Loading...
Please wait, while we are loading the content...
Similar Documents
An empirical analysis of software effort estimation with outlier elimination (2008)
| Content Provider | CiteSeerX |
|---|---|
| Author | Seo, Yeong-Seok Yoon, Kyung-A. Bae, Doo-Hwan |
| Description | Accurate software effort estimation has always been chal-lenge for software engineering communities. To improve the estimation accuracy of software effort, many studies have focused on effort estimation methods without any consider-ation of data quality, although data quality is one of impor-tant factors to impact to the estimation accuracy. In this pa-per, we investigate the influence of outlier elimination upon the accuracy of software effort estimation through empiri-cal studies applying two outlier elimination methods(Least trimmed square and K-means clustering) and three effort es-timation methods ( Least squares, Neural network and Bayes ian network) associatively. The empirical studies are per-formed using two industry data sets(the ISBSG Release 9 and the Bank data set which consists of the project data performed in a bank in Korea) with or without outlier elim-ination. In: Predictive Models in Software Engineering |
| File Format | |
| Language | English |
| Publisher Date | 2008-01-01 |
| Access Restriction | Open |
| Subject Keyword | Industry Data Set Software Effort Impor-tant Factor Bank Data Empirical Study Least Square Empirical Analysis Empiri-cal Study Bayes Ian Network Estimation Accuracy Isbsg Release Project Data Software Engineering Community Data Quality Neural Network Many Study Elimination Method Software Effort Estimation Effort Es-timation Method Effort Estimation Method Accurate Software Effort Estimation K-means Clustering |
| Content Type | Text |
| Resource Type | Article |
