Prediction of software failures through logistic regression

Salem, Ahmed M.; Rekab, Kamel; Whittaker, James A.

doi:10.1016/j.infsof.2003.10.008

Cited by 30 publications

(30 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Logistic regression is a popular statistical technique in which the probability of a dichotomous outcome (such as adoption or non-adoption) is related to a set of explanatory variables that are hypothesized to influence the outcome. It fits a special s-shaped curve, by taking the linear regression form, which could produce any Y-value between minus infinity and plus infinity, and transforming it with the function (Salem et al, 2004). For a logistic regression model, the maximum likelihood estimation (MLE) is used to estimate the unknown parameters (Fienberg, 1983).…”

Section: Methodology Logistic Regression Approachmentioning

confidence: 99%

Influential Factors of VoIP Adoption of Top 500 Export-import Enterprises in Taiwan

Liao

Tseng

2010

CMR

View full text Add to dashboard Cite

Voice over Internet Protocol (VoIP) is a critical innovation technology in the globally oriented business world, which emphasizes flexibility and efficiency as means to reduce operation cost and improve service quality. Yet there is little research in the organization behavior literature investigating what factors affect enterprise decision to adopt VoIP. This study investigated significant determinants of VoIP adoption in the top 500 export-import enterprises in Taiwan. Logistic regression was used to examine four variables: top management support, environment competition, cost and business size. Specifically, the characteristic comparison of VoIP adopters and non-adopters were presented. We concluded by discussing weight ratio of VoIP adoption factor, characteristics of potential adopters and its managerial implications.

show abstract

Section: Methodology Logistic Regression Approachmentioning

confidence: 99%

Influential Factors of VoIP Adoption of Top 500 Export-import Enterprises in Taiwan

Liao

Tseng

2010

CMR

View full text Add to dashboard Cite

show abstract

“…LR finds its application in categorizing the projects based on their cost. This has been successful using historical data of past project which have trained LR model that has been described in [6]. The existence of these applications has motivated us to create a model using evolutionary algorithm to train RBFNN using minimum set of hidden neurons and also create close range so that better classification can be done.…”

Section: Literature Surveymentioning

confidence: 99%

“…After each iteration, the weights are generated using (4). These weights test (6) with the sole motive to minimize the value. The process of iteratively training the weights using RBFNN is stopped when the change in value of (6) is minute or maximum iterations have been achieved.…”

Section: Glr-rbf Learning Algorithmmentioning

confidence: 99%

“…The main approach of GLR-RBF in multiclass learning is combining different statistical and soft computing elements such as Binomial Logistic regression, radial basis function and genetic algorithm [6]. The methodology is a step towards application of hybrid algorithms which works on the rule of detection of correlation in the dataset and reduction of dataset to enhance the basic statistical algorithm efficiency.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Genetically Modified Logistic Regression with Radial Basis Function for Robust Software Effort Prediction

Gaur

2015

Machine Intelligence and Signal Processing

View full text Add to dashboard Cite

Existing logistic regression technique applies log-based function on the dataset and provides the necessary result for analysis. It has been for years for prediction analytics. This project develops a genetically modified evolutionary logistic regression technique using radial basis functions (GLR-RBF). This methodology employs three crucial stages. First stage is an evolutionary stage employing two fitness functions. Initially, the dataset obtained from the repository is modified using Genetic Algorithm (GA), followed by creation and simulation of radial basis neural network (RBFNN). The RBFNN is iteratively trained and simulated. The weight matrix generated in each stage is tested with a fitness function, which define the rule for selection of the best individual that will be appended to the dataset. The process of appending the weight matric to the dataset marks the second stage. In the third stage, the new set of covariates is fed into logistic regression operator which classifies the attributes based on effort response variable. This method has been tested in field of remote sensing image classification and other large dataset. This project also tests this technique for software effort prediction, which is regarded as the crucial activity before the commencement of the software development cycle. The model GLR-RBF was found be competitive when compared with similar standard models. The measure obtained from AUC indicates that GLR-RBF has reached the state-of-the-art.

show abstract

“…Bibi et al [7] and Graves et al [8] applied the regression techniques on the change history of software products in order to accurately predict defect proneness of software modules. Salemet et al [9] applied the regression on the test cases to estimate the number of defects that can be detected. The clustering can be applied on the data specified by experts according to complexity metrics of software products to cluster the fault prone modules and not fault prone modules [10].…”

Section: Introductionmentioning

confidence: 99%

Mining Attributes Patterns of Defective Modules for Object Oriented Software

Mishra¹,

Shukla²

2012

IJCA

View full text Add to dashboard Cite

Defect prediction is the process of predicting the fault prone module using some pre-mined patterns or rules. Several statistical and mathematical strategies have been used in recent past to mine these rules. However, the interpretability of these rules is the matter of concern. In real development process an expert is required to demonstrate the working of mined patterns which prevents the use of these mined patterns in software development process. Considering these facts, in this study we tried to find the combination of attribute-value pair which indicates the bug. These attribute-value pair is known as defect pattern. For defect pattern mining we used GUHA (General Unary Hypothesis Automaton) procedure which is oldest yet very powerful method of pattern mining. The basic idea of GUHA procedure is to mine the entire possible and interesting hypothesis supported by the data in predefined logical form. The experimental results show that the mined patterns can be used as a rule to identify the defective module. Moreover, the mined patterns do not suffer from the interpretability problems.

show abstract

Prediction of software failures through logistic regression

Cited by 30 publications

References 6 publications

Influential Factors of VoIP Adoption of Top 500 Export-import Enterprises in Taiwan

Influential Factors of VoIP Adoption of Top 500 Export-import Enterprises in Taiwan

Genetically Modified Logistic Regression with Radial Basis Function for Robust Software Effort Prediction

Mining Attributes Patterns of Defective Modules for Object Oriented Software

Contact Info

Product

Resources

About