Article ID: | iaor19921701 |
Country: | Japan |
Volume: | 14 |
Issue: | 2 |
Start Page Number: | 192 |
End Page Number: | 203 |
Publication Date: | Sep 1991 |
Journal: | Journal of Information Processing Society of Japan |
Authors: | Jacoby Raymond, Tohma Yoshihiro |
Keywords: | measurement, testing |
In this paper, the Hyper-Geometric Distribution is used to estimate the number of faults in a program at the beginning of the test-and-debug phase. The Hyper-Geometric Distribution Growth Model (HGDM) is well suited to estimating the growth curves of the observed accumulated number of detected faults. The advantage of the model is its applicability to all kinds of observed data. Application of a single model makes it possible to calculate exponential growth curves, as well as S-shaped growth curves. First, HGDM is precisely formulated. Next, the exact relationship of the model to the NHPP Geol-Okumoto Growth Model and the Delayed S-shaped Growth Model is shown. Assumption of an appropriate value of