A. Porter and R. Selby. Evaluating techniques for generating metric-based classification trees. The Journal of Systems and Software, 12(3):209--218, 1990.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....and their Application Classification trees have been used frequently in previous software engineering research. For example, classification trees have been used to classify modules as fault prone or not fault prone [9] and to predict components for which development e#ort is likely to be high [14, 20]. In our context, we use classification trees to predict whether a certain testing scenario facilitates the use of a prioritization technique by measuring program, test suite, and change characteristics that hold for that particular scenario. Classification trees can help with this for several ....

A. Porter and R. Selby. Evaluating techniques for generating metric-based classification trees. The Journal of Systems and Software, 12(3):209--218, 1990.

....is rejected from further consideration [38] 6.5.2 Sensitivity and Specificity Some authors, such as [1] report the sensitivity and specificity values directly. 6.5. 3 Proportion Correct Most authors will report the proportion correct value, for example [1] 38] 49] also called correctness in [46][47] This is an intuitively appealing measure of prediction performance since it is easy to interpret. 6.5.4 Type I and Type II Misclassifications These two evaluative measures are used in a number of different studies, such as [29] 31] 35] 32] The Type I misclassification rate is f 1 , and ....

....studies, such as [29] 31] 35] 32] The Type I misclassification rate is f 1 , and the Type II misclassification rate is s 1 . 6.5.5 Completeness and Correctness Correctness and completeness are also frequently used measures for evaluating binary classifiers. Completeness, as defined in [7][46], is equal to the senstivity. Correctness is the true positive rate [7] 9] 10] 11] also called consistency in [46] 47] and is defined as: 2 n The logic of considering correctness is that it gives an indication of how many of the High risk predictions made by the classifier are actually ....

[Article contains additional citation context not shown here]

A. Porter and R. Selby: "Evaluating Techniques for Generating Metric-Based Classification Trees". In Journal of Systems and Software, 12:209-218, 1990.

....failures or costly defect correction later in the life cycle. 3.2.2. 3 Common Measures of Accuracy Common measures of accuracy for binary classifiers that have been applied in software engineering are the proportion correct value, reported in for example [1] 41] 56] also called correctness in [51][52] completeness, for example [9] 51] which is equal to the senstivity) correctness which is the true positive rate [9] 12] 13] 14] also called consistency in [51] 52] the Kappa coefficient [12] 14] Type I and Type II misclassifications [37] 38] 40] 39] Type I misclassification rate is f ....

....later in the life cycle. 3.2.2. 3 Common Measures of Accuracy Common measures of accuracy for binary classifiers that have been applied in software engineering are the proportion correct value, reported in for example [1] 41] 56] also called correctness in [51] 52] completeness, for example [9][51] (which is equal to the senstivity) correctness which is the true positive rate [9] 12] 13] 14] also called consistency in [51] 52] the Kappa coefficient [12] 14] Type I and Type II misclassifications [37] 38] 40] 39] Type I misclassification rate is f 1 , and the Type II misclassification ....

[Article contains additional citation context not shown here]

A. Porter and R. Selby: "Evaluating Techniques for Generating Metric-Based Classification Trees". In Journal of Systems and Software, 12:209-218, 1990.

....of DT and ANN based estimation systems is that they are adaptable and nonparametric. The result reported in [3] indicates that the improved predictive performance can be obtained through the use of Bayesian analysis. Additional research on ML based software effort estimation can be found in [2,14,15,16]. Software defect prediction Bayesian belief networks are used in [4] to predict software defects. Though the system reported is only a prototype, it shows the potential BBN has in incorporating multiple perspectives on defect prediction into a single, unified model. Variables in the prototype ....

A. Porter and R. Selby, "Evaluating techniques for generating metric-based classification trees," J. Systems Software, Vol. 12, July 1990, pp. 209-218.

....tree algorithm, then the predictions are binary. A plethora of coefficients have been used in the literature for evaluating binary predictions, for example, a chi square test [1] 5] 82] 108] sensitivity and specificity [1] proportion correct [1] 82] 107] also called correctness in [98][99] type I and type II misclassifications [70] 71] true positive rate [11] 15] 18] and Kappa [15] 18] A recent comprehensive review of these measures [35] recommended that they should not be used as evaluative measures because either: i) the results they produce depend on the proportion of ....

A. Porter and R. Selby, "Evaluating Techniques for Generating Metric-Based Classification Trees," Journal of Systems and Software, vol. 12, pp. 209-218, 1990.

....approaches that can be used for evaluating prediction accuracy. 3.2.3. 1 Common Measures of Accuracy Common measures of accuracy for binary classifiers that have been applied in software engineering are the proportion correct value, reported in for example [1] 45] 63] also called correctness in [57][58] completeness, for example [9] 57] which is equal to the senstivity) correctness which is the true positive V7 02 11 99 11 rate [9] 14] 12] 13] also called consistency in [57] 58] the Kappa coefficient [12] 14] Type I and Type II misclassifications [41] 42] 44] 43] Type I ....

....prediction accuracy. 3.2.3. 1 Common Measures of Accuracy Common measures of accuracy for binary classifiers that have been applied in software engineering are the proportion correct value, reported in for example [1] 45] 63] also called correctness in [57] 58] completeness, for example [9][57] (which is equal to the senstivity) correctness which is the true positive V7 02 11 99 11 rate [9] 14] 12] 13] also called consistency in [57] 58] the Kappa coefficient [12] 14] Type I and Type II misclassifications [41] 42] 44] 43] Type I misclassification rate is f 1 , and the Type II ....

[Article contains additional citation context not shown here]

A. Porter and R. Selby: "Evaluating Techniques for Generating Metric-Based Classification Trees". In Journal of Systems and Software, 12:209-218, 1990.

No context found.

A. Porter and R. Selby. Evaluating techniques for generating metric-based classification trees. The Journal of Systems and Software, 12(3):209--218, 1990.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC