% This file was created with JabRef 2.3.1. % Encoding: UTF-8 @BOOK{Alpaydin2004, title = {Introduction to Machine Learning}, publisher = {MIT Press}, year = {2004}, author = {Ethem Alpaydin}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, owner = {ekrem}, timestamp = {2009.10.29} } @ARTICLE{Auer2006, author = {Auer, Martin and Trendowicz, Adam and Graser, Bernhard and Haunschmid, Ernst and Biffl, Stefan}, title = {Optimal Project Feature Weights in Analogy-Based Cost Estimation: Improvement and Limitations}, journal = {IEEE Trans. Softw. Eng.}, year = {2006}, volume = {32}, pages = {83--92}, issue = {2}, mendeley-groups = {Automatically Imported,Cost} } @MASTERSTHESIS{baker07, author = {Dan Baker}, title = {A Hybrid Approach to Expert and Model-based Effort Estimation}, school = {Lane Department of Computer Science and Electrical Engineering, West Virginia University}, year = {2007}, note = {Available from \url{https://eidr.wvu.edu/etd/documentdata.eTD?documentid=5443}}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000} } @ARTICLE{Bakir2009, author = {Bakir, Ayse and Turhan, Burak and Bener, Ayse}, title = {A new perspective on data homogeneity in software cost estimation: A study in the embedded systems domain}, journal = {Software Quality Journal}, year = {2009}, bdsk-url-1 = {http://dx.doi.org/10.1007/s11219-009-9081-z}, citeulike-article-id = {5109598}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, doi = {10.1007/s11219-009-9081-z}, owner = {ekrem}, posted-at = {2009-07-10 18:58:59}, timestamp = {2009.10.28}, url = {http://dx.doi.org/10.1007/s11219-009-9081-z} } @BOOK{Boehm1981, title = {Software Engineering Economics}, publisher = {Prentice Hall PTR}, year = {1981}, author = {Boehm, Barry W.}, address = {Upper Saddle River, NJ, USA}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, isbn = {0138221227} } @INPROCEEDINGS{MenziesBrady10, author = {Adam Brady and Tim Menzies}, title = {Case-Based Reasoning vs Parametric Models for Software Quality Optimization}, booktitle = {International Conference on Predictive Models in Software Engineering PROMISE'10}, year = {2010}, month = {Sept.}, publisher = {IEEE}, date-added = {2010-08-19 22:30:35 +1000}, date-modified = {2010-08-19 22:35:27 +1000} } @BOOK{Breimann1984, title = {Classification and Regression Trees}, publisher = {Wadsworth and Brooks}, year = {1984}, author = {L. Breiman and J. Friedman and R. Olshen and C. Stone}, address = {Monterey, CA}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-19 13:32:06 +1000}, owner = {ekrem}, timestamp = {2010.08.07} } @INPROCEEDINGS{briand00, author = {Briand, L.C. and Langley, T. and Wieczorek, I.}, title = {A replicated assessment and comparison of common software cost modeling techniques}, booktitle = {Software Engineering, 2000. Proceedings of the 2000 International Conference on}, year = {2000}, pages = {377 -386}, abstract = {Delivering a software product on time, within budget, and to an agreed level of quality is a critical concern for many software organizations. Underestimating software costs can have detrimental effects on the quality of the delivered software and thus on a company's business reputation and competitiveness. On the other hand, overestimation of software cost can result in missed opportunities to funds in other projects. In response to industry demand, a myriad of estimation techniques has been proposed during the last three decades. In order to assess the suitability of a technique from a diverse selection, its performance and relative merits must be compared. The current study replicates a comprehensive comparison of common estimation techniques within different organizational contexts, using data from the European Space Agency. Our study is motivated by the challenge to assess the feasibility of using multi-organization data to build cost models and the benefits gained from company-specific data collection. Using the European Space Agency data set, we investigated a yet unexplored application domain, including military and space projects. The results showed that traditional techniques, namely, ordinary least-squares regression and analysis of variance outperformed analogy-based estimation and regression trees. Consistent with the results of the replicated study no significant difference was found in accuracy between estimates derived from company-specific data and estimates derived from multi-organizational data}, bdsk-file-1 = {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}, bdsk-url-1 = {http://dx.doi.org/10.1109/ICSE.2000.870428}, date-modified = {2010-08-03 16:35:12 +1000}, doi = {10.1109/ICSE.2000.870428}, keywords = {common software cost modeling;cost models;least-squares regression;replicated assessment;software costs;software organizations;software product;software cost estimation;} } @INPROCEEDINGS{briand99, author = {Briand, L. and Pfahl, D.}, title = {Using simulation for assessing the real impact of test coverage on defect coverage}, booktitle = {Software Reliability Engineering, 1999. Proceedings. 10th International Symposium on}, year = {1999}, pages = {148 -157}, abstract = {The use of test coverage measures (e.g. block coverage) to control the software test process has become an increasingly common practice. This is justified by the assumption that higher test coverage helps achieve higher defect coverage and therefore improves software quality. In practice, data often shows that defect coverage and test coverage grow over time, as additional testing is performed. However, it is unclear whether this phenomenon of concurrent growth can be attributed to a causal dependency or if it is coincidental, simply due to the cumulative nature of both measures. Answering such a question is important as it determines whether a given test coverage measure should be monitored for quality control and used to drive testing. Although this is no general answer to the problem above, we propose a procedure to investigate whether any test coverage criterion has a genuine additional impact on defect coverage when compared to the impact of just running additional test cases. This procedure is applicable in typical testing conditions where the software is tested once, according to a given strategy and where coverage measures are collected as well as defect data. We then test the procedure on published data and compare our results with the original findings. The study outcomes do not support the assumption of a causal dependency between test coverage and defect coverage, a result for which several plausible explanations are provided}, bdsk-url-1 = {http://dx.doi.org/10.1109/ISSRE.1999.809319}, date-modified = {2010-08-03 16:35:00 +1000}, doi = {10.1109/ISSRE.1999.809319}, keywords = {causal dependency;defect coverage;quality control;simulation;software quality;software testing;test coverage;program testing;software quality;} } @INPROCEEDINGS{Briand1999, author = {Briand, Lionel C. and El Emam, Khaled and Surmann, Dagmar and Wieczorek, Isabella and Maxwell, Katrina D.}, title = {An assessment and comparison of common software cost estimation modeling techniques}, booktitle = {ICSE '99: Proceedings of the 21st international conference on Software engineering}, year = {1999}, pages = {313--322}, address = {New York, NY, USA}, publisher = {ACM}, bdsk-url-1 = {http://doi.acm.org/10.1145/302405.302647}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, doi = {http://doi.acm.org/10.1145/302405.302647}, isbn = {1-58113-074-0}, location = {Los Angeles, California, United States} } @ARTICLE{chang74, author = {C.L. Chang}, title = {Finding Prototypes for Nearest Neighbor Classifiers}, journal = {IEEE Trans. on Computers}, year = {1974}, pages = {1179-1185}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000} } @INPROCEEDINGS{dimartino07, author = {Di Martino, S. and Ferrucci, F. and Gravino, C. and Mendes, E.}, title = {Comparing Size Measures for Predicting Web Application Development Effort: A Case Study}, booktitle = {Empirical Software Engineering and Measurement, 2007. ESEM 2007. First International Symposium on}, year = {2007}, pages = {324 -333}, month = {20-21}, abstract = {Size represents one of the most important attribute of software products used to predict software development effort. In the past nine years, several measures have been proposed to estimate the size of Web applications, and it is important to determine which one is most effective to predict Web development effort. To this aim in this paper we report on an empirical analysis where, using data from 15 Web projects developed by a software company, we compare four sets of size measures, using two prediction techniques, namely Forward Stepwise Regression (SWR) and Case-Based Reasoning (CBR). All the measures provided good predictions in terms of MMRE, MdMRE, and Pred(0.25) statistics, for both SWR and CBR. Moreover, when using SWR, length measures and Web Objects gave significant better results than Functional measures, however presented similar results to the Tukutuku measures. As for CBR, results did not show any significant differences amongst the four sets of size measures.}, bdsk-url-1 = {http://dx.doi.org/10.1109/ESEM.2007.20}, date-modified = {2010-08-03 16:37:07 +1000}, doi = {10.1109/ESEM.2007.20}, issn = {1938-6451}, keywords = {CBR technique;SWR technique;Web application development effort prediction;case-based reasoning;forward stepwise regression;size measures;software products;Web design;case-based reasoning;regression analysis;software metrics;} } @INPROCEEDINGS{FayIra93Multi, author = {U M Fayyad and I H Irani}, title = {Multi-interval Discretization of Continuous-valued Attributes for Classification Learning}, booktitle = {IJCAI'93}, year = {1993}, pages = {1022--1027}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000} } @ARTICLE{Finnie1997, author = {G. R. Finnie and G. E. Wittig and J-M. Desharnais}, title = {A comparison of software effort estimation techniques: Using function points with neural networks, case-based reasoning and regression models}, journal = {Journal of Systems and Software}, year = {1997}, volume = {39}, pages = {281 - 289}, number = {3}, bdsk-url-1 = {http://www.sciencedirect.com/science/article/B6V0N-3SP2RBC-6/2/4416e483f8e9fa78f01486d8fa6b7693}, bdsk-url-2 = {http://dx.doi.org/10.1016/S0164-1212(97)00055-1}, doi = {DOI: 10.1016/S0164-1212(97)00055-1}, issn = {0164-1212}, url = {http://www.sciencedirect.com/science/article/B6V0N-3SP2RBC-6/2/4416e483f8e9fa78f01486d8fa6b7693} } @ARTICLE{foss03, author = {Foss, T and Stensrud, E and Kitchenham, B and Myrtveit, I}, title = {A simulation study of the model evaluation criterion MMRE}, journal = {IEEE Trans. Softw. Eng.}, year = {2003}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-19 13:28:43 +1000} } @INPROCEEDINGS{gama06, author = {Joao Gama and Carlos Pinto}, title = {Discretization from data streams: applications to histograms and data mining}, booktitle = {SAC '06: Proceedings of the 2006 ACM symposium on Applied computing}, year = {2006}, pages = {662--667}, address = {New York, NY, USA}, publisher = {ACM Press}, note = {Available from \url{http://www.liacc.up.pt/~jgama/IWKDDS/Papers/p6.pdf }}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, isbn = {1-59593-108-2}, location = {Dijon, France} } @ARTICLE{hall03, author = {M.A. Hall and G. Holmes}, title = {Benchmarking Attribute Selection Techniques for Discrete Class Data Mining}, journal = {IEEE Transactions On Knowledge And Data Engineering}, year = {2003}, volume = {15}, pages = {1437-1447}, number = {6}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000} } @INPROCEEDINGS{khaled06, author = {Khaled Hamdan and Hazem El Khatib and John Moses and Peter Smith}, title = {A Software Cost Ontology System for Assisting Estimation of Software Project Effort for Use with Case-Based Reasoning}, booktitle = {Innovations in Information Technology, 2006}, year = {2006}, pages = {1 -5}, month = {nov.}, abstract = {Software project cost and effort estimation has become an increasingly important field in the past years due to the overwhelming role of software in today's global market. Several studies have been dedicated to create models in order to estimate the effort of software development. Most of the studies focused on expert judgment, analogy, parametric and algorithmic methods, bottom-up methods, and top-down methods. Nearly all estimating methods need information about how projects have been implemented in the past. However, this information may be of limited use to estimators, as there are uncertainties in the way that various terms, variables and factors are being interpreted. Two projects that may seem similar may indeed be different in a critical way. Moreover, the uncertainty in assessing similarities and differences means that two different analysts could develop significantly different views and effort estimates. The major contributions this paper makes are: 1) identification of an ontology-based cost estimation process framework for defining the semantics of project development data; 2) introduce the culture factor as it affects the software effort estimation; and 3) development of a software effort estimation ontology system (SEEOS) for use in estimating software project cost in a group of organizations. The system establishes a set of common project parameters between different projects and provides a common understanding of project parameters and their semantics. This system enables project managers to elicit software project features that are semantically compatible with new project requirements. The system has been implemented using Java and a relational database management system and data which have been collected from within UAE companies using an online system}, bdsk-url-1 = {http://dx.doi.org/10.1109/INNOVATIONS.2006.301942}, date-modified = {2010-08-03 16:36:52 +1000}, doi = {10.1109/INNOVATIONS.2006.301942}, keywords = {Java;case-based reasoning;online system;project development data semantics;project requirement;relational database management system;software cost ontology system;software development;software project cost estimation;software project effort estimation;software project feature elicitation;Internet;Java;case-based reasoning;ontologies (artificial intelligence);project management;relational databases;software cost estimation;software development management;} } @INPROCEEDINGS{hihn91, author = {Hihn, J. and Habib-agahi, H.}, title = {Cost estimation of software intensive projects: a survey of current practices}, booktitle = {Software Engineering, 1991. Proceedings., 13th International Conference on}, year = {1991}, pages = {276 -287}, month = {13-16}, abstract = {The authors describe a survey conducted at the Jet Propulsion Laboratory (JPL) to estimate software costs for software intensive projects in JPL's technical divisions. Respondents to the survey described what techniques they use in estimating software costs and, in an experiment, each respondent estimated the size and cost of a specific piece of software described in a design document provided by the authors. It was found that the majority of the technical staff estimating software costs use informal analogy and high-level partitioning of requirements, and that no formal procedure exists for incorporating risk and uncertainty. The technical staff is significantly better at estimating effort than size. However, in both cases the variances are so large that there is a 30% probability that any one estimate can be more than 50% off}, bdsk-url-1 = {http://dx.doi.org/10.1109/ICSE.1991.130653}, date-modified = {2010-08-03 16:34:23 +1000}, doi = {10.1109/ICSE.1991.130653}, keywords = {cost estimation;design document;high-level partitioning;software intensive projects;survey;economics;software engineering;} } @ARTICLE{Hornik1989, author = {Hornik, K. and Stinchcombe, M. and White, H.}, title = {Multilayer feedforward networks are universal approximators}, journal = {Neural Netw.}, year = {1989}, volume = {2}, pages = {359--366}, number = {5}, address = {Oxford, UK, UK}, bdsk-url-1 = {http://dx.doi.org/10.1016/0893-6080(89)90020-8}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, doi = {http://dx.doi.org/10.1016/0893-6080(89)90020-8}, issn = {0893-6080}, owner = {ekrem}, publisher = {Elsevier Science Ltd.}, timestamp = {2010.08.07} } @INPROCEEDINGS{idri02, author = {Idri, A. and Abran, A. and Khoshgoftaar, T.M.}, title = {Estimating software project effort by analogy based on linguistic values}, booktitle = {Software Metrics, 2002. Proceedings. Eighth IEEE Symposium on}, year = {2002}, pages = {21 - 30}, abstract = { Estimation models in software engineering are used to predict some important attributes of future entities such as software development effort, software reliability and programmers' productivity. Among these models, those estimating software effort have motivated considerable research in recent years. The prediction procedure used by these software-effort models can be based on a mathematical function or other techniques such as analogy based reasoning, neural networks, regression trees, and rule induction models. Estimation by analogy is one of the most attractive techniques in the software effort estimation field. However, the procedure used in estimation by analogy is not yet able to handle correctly linguistic values (categorical data) such as 'very low', 'low' and 'high'. We propose a new approach based on reasoning by analogy, fuzzy logic and linguistic quantifiers to estimate software project effort when it is described either by numerical or linguistic values; this approach is referred to as Fuzzy Analogy. This paper also presents an empirical validation of our approach based on the COCOMO'81 dataset.}, bdsk-url-1 = {http://dx.doi.org/10.1109/METRIC.2002.1011322}, date-modified = {2010-08-03 16:35:51 +1000}, doi = {10.1109/METRIC.2002.1011322}, keywords = {COCOMO dataset; Fuzzy Analogy; analogy based reasoning; estimation by analogy; fuzzy logic; linguistic quantifiers; linguistic values; programmer productivity; reasoning by analogy; software engineering estimation models; software metrics; software project effort estimation; software reliability; case-based reasoning; fuzzy logic; project management; software development management; software metrics;} } @ARTICLE{Jor2005a, author = {Jorgensen, M.}, title = {Evidence-based guidelines for assessment of software development cost uncertainty}, journal = {Software Engineering, IEEE Transactions on}, year = {2005}, volume = {31}, pages = {942-954}, number = {11}, note = {0098-5589}, abstract = {Several studies suggest that uncertainty assessments of software development costs are strongly biased toward overconfidence, i.e., that software cost estimates typically are believed to be more accurate than they really are. This overconfidence may lead to poor project planning. As a means of improving cost uncertainty assessments, we provide evidence-based guidelines for how to assess software development cost uncertainty, based on results from relevant empirical studies. The general guidelines provided are: 1) Do not rely solely on unaided, intuition-based uncertainty assessment processes, 2) do not replace expert judgment with formal uncertainty assessment models, 3) apply structured and explicit judgment-based processes, 4) apply strategies based on an outside view of the project, 5) combine uncertainty assessments from different sources through group work, not through mechanical combination, 6) use motivational mechanisms with care and only if greater effort is likely to lead to improved assessments, and 7) frame the assessment problem to fit the structure of the relevant uncertainty information and the assessment process. These guidelines are preliminary and should be updated in response to new evidence.}, date-added = {2010-08-15 20:37:06 +1000}, date-modified = {2010-08-15 20:37:06 +1000}, keywords = {formal specification project management software cost estimation evidence-based guideline formal uncertainty assessment model intuition-based uncertainty assessment mechanical combination project planning software cost estimation software development cost uncertainty software psychology Index Terms- Cost estimation management software psychology uncertainty of software development cost.} } @ARTICLE{Jor2005b, author = {Jorgensen, M.}, title = {Practical guidelines for expert-judgment-based software effort estimation}, journal = {Software, IEEE}, year = {2005}, volume = {22}, pages = {57-63}, number = {3}, note = {0740-7459}, abstract = {This article presents seven guidelines for producing realistic software development effort estimates. The guidelines derive from industrial experience and empirical studies. While many other guidelines exist for software effort estimation, these guidelines differ from them in three ways: 1) They base estimates on expert judgments rather than models. 2) They are easy to implement. 3) They use the most recent findings regarding judgment-based effort estimation. Estimating effort on the basis of expert judgment is the most common approach today, and the decision to use such processes instead of formal estimation models shouldn't be surprising. Simple process changes such as reframing questions can lead to more realistic estimates of software development efforts.}, date-added = {2010-08-15 20:37:06 +1000}, date-modified = {2010-08-15 20:37:06 +1000}, keywords = {project management software cost estimation software development management expert judgment approach project management software development software effort estimation project management software cost estimation software development management} } @ARTICLE{Jor2004a, author = {Jorgensen, M.}, title = {Realism in assessment of effort estimation uncertainty: it matters how you ask}, journal = {Software Engineering, IEEE Transactions on}, year = {2004}, volume = {30}, pages = {209-217}, number = {4}, note = {0098-5589}, abstract = {Traditionally, software professionals are requested to provide minimum-maximum intervals to indicate the uncertainty of their effort estimates. We claim that the traditional request is not optimal and leads to overoptimistic views about the level of estimation uncertainty. Instead, we propose that it is better to frame the request for uncertainty assessment: How likely is it that the actual effort will be more than/less than X? Our claim is based on the results of a previously reported-experiment and field studies in two companies. The two software companies were instructed to apply the traditional and our alternative framing on random samples of their projects. In total, we collected information about 47 projects applying the traditional-framing and 23 projects applying the alternative framing.}, date-added = {2010-08-15 20:37:06 +1000}, date-modified = {2010-08-15 20:37:06 +1000}, keywords = {professional aspects project management risk management software cost estimation software houses alternative framing project risk assessment software companies software cost estimation software professionals software psychology traditional-framing project} } @ARTICLE{Jor2004d, author = {Jorgensen, M. and Carelius, G. J.}, title = {An empirical study of software project bidding}, journal = {Software Engineering, IEEE Transactions on}, year = {2004}, volume = {30}, pages = {953-969}, number = {12}, note = {0098-5589}, abstract = {The study described in this paper reports from a real-life bidding process in which 35 companies were bidding for the same contract. The bidding process consisted of two separate phases: a prestudy phase and a bidding phase. In the prestudy phase, 17 of the 35 bidding companies provided rough price indications based on a brief, incomplete description of user requirements. In the bidding phase, all 35 companies provided bids based on a more complete requirement specification that described a software system with substantially more functionality than the system indicated in the prestudy phase. The main result of the study is that the 17 companies involved in the prestudy phase presented bids that were, on average, about 70 percent higher than the bids of the other companies, although all companies based their bids on the same requirement specification. We propose an explanation for this difference that is consistent with the prospect theory and the precautionary bidding effect. A possible implication of our findings is that software clients should not request early price indications based on limited and uncertain information when the final bids can be based on more complete and reliable information.}, date-added = {2010-08-15 20:37:06 +1000}, date-modified = {2010-08-15 20:37:06 +1000}, keywords = {DP industry contracts formal specification project management risk management software cost estimation software management bidding phase prestudy phase requirement specification software client software project bidding software system} } @INPROCEEDINGS{Jor2005, author = {Jorgensen, M. and Dyba, T. and Kitchenham, B.}, title = {Teaching Evidence-Based Software Engineering to University Students}, year = {2005}, pages = {24-24}, abstract = {Evidence-based software engineering (EBSE) describes a process of identifying, understanding and evaluating findings from research and practice-based experience. This process aims at improving software engineering decisions. For the last three years, EBSE has been taught to university students at Hedmark University College, Rena, Norway. The motivation for the EBSE-course is that it is essential for the students, as future practitioners, to learn how to base important software engineering decisions on the systematic and critical evaluation of the best available evidence. The main purpose of this paper is to inspire and support other universities in their work on developing their own EBSE-courses. For this purpose we report on how our course has been organized and what lessons have been learned. There are currently no studies available on the effects of teaching EBSE and, as far as we know, only we have gained practice-based experience. To acquire more knowledge about the costs and benefits of teaching EBSE we hope that other universities will develop their own EBSE-courses and report their experience.}, date-added = {2010-08-15 20:37:06 +1000}, date-modified = {2010-08-15 20:37:06 +1000} } @INPROCEEDINGS{Jor2005c, author = {Jorgensen, M. and Grimstad, S.}, title = {Over-Optimism in Software Development Projects: The Winner\&\#146;s Curse}, year = {2005}, pages = {280-285}, abstract = {It is well known that software development projects tend to be based on over-optimistic cost estimates. Better knowledge of the sources of this over-optimism is necessary to improve realism in software development project bids and budgets. This paper analyses the effect of the winner&\#146;s curse. The winner&\#146;s curse is a result of the selection of software providers among those with the lowest bid, i.e., those with a tendency towards the highest level of over-optimism. The winner&\#146;s curse has not been extensively analyzed in software cost estimation studies, but is a well known phenomenon in domains such as auctioning. We exemplify the effect of the winner&\#146;s curse with data from a real software development bidding round and simulate how increase in number of bidders and cost uncertainty impact the expected profit. We argue that the winners&\#146; curse is a problem for both clients and providers, and that it may lead to inefficient use of scarce resources. Possible remedies for reduction of negative effects of the winner&\#146;s curse are discussed.}, date-added = {2010-08-15 20:37:06 +1000}, date-modified = {2010-08-15 20:37:06 +1000} } @INPROCEEDINGS{Jor2003, author = {Jorgensen, M. and Molokken, K.}, title = {A preliminary checklist for software cost management}, year = {2003}, pages = {134-140}, abstract = {This paper presents a process framework and a preliminary checklist for software cost management. While most textbooks and research papers on cost estimation look mainly at the estimation phase, our framework and checklist includes the phases relevant to estimation: preparation, estimation, application, and learning. We believe that cost estimation processes and checklists should support these phases to enable high estimation accuracy. The checklist we suggest is based on checklists from a number of sources, e.g., a handbook in forecasting and checklists present in several Norwegian software companies, it needs, however, to be extended through feedback from other researchers and software practitioners. There is also a need for a provision of conditions for meaningful use of the checklist issues and descriptions of the strength and sources of evidence in favor of the checklist issues. The present version of the checklist should therefore be seen as preliminary and we want to get feedback from the conference participants and other readers of this paper for further improvements.}, date-added = {2010-08-15 20:37:06 +1000}, date-modified = {2010-08-15 20:37:06 +1000}, keywords = {software cost estimation software quality risk management software cost estimation checklist software cost management software quality assurance software quality management} } @ARTICLE{Jor2004c, author = {Jorgensen, M. and Molokken-Ostvold, K.}, title = {Reasons for software effort estimation error: impact of respondent role, information collection approach, and data analysis method}, journal = {Software Engineering, IEEE Transactions on}, year = {2004}, volume = {30}, pages = {993-1007}, number = {12}, note = {0098-5589}, abstract = {This study aims to improve analyses of why errors occur in software effort estimation. Within one software development company, we collected information about estimation errors through: 1) interviews with employees in different roles who are responsible for estimation, 2) estimation experience reports from 68 completed projects, and 3) statistical analysis of relations between characteristics of the 68 completed projects and estimation error. We found that the role of the respondents, the data collection approach, and the type of analysis had an important impact on the reasons given for estimation error. We found, for example, a strong tendency to perceive factors outside the respondents' own control as important reasons for inaccurate estimates. Reasons given for accurate estimates, on the other hand, typically cited factors that were within the respondents' own control and were determined by the estimators' skill or experience. This bias in types of reason means that the collection only of project managers' viewpoints will not yield balanced models of reasons for estimation error. Unfortunately, previous studies on reasons for estimation error have tended to collect information from project managers only. We recommend 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.}, date-added = {2010-08-15 20:37:06 +1000}, date-modified = {2010-08-15 20:37:06 +1000}, keywords = {cost-benefit analysis error handling project management software cost estimation software development management software performance evaluation cost estimation data analysis information collection approach interviews performance evaluation project evaluation project management software development software effort estimation error software review statistical analysis} } @INPROCEEDINGS{Jor2000, author = {Jorgensen, M. and Sjoberg, D. I. K. and Kirkeboen, G.}, title = {The prediction ability of experienced software maintainers}, year = {2000}, pages = {93-99}, abstract = {Reports an empirical study of 109 randomly selected maintenance tasks in a large Norwegian software organization. When the maintainers had understood the maintenance task specifications, we asked whether they knew how to solve the task. A high confidence in knowing how to solve the task meant that the maintainers did not expect any major difficulties. Then, immediately after the task was completed, we asked whether there had been any major unexpected difficulties. A comparison of the answers gave the seemingly surprising result that one could not, except for corrective, small and simple maintenance tasks, have more confidence in the predictions of an experienced maintainer than the predictions of an inexperienced maintainer. We believe that better quality of the feedback on previous predictions and more training in probabilistic thinking are important means to improve the prediction abilities of maintainers. Decision aids, such as maintenance effort estimation models, should enable the analysis of previous predictions and stimulate probabilistic thinking}, date-added = {2010-08-15 20:37:06 +1000}, date-modified = {2010-08-15 20:37:06 +1000}, keywords = {personnel software development management software maintenance training Norwegian software organization confidence decision aids experienced software maintainers feedback quality maintenance effort estimation models prediction ability probabilistic thinking software maintenance tasks task specification training unexpected difficulties} } @INPROCEEDINGS{Jor2004b, author = {Jorgensen, M. W. and Ostergaard, E. H. and Lund, H. H.}, title = {Modular ATRON: modules for a self-reconfigurable robot}, year = {2004}, volume = {2}, pages = {2068-2073 vol.2}, abstract = {This paper describes the mechanical and electrical design of a new lattice based self-reconfigurable robot, called the ATRON. The ATRON system consists of several fully self-contained robot modules, each having their own processing power, power supply, sensors and actuators. The ATRON modules are roughly spheres with equatorial rotation. Each module can be connected to up to eight neighbors through four male and four female connectors. In this paper, we describe the realization of the design, both the mechanics and the electronics. Details on power sharing and power consumption is given. Finally, this paper includes a brief outline of our future work on the ATRON system.}, date-added = {2010-08-15 20:37:06 +1000}, date-modified = {2010-08-15 20:37:06 +1000}, keywords = {control system synthesis robots self-adjusting systems modular ATRON power consumption power sharing self-contained robot modules self-reconfigurable robot} } @ARTICLE{Jor2004e, author = {Magne J{\o}rgensen}, title = {A review of studies on expert estimation of software development effort}, journal = {Journal of Systems and Software}, year = {2004}, volume = {70}, pages = {37-60}, number = {1-2}, bibsource = {DBLP, http://dblp.uni-trier.de}, date-modified = {2010-08-17 15:48:01 +1000}, ee = {http://dx.doi.org/10.1016/S0164-1212(02)00156-5} } @ARTICLE{Kadoda2000, author = {Kadoda, G and Cartwright, M and Shepperd, M}, title = {On configuring a case-based reasoning software project prediction system}, journal = {UK CBR Workshop, Cambridge, UK}, year = {2000}, pages = {1--10}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, owner = {ekrem}, timestamp = {2009.10.21} } @INPROCEEDINGS{keung08b, author = {Keung, J.W.}, title = {Theoretical Maximum Prediction Accuracy for Analogy-Based Software Cost Estimation}, booktitle = {Software Engineering Conference, 2008. APSEC '08. 15th Asia-Pacific}, year = {2008}, pages = {495 -502}, month = {3-5}, abstract = {Software cost estimation is an important area of research in software engineering. Various cost estimation model evaluation criteria (such as MMRE, MdMRE etc.) have been developed for comparing prediction accuracy among cost estimation models. All of these metrics capture the residual difference between the predicted value and the actual value in the dataset, but ignore the importance of the dataset quality. What is more, they implicitly assume the prediction model to be able to predict with up to 100% accuracy at its maximum for a given dataset. Given that these prediction models only provide an estimate based on observed historical data, absolute accuracy cannot be possibly achieved. It is therefore important to realize the theoretical maximum prediction accuracy (TMPA) for the given model with a given dataset. In this paper, we first discuss the practical importance of this notion, and propose a novel method for the determination of TMPA in the application of analogy-based software cost estimation. Specifically, we determine the TMPA of analogy using a unique dynamic K-NN approach to simulate and optimize the prediction system. The results of an empirical experiment show that our method is practical and important for researchers seeking to develop improved prediction models, because it offers an alternative for practical comparison between different prediction models.}, bdsk-url-1 = {http://dx.doi.org/10.1109/APSEC.2008.43}, date-modified = {2010-08-03 16:37:20 +1000}, doi = {10.1109/APSEC.2008.43}, issn = {1530-1362}, keywords = {analogy-based software cost estimation;prediction models;software metrics;theoretical maximum prediction accuracy;software cost estimation;software metrics;} } @INPROCEEDINGS{keung2008a, author = {Keung, Jacky}, title = {Empirical evaluation of analogy-x for software cost estimation}, booktitle = {ESEM '08}, year = {2008}, pages = {294--296}, address = {New York, NY, USA}, publisher = {ACM}, bdsk-url-1 = {http://doi.acm.org/10.1145/1414004.1414057}, doi = {http://doi.acm.org/10.1145/1414004.1414057}, isbn = {978-1-59593-971-5}, location = {Kaiserslautern, Germany} } @INPROCEEDINGS{keung08a, author = {Keung, J. and Kitchenham, B.}, title = {Experiments with Analogy-X for Software Cost Estimation}, booktitle = {Software Engineering, 2008. ASWEC 2008. 19th Australian Conference on}, year = {2008}, pages = {229 -238}, month = {26-28}, abstract = {We developed a novel method called Analogy-X to provide statistical inference procedures for analogy- based software effort estimation. Analogy-X is a method to statistically evaluate the relationship between useful project features and target features such as effort to be estimated, which ensures the dataset used is relevant to the prediction problem, and project features are selected based on their statistical contribution to the target variables. We hypothesize that this method can be (1) easily applied to a much larger dataset, and (2) also it can be used for incorporating joint effort and duration estimation into analogy, which was not previously possible with conventional analogy estimation. To test these two hypotheses, we conducted two experiments using different datasets. Our results show that Analogy-X is able to deal with ultra large datasets effectively and provides useful statistics to assess the quality of the dataset. In addition, our results show that feature selection for duration estimation differs from feature selection for joint-effort duration estimation. We conclude Analogy-X allows users to assess the best procedure for estimating duration given their specific requirements and dataset.}, bdsk-url-1 = {http://dx.doi.org/10.1109/ASWEC.2008.4483211}, date-modified = {2010-08-03 16:37:24 +1000}, doi = {10.1109/ASWEC.2008.4483211}, issn = {1530-0803}, keywords = {analogy-X;datasets;duration estimation;feature selection;joint-effort estimation;software cost estimation;statistical inference;software cost estimation;statistical analysis;} } @INPROCEEDINGS{keung2008c, author = {Keung, Jacky and Kitchenham, Barbara}, title = {Experiments with Analogy-X for Software Cost Estimation}, booktitle = {ASWEC '08: Proceedings of the 19th Australian Conference on Software Engineering}, year = {2008}, pages = {229--238}, address = {Washington, DC, USA}, publisher = {IEEE Computer Society}, isbn = {978-0-7695-3100-7} } @ARTICLE{keung2008b, author = {Keung, Jacky Wai and Kitchenham, Barbara A. and Jeffery, David Ross}, title = {Analogy-X: Providing Statistical Inference to Analogy-Based Software Cost Estimation}, journal = {IEEE Trans. Softw. Eng.}, year = {2008}, volume = {34}, pages = {471--484}, number = {4}, address = {Piscataway, NJ, USA}, bdsk-url-1 = {http://dx.doi.org/10.1109/TSE.2008.34}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, doi = {http://dx.doi.org/10.1109/TSE.2008.34}, issn = {0098-5589}, publisher = {IEEE Press} } @ARTICLE{Kirsopp2002, author = {Kirsopp, C. and Shepperd, M.}, title = {Making inferences with small numbers of training sets}, journal = {Software, IEE Proceedings}, year = {2002}, volume = {149}, bdsk-url-1 = {http://dx.doi.org/10.1049/ip-sen}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, doi = {10.1049/ip-sen}, issue = {5}, mendeley-groups = {Automatically Imported}, owner = {ekrem}, timestamp = {2009.11.26} } @ARTICLE{Kirsopp2003, author = {Kirsopp, C. and Shepperd, M. and Premrag, R.}, title = {Case and feature subset selection in case-based software project effort prediction}, journal = {Research and development in intelligent systems XIX: proceedings of ES2002, the twenty-second SGAI International Conference on Knowledge Based Systems and Applied Artificial Intelligence}, year = {2003}, pages = {61}, file = {:C$\backslash$:/Users/ekrem/Documents/My Projects/Tez Related/2009-11-Papers/ES2002\_final.pdf:pdf}, mendeley-groups = {Automatically Imported}, owner = {ekrem}, publisher = {Springer-Verlag New York Inc}, timestamp = {2009.11.26} } @ARTICLE{Kirsopp2002a, author = {Kirsopp, Colin and Shepperd, Martin J. and Hart, John}, title = {Search Heuristics, Case-based Reasoning And Software Project Effort Prediction}, year = {2002}, pages = {1367--1374}, address = {San Francisco, CA, USA}, booktitle = {GECCO '02: Proceedings of the Genetic and Evolutionary Computation Conference}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, isbn = {1-55860-878-8}, publisher = {Morgan Kaufmann Publishers Inc.} } @ARTICLE{Mendes2007, author = {Kitchenham, Barbara and Mendes, Emilia and Travassos, Guilherme H.}, title = {Cross versus Within-Company Cost Estimation Studies: A Systematic Review}, journal = {IEEE Trans. Softw. Eng.}, year = {2007}, volume = {33}, pages = {316--329}, number = {5}, address = {Piscataway, NJ, USA}, bdsk-url-1 = {http://dx.doi.org/10.1109/TSE.2007.1001}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, doi = {http://dx.doi.org/10.1109/TSE.2007.1001}, issn = {0098-5589}, publisher = {IEEE Press} } @ARTICLE{kitchenham01, author = {Kitchenham, B.A. and Pickard, L.M. and MacDonell, S.G. and Shepperd, M.J.}, title = {What accuracy statistics really measure [software estimation]}, journal = {Software, IEE Proceedings}, year = {2001}, volume = {148}, pages = {81 -85}, number = {3}, month = {jun}, abstract = {Provides the software estimation research community with a better understanding of the meaning of, and relationship between, two statistics that are often used to assess the accuracy of predictive models: the mean magnitude relative error (MMRE) and the number of predictions within 25% of the actual, pred(25). It is demonstrated that MMRE and pred(25) are, respectively, measures of the spread and the kurtosis of the variable z, where z=estimate/actual. Thus, z is considered to be a measure of accuracy, and statistics such as MMRE and pred(25) to be measures of properties of the distribution of z. It is suggested that measures of the central location and skewness of z, as well as measures of spread and kurtosis, are necessary. Furthermore, since the distribution of z is non-normal, non-parametric measures of these properties may be needed. For this reason, box-plots of z are useful alternatives to simple summary metrics. It is also noted that the simple residuals are better behaved than the z variable, and could also be used as the basis for comparing prediction systems}, bdsk-url-1 = {http://dx.doi.org/10.1049/ip-sen:20010506}, date-modified = {2010-08-03 16:35:29 +1000}, doi = {10.1049/ip-sen:20010506}, issn = {1462-5970}, keywords = {accuracy measures;accuracy statistics;box-plots;central location measure;kurtosis measure;mean magnitude relative error;nonnormal distribution;nonparametric measures;prediction number;prediction systems comparison;predictive models;residuals;skewness measure;software estimation;spread measure;statistical distribution properties;summary metrics;nonparametric statistics;software cost estimation;software metrics;} } @ARTICLE{kleijnen97, author = {J.P.C. Kliijnen}, title = {Sensitivity Analysis and Related Analyses: a Survey of Statistical Techniques}, journal = {Journal Statistical Computation and Simulation}, year = {1997}, volume = {57}, pages = {111-142}, number = {1--4}, date-added = {2010-08-15 14:42:20 +1000}, date-modified = {2010-08-15 14:42:20 +1000} } @INPROCEEDINGS{Kocaguneli2010, author = {Ekrem Kocaguneli and Gregory Gay and Ye Yang and Tim Menzies and Jacky Keung}, title = {When to Use Data from Other Projects for Effort Estimation}, booktitle = {ASE '10: To Appear In the Proceedings of the twenty-second IEEE/ACM international conference on Automated software engineering}, year = {2010}, address = {New York, NY, USA} } @ARTICLE{kohavi97, author = {Ron Kohavi and George H. John}, title = {Wrappers for Feature Subset Selection}, journal = {Artificial Intelligence}, year = {1997}, volume = {97}, pages = {273-324}, number = {1-2}, url = {citeseer.nj.nec.com/kohavi96wrappers.html} } @INPROCEEDINGS{Kultur2008, author = {Kultur, Yigit and Turhan, Burak and Bener, Ayse Basar}, title = {{ENNA: software effort estimation using ensemble of neural networks with associative memory}}, booktitle = {SIGSOFT '08/FSE-16: Proceedings of the 16th ACM SIGSOFT International Symposium on Foundations of software engineering}, year = {2008}, pages = {330--338}, address = {New York, NY, USA}, file = {:Users/ekremkocaguneli/Library/Application Support/Mendeley Desktop/Downloaded/Kultur, Turhan, Bener - 2008 - ENNA software effort estimation using ensemble of neural networks with associative memory.pdf:pdf}, isbn = {978-1-59593-995-1} } @ARTICLE{Li2008, author = {Li, J and Ruhe, G}, title = {{Analysis of attribute weighting heuristics for analogy-based software effort estimation method AQUA+}}, journal = {Empirical Software Engineering}, year = {2008}, volume = {13}, pages = {63--96}, number = {1}, bdsk-url-1 = {http://www.springerlink.com/index/P821335293V53481.pdf}, file = {:Users/ekremkocaguneli/Library/Application Support/Mendeley Desktop/Downloaded/Li, Ruhe - 2008 - Analysis of attribute weighting heuristics for analogy-based software effort estimation.pdf:pdf}, keywords = {attribute weighting,effort estimation by analogy,feature selection,heuristics,learning,rough set analysis}, publisher = {Springer}, url = {http://www.springerlink.com/index/P821335293V53481.pdf} } @INPROCEEDINGS{LiandRuheAtPRomise2007, author = {Jingzhou Li and Ruhe, G.}, title = {Decision Support Analysis for Software Effort Estimation by Analogy}, booktitle = {International Conference on Predictive Models in Software Engineering PROMISE'07}, year = {2007}, month = {May}, abstract = {Effort estimation by analogy (EBA) is an established method for software effort estimation. For this paper, we understand EBA as a meta-method which needs to be instantiated and customized at different stages and decision points regarding a specific context. Some example decision problems are related to the selection of the similarity measures, the selection of analogs for adaptation or the weighting and selection of attributes. This paper proposes a decision-centric process model for EBA by generalizing the existing EBA methods. Typical decision-making problems are identified at different stages of the process as part of the model. Some existing solution alternatives of the decision-making problems are then studied. The results of the decision support analysis can be used for better understanding of EBA related techniques and for providing guidelines for implementation and customization of general EBA. An example case of the process model is finally presented.}, bdsk-url-1 = {http://dx.doi.org/10.1109/PROMISE.2007.5}, date-modified = {2010-08-19 22:34:05 +1000}, doi = {10.1109/PROMISE.2007.5}, keywords = {decision support analysis;decision-centric process;decision-making problems;software effort estimation by analogy;decision making;decision support systems;software engineering;} } @ARTICLE{Li2006, author = {Li, J. and Ruhe, G.}, title = {A comparative study of attribute weighting heuristics for effort estimation by analogy}, journal = {Proceedings of the 2006 ACM/IEEE international symposium on Empirical software engineering}, year = {2006}, pages = {74}, bdsk-url-1 = {http://portal.acm.org/citation.cfm?id=1159733.1159746}, publisher = {ACM}, url = {http://portal.acm.org/citation.cfm?id=1159733.1159746} } @ARTICLE{Li2009, author = {Li, Y and Xie, M and Goh, T}, title = {A study of project selection and feature weighting for analogy based software cost estimation}, journal = {Journal of Systems and Software}, year = {2009}, volume = {82}, pages = {241--252}, bdsk-url-1 = {http://dx.doi.org/10.1016/j.jss.2008.06.001}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, doi = {10.1016/j.jss.2008.06.001}, issn = {01641212}, issue = {2} } @ARTICLE{Li2009a, author = {Li, Y. and Xie, M. and Goh T.}, title = {A study of the non-linear adjustment for analogy based software cost estimation}, journal = {Empirical Software Engineering}, year = {2009}, pages = {603-643}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000} } @ARTICLE{Lipowezky1998, author = {Lipowezky, U.}, title = {Selection of the optimal prototype subset for 1-NN classification}, journal = {Pattern Recognition Letters}, year = {1998}, volume = {19}, pages = {907-918}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, issue = {10} } @INPROCEEDINGS{Lum2008, author = {Lum, Karen and Menzies, Tim and Baker, Dan}, title = {2CEE, A Twenty First Century Effort Estimation Methodology}, booktitle = {International Society of Parametric Analysis Conference (ISPA / SCEA)}, year = {2008}, month = {May}, date-added = {2010-08-20 15:38:45 +1000}, date-modified = {2010-08-20 15:40:59 +1000} } @INPROCEEDINGS{Lum2008b, author = {Lum, Karen and Menzies, Tim and Baker, Dan}, title = {2CEE, A Twenty First Century Effort Estimation Methodology}, year = {2008}, number = {May}, pages = {12 -- 14}, annote = {While we have found that COCOMO is a very robust model, our results also indicate that local calibration using boot strapping over standard regression, combined with variable reduction (column pruning) andstratification (row pruning using nearest neighbor) is in the vast majority of experiments the most efficient and effective tuning method.}, date-modified = {2010-08-20 15:40:33 +1000}, file = {:Users/ekremkocaguneli/Library/Application Support/Mendeley Desktop/Downloaded/Lum, Menzies, Baker - 2008 - 2CEE, A TWENTY FIRST CENTURY EFFORT ESTIMATION METHODOLOGY.pdf:pdf}, journal = {International Society of Parametric Analysis (ISPA / SCEA)} } @INPROCEEDINGS{macdonell97, author = {MacDonell, S.G. and Shepperd, M.J. and Sallis, P.J.}, title = {Metrics for database systems: an empirical study}, booktitle = {Software Metrics Symposium, 1997. Proceedings., Fourth International}, year = {1997}, pages = {99 -107}, month = {5-7}, abstract = {An important task for any software project manager is to be able to predict and control project size and development effort. Unfortunately, there is comparatively little work, other than function points, that tackles the problem of building prediction systems for software that is dominated by data considerations, in particular systems developed using 4GLs. We describe an empirical investigation of 70 such systems. Various easily obtainable counts were extracted from data models (e.g. number of entities) and from specifications (e.g. number of screens). Using simple regression analysis, a prediction system of implementation size with accuracy of MMRE=21% was constructed. This approach offers several advantages. First there tend to be fewer counting problems than with function points since the metrics we used were based upon simple counts. Second, the prediction systems were calibrated to specific local environments rather than being based upon industry weights. We believe this enhanced their accuracy. Our work shows that it is possible to develop simple and useful local prediction systems based upon metrics easily derived from functional specifications and data models, without recourse to overly complex metrics or analysis techniques. We conclude that this type of use of metrics can provide valuable support for the management and control of 4GL and database projects}, bdsk-url-1 = {http://dx.doi.org/10.1109/METRIC.1997.637170}, date-modified = {2010-08-03 16:34:44 +1000}, doi = {10.1109/METRIC.1997.637170}, keywords = {4GLs;counting problems;data considerations;data models;database project management;database system metrics;empirical study;function points;functional specifications;implementation size;local prediction systems;prediction system;prediction systems;project size;simple regression analysis;software project manager;data structures;formal specification;project management;software metrics;software reliability;statistical analysis;} } @INPROCEEDINGS{martin05, author = {Martin, C.L. and Pasquier, J.L. and Yanez, C.M. and Tornes, A.G.}, title = {Software development effort estimation using fuzzy logic: a case study}, booktitle = {Computer Science, 2005. ENC 2005. Sixth Mexican International Conference on}, year = {2005}, pages = {113 - 120}, month = {26-30}, abstract = { Software estimation has been identified as one of the three great challenges for half-century-old computer science. Developers should be able to achieve practices containing effort estimation based on their own programs. New paradigms as fuzzy logic may offer an alternative for software effort estimation. This paper describes an application whose results are compared with those of a multiple regression. A subset of 41 modules developed from ten programs are used as data. Result shows that the value of MMRE (an aggregation of magnitude of relative error, MRE) applying fuzzy logic was slightly higher than MMRE applying multiple regression; while the value of Pred(20) applying fuzzy logic was slightly higher than Pred(20) applying multiple regression. Moreover, six of 41 MRE was equal to zero (without any deviation) when fuzzy logic was applied (not any similar case was presented when multiple regression was applied).}, bdsk-url-1 = {http://dx.doi.org/10.1109/ENC.2005.47}, date-modified = {2010-08-03 16:36:41 +1000}, doi = {10.1109/ENC.2005.47}, issn = {1550-4069}, keywords = {fuzzy logic; multiple regression; relative error; software development; software effort estimation; fuzzy logic; regression analysis; software metrics;} } @INPROCEEDINGS{mendes00, author = {Mendes, E. and Counsell, S.}, title = {Web development effort estimation using analogy}, booktitle = {Software Engineering Conference, 2000. Proceedings. 2000 Australian}, year = {2000}, pages = {203 -212}, abstract = {Although estimating the effort required in developing Web applications is a difficult task, accurate estimates of development effort have an important role to play in the successful management of Web development projects. In software development work to date, emphasis has focused on algorithmic cost models such as COCOMO and function points. Two disadvantages of these models are firstly, the need for calibration of a model for each individual measurement environment and, secondly, the variable accuracy levels achieved even after calibration. The paper describes the use of estimation by analogy to calculate the development effort of Web applications. Two datasets containing empirical Web development data were used in the case study. One set contained data relating to forty-one novice developers, the other to twenty-nine experienced developers. The ANGEL tool supporting the automatic collection, storage and identification of the most analogous projects was used as a basis for estimating effort required for a new project. Results show estimation by analogy to be a promising alternative to algorithmic techniques}, bdsk-url-1 = {http://dx.doi.org/10.1109/ASWEC.2000.844577}, date-modified = {2010-08-03 16:35:06 +1000}, doi = {10.1109/ASWEC.2000.844577}, keywords = {ANGEL tool;Web applications;Web development effort estimation;Web development projects;algorithmic cost models;analogous projects;analogy based estimation;automatic collection;calibration;datasets;development effort;empirical Web development data;measurement environment;novice developers;software development work;variable accuracy levels;distributed programming;information resources;project management;software cost estimation;software development management;} } @INPROCEEDINGS{mendes_04, author = {Mendes, Emilia and Kitchenham, Barbara}, title = {Further Comparison of Cross-Company and Within-Company Effort Estimation Models for Web Applications}, booktitle = {METRICS '04: Proceedings of the Software Metrics, 10th International Symposium}, year = {2004}, pages = {348--357}, address = {Washington, DC, USA}, publisher = {IEEE Computer Society}, bdsk-url-1 = {http://dx.doi.org/10.1109/METRICS.2004.24}, date-modified = {2010-08-15 12:40:33 +1000}, doi = {http://dx.doi.org/10.1109/METRICS.2004.24}, isbn = {0-7695-2129-0} } @INPROCEEDINGS{mendes_05, author = {Mendes, Emilia and Lokan, Chris and Harrison, Robert and Triggs, Chris}, title = {A Replicated Comparison of Cross-Company and Within-Company Effort Estimation Models Using the ISBSG Database}, booktitle = {METRICS '05: Proceedings of the 11th IEEE International Software Metrics Symposium}, year = {2005}, pages = {36}, address = {Washington, DC, USA}, publisher = {IEEE Computer Society}, bdsk-url-1 = {http://dx.doi.org/10.1109/METRICS.2005.4}, date-modified = {2010-08-15 12:41:05 +1000}, doi = {http://dx.doi.org/10.1109/METRICS.2005.4}, isbn = {0-7695-2371-4} } @INPROCEEDINGS{mendes02b, author = {Mendes, E. and Mosley, N.}, title = {Further investigation into the use of CBR and stepwise regression to predict development effort for Web hypermedia applications}, booktitle = {Empirical Software Engineering, 2002. Proceedings. 2002 International Symposium n}, year = {2002}, pages = {79 - 90}, abstract = { To date studies using CBR for Web hypermedia effort prediction have not applied adaptation rules to adjust effort according to a given criterion. In addition, when applying n-fold cross-validation, their analysis has been limited to a maximum of three training sets, which according to recent studies, may lead to untrustworthy results. This paper has therefore two objectives. The first is to further investigate the use of CBR for Web hypermedia effort prediction by comparing the prediction accuracy of eight CBR techniques, of which three have previously been compared. The second objective is to compare the prediction accuracy of the best CBR technique against stepwise regression, using a twenty-fold cross-validation. All prediction accuracies were measured using Mean Magnitude of Relative Error (MMRE), Median Magnitude of Relative Error, Prediction at level 1 (1=25%), and boxplots of the residuals. One dataset was used in the estimation process and, according to all measures of prediction accuracy, stepwise regression showed the best prediction accuracy.}, bdsk-url-1 = {http://dx.doi.org/10.1109/ISESE.2002.1166928}, date-modified = {2010-08-03 16:36:08 +1000}, doi = {10.1109/ISESE.2002.1166928}, keywords = {Web hypermedia; case based reasoning; dataset; development effort; mean magnitude of relative error; median magnitude of relative error; n-fold cross-validation; prediction accuracy; stepwise regression; Internet; case-based reasoning; hypermedia; software engineering;} } @INPROCEEDINGS{mendes02a, author = {Mendes, E. and Watson, I. and Triggs, C. and Mosley, N. and Counsell, S.}, title = {A comparison of development effort estimation techniques for Web hypermedia applications}, booktitle = {Software Metrics, 2002. Proceedings. Eighth IEEE Symposium on}, year = {2002}, pages = {131 - 140}, abstract = { Several studies have compared the prediction accuracy of different types of techniques with emphasis placed on linear and stepwise regressions, and case-based reasoning (CBR). We believe the use of only one type of CBR technique may bias the results, as there are others that can also be used for effort prediction. This paper has two objectives. The first is to compare the prediction accuracy of three CBR techniques to estimate the effort to develop Web hypermedia applications. The second objective is to compare the prediction accuracy of the best CBR technique, according to our findings, against three commonly used prediction models, namely multiple linear regression, stepwise regression and regression trees. One dataset was used in the estimation process and the results showed that different measures of prediction accuracy gave different results. MMRE and MdMRE showed better prediction accuracy for multiple regression models whereas box plots showed better accuracy for CBR.}, bdsk-url-1 = {http://dx.doi.org/10.1109/METRIC.2002.1011332}, date-modified = {2010-08-03 16:36:14 +1000}, doi = {10.1109/METRIC.2002.1011332}, keywords = {case-based reasoning; effort prediction models; multiple regression models; prediction accuracy; project management; software projects; web hypermedia; case-based reasoning; hypermedia; project management; software cost estimation; software development management;} } @ARTICLE{Mendes2003, author = {Emilia Mendes and Ian D. Watson and Chris Triggs and Nile Mosley and Steve Counsell}, title = {A Comparative Study of Cost Estimation Models for Web Hypermedia Applications}, journal = {Empirical Software Engineering}, year = {2003}, volume = {8}, pages = {163-196}, number = {2}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000} } @ARTICLE{Menzies2006, author = {Menzies, Tim and Chen, Zhihao and Hihn, Jairus and Lum, Karen}, title = {Selecting Best Practices for Effort Estimation}, journal = {IEEE Trans. Softw. Eng.}, year = {2006}, volume = {32}, pages = {883--895}, bdsk-url-1 = {http://dx.doi.org/10.1109/TSE.2006.114}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, doi = {10.1109/TSE.2006.114} } @ARTICLE{menzies11, author = {Menzies, Tim and Jalali, Omid and Hihn, Jairus and Baker, Dan and Lum, Karen}, title = {Stable rankings for different effort models}, journal = {Automated Software Engineering}, year = {2010}, volume = {17}, pages = {409-437}, abstract = {There exists a large and growing number of proposed estimation methods but little conclusive evidence ranking one method over another. Prior effort estimation studies suffered from conclusion instability , where the rankings offered to different methods were not stable across (a) different evaluation criteria; (b) different data sources; or (c) different random selections of that data. This paper reports a study of 158 effort estimation methods on data sets based on COCOMO features. Four best methods were detected that were consistently better than the rest of the other 154 methods. These rankings of best and rest methods were stable across (a) three different evaluation criteria applied to (b) multiple data sets from two different sources that were (c) divided into hundreds of randomly selected subsets using four different random seeds. Hence, while there exists no single universal best effort estimation method, there appears to exist a small number (four) of most useful methods. This result both complicates and simplifies effort estimation research. The complication is that any future effort estimation analysis should be preceded by a selection study that finds the best local estimator. However, the simplification is that such a study need not be labor intensive, at least for COCOMO style data sets.}, affiliation = {West Virginia University Lane Department of Computer Science and Electrical Engineering Morgantown USA}, bdsk-url-1 = {http://dx.doi.org/10.1007/s10515-010-0070-z}, date-added = {2010-08-20 15:34:05 +1000}, date-modified = {2010-08-20 15:36:00 +1000}, issn = {0928-8910}, issue = {4}, keyword = {Computer Science}, publisher = {Springer Netherlands}, url = {http://dx.doi.org/10.1007/s10515-010-0070-z} } @INPROCEEDINGS{Milic2004, author = {Milic, Drazen and Wohlin, Claes}, title = {Distribution Patterns of Effort Estimations}, booktitle = {Euromicro}, year = {2004}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000} } @ARTICLE{Miyazaki1994, author = {Miyazaki, Y. and Terakado, M. and Ozaki, K. and Nozaki, H.}, title = {Robust regression for developing software estimation models}, journal = {J. Syst. Softw.}, year = {1994}, volume = {27}, pages = {3--16}, number = {1}, address = {New York, NY, USA}, bdsk-url-1 = {http://dx.doi.org/10.1016/0164-1212(94)90110-4}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, doi = {http://dx.doi.org/10.1016/0164-1212(94)90110-4}, issn = {0164-1212}, publisher = {Elsevier Science Inc.} } @ARTICLE{myrtveit05, author = {Myrtveit, I. and Stensrud, E. and Shepperd, M.}, title = {Reliability and validity in comparative studies of software prediction models}, journal = {IEEE Trans. Softw. Eng.}, year = {2005}, volume = {31}, pages = {380 - 391} } @ARTICLE{Robson2002, author = {Robson, C}, title = {Real world research: a resource for social scientists and practitioner-researchers}, journal = {Blackwell Publisher Ltd}, year = {2002}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000} } @INPROCEEDINGS{ruhe03, author = {Ruhe, M. and Jeffery, R. and Wieczorek, I.}, title = {Cost estimation for web applications}, booktitle = {Software Engineering, 2003. Proceedings. 25th International Conference on}, year = {2003}, pages = {285 - 294}, month = {3-10}, abstract = {In this paper, we investigate the application of the COBRA trade; method (Cost Estimation, Benchmarking, and Risk Assessment) in a new application domain, the area of web development. COBRA combines expert knowledge with data on a small number of projects to develop cost estimation models, which can also be used for risk analysis and benchmarking purposes. We modified and applied the method to the web applications of a small Australian company, specializing in web development. In this paper we present the modifications made to the COBRA method and results of applying the method In our study, using data on twelve web applications, the estimates derived from our Web-COBRA model showed a Mean Magnitude of Relative Error (MMRE) of 0.17. This result significantly outperformed expert estimates from Allette Systems (MMRE 0.37). A result comparable to Web-COBRA was obtained when applying ordinary least squares regression with size in terms of Web Objects as an independent variable (MMRE 0.23).}, bdsk-url-1 = {http://dx.doi.org/10.1109/ICSE.2003.1201208}, date-modified = {2010-08-03 16:36:20 +1000}, doi = {10.1109/ICSE.2003.1201208}, issn = {0270-5257}, keywords = {COBRA application; Web applications; Web-COBRA model; least squares regression; mean magnitude of relative error; software cost estimation; Internet; distributed object management; regression analysis; software cost estimation;} } @BOOK{Seni2010, title = {Ensemble Methods in Data Mining: Improving Accuracy Through Combining Predictions}, publisher = {Morgan and Claypool Publishers}, year = {2010}, author = {Seni, Giovanni and Elder, John}, isbn = {1608452840, 9781608452842} } @ARTICLE{Sentas2005, author = {Panagiotis Sentas and Lefteris Angelis and Ioannis Stamelos and George Bleris}, title = {Software productivity and effort prediction with ordinal regression}, journal = {Information and Software Technology}, year = {2005}, volume = {47}, pages = {17 - 29}, number = {1}, bdsk-url-1 = {http://www.sciencedirect.com/science/article/B6V0B-4CVR4MP-1/2/72e600ea322bfe4d64b1c90c3a968013}, bdsk-url-2 = {http://dx.doi.org/10.1016/j.infsof.2004.05.001}, doi = {DOI: 10.1016/j.infsof.2004.05.001}, issn = {0950-5849}, keywords = {Ordinal regression}, url = {http://www.sciencedirect.com/science/article/B6V0B-4CVR4MP-1/2/72e600ea322bfe4d64b1c90c3a968013} } @INPROCEEDINGS{shepperd01a, author = {Shepperd, M. and Kadoda, G.}, title = {Using simulation to evaluate prediction techniques [for software]}, booktitle = {Software Metrics Symposium, 2001. METRICS 2001. Proceedings. Seventh International}, year = {2001}, pages = {349 -359}, abstract = {The need for accurate software prediction systems increases as software becomes larger and more complex. A variety of techniques have been proposed, but none has proved consistently accurate. The underlying characteristics of the data set influence the choice of the prediction system to be used. It has proved difficult to obtain significant results over small data sets; consequently, we required large validation data sets. Moreover, we wished to control the characteristics of such data sets in order to systematically explore the relationship between accuracy, choice of prediction system and data set characteristics. Our solution has been to simulate data, allowing both control and the possibility of large validation cases. We compared regression, rule induction and nearest neighbours (a form of case-based reasoning). The results suggest that there are significant differences depending upon the characteristics of the data set. Consequently, researchers should consider the prediction context when evaluating competing prediction systems. We also observed that the more ldquo;messy rdquo; the data and the more complex the relationship with the dependent variable, the more variability in the results. This became apparent since we sampled two different training sets from each simulated population of data. In the more complex cases, we observed significantly different results depending upon the training set. This suggests that researchers will need to exercise caution when comparing different approaches and utilise procedures such as bootstrapping in order to generate multiple samples for training purposes}, bdsk-url-1 = {http://dx.doi.org/10.1109/METRIC.2001.915542}, date-modified = {2010-08-03 16:35:23 +1000}, doi = {10.1109/METRIC.2001.915542}, keywords = {accuracy;bootstrapping;case-based reasoning;data set characteristics;dependent variable relationship;large validation data sets;multiple sample generation;nearest neighbours;prediction context;regression;results variability;rule induction;simulation;software prediction techniques evaluation;training sets;computer aided software engineering;forecasting theory;inference mechanisms;software metrics;statistical analysis;virtual machines;} } @ARTICLE{shepperd01b, author = {Shepperd, M. and Kadoda, G.}, title = {Comparing software prediction techniques using simulation}, journal = {IEEE Trans. Softw. Eng.}, year = {2001}, volume = {27}, pages = {1014 -1022}, number = {11}, month = {nov}, abstract = {The need for accurate software prediction systems increases as software becomes much larger and more complex. We believe that the underlying characteristics: size, number of features, type of distribution, etc., of the data set influence the choice of the prediction system to be used. For this reason, we would like to control the characteristics of such data sets in order to systematically explore the relationship between accuracy, choice of prediction system, and data set characteristic. It would also be useful to have a large validation data set. Our solution is to simulate data allowing both control and the possibility of large (1000) validation cases. The authors compare four prediction techniques: regression, rule induction, nearest neighbor (a form of case-based reasoning), and neural nets. The results suggest that there are significant differences depending upon the characteristics of the data set. Consequently, researchers should consider prediction context when evaluating competing prediction systems. We observed that the more "messy" the data and the more complex the relationship with the dependent variable, the more variability in the results. In the more complex cases, we observed significantly different results depending upon the particular training set that has been sampled from the underlying data set. However, our most important result is that it is more fruitful to ask which is the best prediction system in a particular context rather than which is the "best" prediction system}, bdsk-file-1 = {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}, bdsk-url-1 = {http://dx.doi.org/10.1109/32.965341}, date-modified = {2010-08-03 16:35:38 +1000}, doi = {10.1109/32.965341}, issn = {0098-5589}, keywords = {case-based reasoning;data set characteristics;machine learning;nearest neighbor;neural nets;prediction problem;regression;rule induction;simulation;small data sets;software prediction systems;software prediction technique comparison;training set;case-based reasoning;learning (artificial intelligence);neural nets;software metrics;virtual machines;} } @ARTICLE{shepperd97, author = {Shepperd, M. and Schofield, C.}, title = {Estimating software project effort using analogies}, journal = {IEEE Trans. Softw. Eng.}, year = {1997}, volume = {23}, pages = {736 -743}, number = {11}, month = {nov}, abstract = {Accurate project effort prediction is an important goal for the software engineering community. To date most work has focused upon building algorithmic models of effort, for example COCOMO. These can be calibrated to local environments. We describe an alternative approach to estimation based upon the use of analogies. The underlying principle is to characterize projects in terms of features (for example, the number of interfaces, the development method or the size of the functional requirements document). Completed projects are stored and then the problem becomes one of finding the most similar projects to the one for which a prediction is required. Similarity is defined as Euclidean distance in n-dimensional space where n is the number of project features. Each dimension is standardized so all dimensions have equal weight. The known effort values of the nearest neighbors to the new project are then used as the basis for the prediction. The process is automated using a PC-based tool known as ANGEL. The method is validated on nine different industrial datasets (a total of 275 projects) and in all cases analogy outperforms algorithmic models based upon stepwise regression. From this work we argue that estimation by analogy is a viable technique that, at the very least, can be used by project managers to complement current estimation techniques}, bdsk-file-1 = {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}, bdsk-url-1 = {http://dx.doi.org/10.1109/32.637387}, date-modified = {2010-08-03 16:34:53 +1000}, doi = {10.1109/32.637387}, issn = {0098-5589}, keywords = {ANGEL;COCOMO;Euclidean distance;algorithmic models;estimation by analogy;functional requirements document;industrial datasets;nearest neighbors;personal computer-based tool;project effort prediction;project management;software development method;software engineering;software project effort estimation;stepwise regression;project management;software cost estimation;software development management;software metrics;software tools;} } @INPROCEEDINGS{shepperd96, author = {Shepperd, M. and Schofield, C. and Kitchenham, B.}, title = {Effort estimation using analogy}, booktitle = {Proceedings of the 18th International Conference on Software Engineering}, year = {1996}, pages = {170 -178}, month = {25-29}, abstract = {The staff resources or effort required for a software project are notoriously difficult to estimate in advance. To date most work has focused upon algorithmic cost models such as COCOMO and Function Points. These can suffer from the disadvantage of the need to calibrate the model to each individual measurement environment coupled with very variable accuracy levels even after calibration. An alternative approach is to use analogy for estimation. We demonstrate that this method has considerable promise in that we show it to out perform traditional algorithmic methods for six different datasets. A disadvantage of estimation by analogy is that it requires a considerable amount of computation. The paper describes an automated environment known as ANGEL that supports the collection, storage and identification of the most analogous projects in order to estimate the effort for a new project. ANGEL is based upon the minimisation of Euclidean distance in n-dimensional space. The software is flexible and can deal with differing datasets both in terms of the number of observations (projects) and in the variables collected. Our analogy approach is evaluated with six distinct datasets drawn from a range of different environments and is found to outperform other methods. It is widely accepted that effective software effort estimation demands more than one technique. We have shown that estimating by analogy is a candidate technique and that with the aid of an automated environment is an eminently practical technique}, bdsk-url-1 = {http://dx.doi.org/10.1109/ICSE.1996.493413}, date-modified = {2010-08-03 16:34:35 +1000}, doi = {10.1109/ICSE.1996.493413}, keywords = {ANGEL automated environment;Euclidean distance minimisation;analogous project collection;analogous project identification;analogous project storage;analogy;computation;datasets;effort estimation;n-dimensional space;observations;software project;variables;project management;software cost estimation;software development management;software tools;} } @ARTICLE{Stensrud, author = {Stensrud, Erik and Foss, Tron and Kitchenham, Barbara and Myrtveit, Ingunn}, title = {A Further Empirical Investigation of the Relationship Between MRE and Project Size}, journal = {Empirical Softw. Engg.}, year = {2003}, volume = {8}, pages = {139--161}, number = {2}, address = {Hingham, MA, USA}, bdsk-url-1 = {http://dx.doi.org/10.1023/A:1023010612345}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, doi = {http://dx.doi.org/10.1023/A:1023010612345}, issn = {1382-3256}, publisher = {Kluwer Academic Publishers} } @INPROCEEDINGS{stensrud02, author = {Stensrud, E. and Foss, T. and Kitchenham, B. and Myrtveit, I.}, title = {An empirical validation of the relationship between the magnitude of relative error and project size}, booktitle = {Software Metrics, 2002. Proceedings. Eighth IEEE Symposium on}, year = {2002}, pages = {3 - 12}, abstract = { Cost estimates are important deliverables of a software project. Consequently, a number of cost prediction models have been proposed and evaluated. The common evaluation criteria have been MMRE, MdMRE and PRED(k). MRE is the basic metric in these evaluation criteria. The implicit rationale of using a relative error measure like MRE, rather than an absolute one, is presumably to have a measure that is independent of project size. We investigate if this implicit claim holds true for several data sets: Albrecht, Kemerer, Finnish, DMR and Accenture-ERP. The results suggest that MRE is not independent of project size. Rather, MRE is larger for small projects than for large projects. A practical consequence is that a project manager predicting a small project may falsely believe in a too low MRE. Vice versa when predicting a large project. For researchers, it is important to know that MMRE is not an appropriate measure of the expected MRE of small and large projects. We recommend therefore that the data set be partitioned into two or more subsamples and that MMRE is reported per subsample. In the long term, we should consider using other evaluation criteria.}, bdsk-url-1 = {http://dx.doi.org/10.1109/METRIC.2002.1011320}, date-modified = {2010-08-03 16:35:46 +1000}, doi = {10.1109/METRIC.2002.1011320}, keywords = {Accenture-ERP data set; Albrecht data set; DMR data set; Finnish data set; Kemerer data set; MMRE; MRE; MdMRE; PRED; common evaluation criteria; cost prediction models; magnitude of relative error; relative error measure; software cost estimates; software metrics; software project size; project management; software cost estimation; software development management; software metrics;} } @INPROCEEDINGS{Turhan2007, author = {Turhan, B. and Kutlubay, O. and Bener, A.}, title = {Evaluation of Feature Extraction Methods on Software Cost Estimation}, booktitle = {Empirical Software Engineering and Measurement, 2007. ESEM 2007. First International Symposium on}, year = {2007}, pages = {497 -497}, month = {20-21}, bdsk-url-1 = {http://dx.doi.org/10.1109/ESEM.2007.57}, doi = {10.1109/ESEM.2007.57}, issn = {1938-6451}, keywords = {Isomap;feature extraction method evaluation;nonlinear feature extraction;principal component analysis;software cost estimation performance;support vector regression;feature extraction;principal component analysis;regression analysis;software cost estimation;} } @ARTICLE{Walkerden1999, author = {Walkerden, Fiona and Jeffery, Ross}, title = {An Empirical Study of Analogy-based Software Effort Estimation}, journal = {Empirical Softw. Engg.}, year = {1999}, volume = {4}, pages = {135--158}, number = {2}, address = {Hingham, MA, USA}, bdsk-url-1 = {http://dx.doi.org/10.1023/A:1009872202035}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, doi = {http://dx.doi.org/10.1023/A:1009872202035}, issn = {1382-3256}, publisher = {Kluwer Academic Publishers} } @ARTICLE{Wang2009, author = {Wang, Y. and Song, Q. and MacDonell, S. and Shepperd, M. and Shen, J.}, title = {Integrate the GM(1,1) and Verhulst Models to Predict Software Stage-Effort}, journal = {IEEE Transactions on Systems}, year = {2009}, volume = {39}, pages = {647 - 658}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000}, owner = {ekrem}, timestamp = {2010.01.14} } @INPROCEEDINGS{wu06, author = {Wu, S.I.K.}, title = {The quality of design team factors on software effort estimation}, booktitle = {Service Operations and Logistics, and Informatics, 2006. SOLI '06. IEEE International Conference on}, year = {2006}, pages = {6 -11}, month = {21-23}, abstract = {Over the past ten couple of years, there is a variety of effort models proposed by academicians and practitioners at early stage of software development life cycle. Some addressed that efforts could be predicted using lines of codes (LOC) and COCOMO, others emphasized that it could be made using function point analysis (FPA) or others. The study seeks to develop a model that estimates software effort by studying and analyzing small and medium scale application software. To develop such a model, 50 completed software projects are collected from a software company. With the sample data, design team factors are identified and extracted. By applying them to simple regression analyses, a prediction of software of effort estimates with accuracy of MMRE=9% was constructed. The results give several benefits. First, the estimation problems are minimized due to the simple procedure used in identifying those factors. Second, the predicted software projects are only limited to a specific environment rather than being based upon industry environment. We believe the accuracy of effort estimates can be improved. According to the results analyzed, the work shows that it is possible to build up simple and useful prediction model based on data extracted at the early stage of software development life cycle. We hope this model can provide valuable ideas and suggestions for project designers for planning and controlling software projects in near future}, bdsk-url-1 = {http://dx.doi.org/10.1109/SOLI.2006.328973}, date-modified = {2010-08-03 16:36:57 +1000}, doi = {10.1109/SOLI.2006.328973}, keywords = {application software;design team factor;regression analysis;software development life cycle;software effort estimation;software project;software quality;project management;regression analysis;software cost estimation;software development management;software quality;} } @INPROCEEDINGS{YanWeb02Comparative, author = {Ying Yang and Geoffrey I. Webb}, title = {A Comparative Study of Discretization Methods for Naive-Bayes Classifiers}, booktitle = {Proceedings of PKAW 2002: The 2002 Pacific Rim Knowledge Acquisition Workshop}, year = {2002}, pages = {159-173}, date-added = {2010-08-16 09:34:21 +1000}, date-modified = {2010-08-16 09:34:21 +1000} }