitation method, as well as to practical application. Expand
Experience With the Accuracy of Software Maintenance Task Effort Prediction Models
The paper reports experience from the development and use of eleven different software maintenance effort prediction models and suggests the use of prediction models as instruments to support the expert estimates and to analyse the impact of the maintenance variables on the maintenance process and product. Expand