
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
M. Sahinoglu, "CompoundPoisson Software Reliability Model," IEEE Transactions on Software Engineering, vol. 18, no. 7, pp. 624630, July, 1992.  
BibTex  x  
@article{ 10.1109/32.148480, author = {M. Sahinoglu}, title = {CompoundPoisson Software Reliability Model}, journal ={IEEE Transactions on Software Engineering}, volume = {18}, number = {7}, issn = {00985589}, year = {1992}, pages = {624630}, doi = {http://doi.ieeecomputersociety.org/10.1109/32.148480}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Software Engineering TI  CompoundPoisson Software Reliability Model IS  7 SN  00985589 SP624 EP630 EPD  624630 A1  M. Sahinoglu, PY  1992 KW  compoundPoisson software reliability model; discrete compound Poisson prediction model; probability density estimation; software failures; clustering; clumping; random variable; Poisson arrivals; predictive validity; MusaOkumoto logPoisson model; software reliability VL  18 JA  IEEE Transactions on Software Engineering ER   
The probability density estimation of the number of software failures in the event of clustering or clumping of the software failures is considered. A discrete compound Poisson (CP) prediction model is proposed for the random variable X/sub rem/, which is the remaining number of software failures. The compounding distributions, which are assumed to govern the failure sizes at Poisson arrivals, are respectively taken to be geometric when failures are forgetful and logarithmicseries when failures are contagious. The expected value ( mu ) of X/sub rem/ is calculated as a function of the timedependent Poisson and compounding distribution based on the failures experienced. Also, the variance/mean parameter for the remaining number of failures, q/sub rem/, is best estimated by q/sub past/ from the failures already experienced. Then, one obtains the PDF of the remaining number of failures estimated by CP( mu ,q). CP is found to be superior to Poisson where clumping of failures exists. Its predictive validity is comparable to the MusaOkumoto logPoisson model in certain cases.
[1] C. C. Sherbrooke, "Discrete compound Poisson processes and tables of the geometric Poisson distribution,"Memorandum RM4831PR, The Rand Corporation, Santa Monica, CA, July 1966.
[2] L. H. Crow and N. D. Singpurwalla, "An empirically developed Fourier series model for describing software failures,"IEEE Trans. Reliability, vol. R33, June 1984.
[3] E.Çinlar,Introduction to Stochastic Processes. Englewood Cliffs, NJ: PrenticeHall, 1975.
[4] W. Feller,An Introduction to Probability Theory and Its Applications, Vol. 1, 3rd Ed. New York: Wiley, 1968, pp. 288292.
[5] J. D. Musaet al., Software Reliability Measurement, Prediction, Application. New York: McGrawHill International, 1987.
[6] J. D. Musa and K. Okumoto, "A logarithmic Poisson execution time model for software reliability measurement," inProc. Compsac' 84, Chicago, IL, 1984, pp. 230238.
[7] J. D. Musa, "Software Reliability Data," Bell Telephone Laboratories, Whippany, NJ, 1979.
[8] R. M. Adelson, "Compound Poisson distributions,"Operational Research Quarterly, vol. 17, pp. 7374, 1966.
[9] R. F. Serfozo, "Compound Poisson approximations for sums of random variables,"The Annals of Probability, vol. 14, pp. 13911398, 1986.
[10] M. Sahinoglu, "The limit of sum of Markov Bernoulli variables in system reliability evaluation,"IEEE Trans. Reliability, pp. 4650, Apr. 1990.
[11] A. L. Goel, "Software reliability models: Assumptions, limitations, applicability,"IEEE Trans. Software Eng., pp. 14111423, Dec. 1985.
[12] R. B. D'Agostino and M. A. Stephens,Goodness of Fit Techniques. New York: Marcel Dekker, 1986.
[13] M. Sahinoglu, "Geometric Poisson density estimation of the number of software failures," inIEEE Proc. 28th Annual Reliability, Spring Seminar of the Central New England Council, The Boston Chapter Reliability Society, pp. 149174, Apr. 1990.
[14] Encyclopedia Stat. Sciences, vol. 5, pp. 92, 111113, 1988.
[15] Encyclopedia Stat. Sciences, vol. 6, pp. 169176, 1988.
[16] Student,Biometrika, vol. 12, pp. 211215, 1919.
[17] M. Greenwood and G. U. Yule, "An inquiry into the nature of frequency distributions representative of multiplehappenings,"J. Royal Statistical Society, vol. 83, pp. 255279, 1920.
[18] B. Brown, "Some tables of the negative binomial distribution and their use,"Memorandum RM4577PR, The Rand Corporation, Santa Monica, CA, June 1965.
[19] F. N. David and N. L. Johnson, "The truncated Poisson,"Biometrics, pp. 275285, Dec. 1952.
[20] R. A. Fisher, "The significance of deviations from expectation in a Poisson series,"Biometrics, pp. 1724, Mar. 1950.
[21] M. Sahinoglu, "Compound Poisson estimation of the number of software failures," presented (invited) at Software Reliability Workshop by Tech. Comm. on Software Reliability Eng., Subcomm. on Software Reliability Eng., Apr. 1990.
[22] M. Sahinoglu, "Negative binomial density of the software failure count," inProc. Fifth Int. Symp. Computer and Information Sciences, vol. 1, pp. 231239, Oct. 1990.
[23] M. Sahinoglu and E. H. Spafford, "A sequential statistical mutationbased testing strategy," inIEEE Proc. 28th Annual Spring Reliability Seminar, pp. 127149, May 1990.
[24] M. Sahinoglu and E. H. Spafford, "A Bayes sequential statistical procedure for approving software products," IFIP Conference on Approving Software Products (ASP90) Garmisch Partenkirschen, Germany, Sept. 1990.
[25] P. Randolph and M. Sahinoglu, "A compound Poisson Bayesian stopping rule for software reliability," ASA Joint Stat Meetings, Atlanta, GA, Session 183: Computer Packages, Aug. 21, 1991.
[26] A. Ianninoet al., "Criteria for software reliability model,"IEEE Trans. Software Eng., vol. 10, pp. 687691, Nov. 1984.
[27] C. V. Ramamoorthy and F. B. Bastani, "Software reliabilitystatus and perspectives,"IEEE Trans. Software Eng., vol. 8, July 1982.
[28] P. C. Consul,Generalized Poisson Distributions. New York: Marcel Dekker, 1989.