A Comparative Study of Assessing Software Reliability using Spc: an Mmle Approach

The Modified Maximum Likelihood Estimation (MMLE) of the parameters of Exponential and Half Logistic distributions are considered and compared. An analytical approximation is used instead of linear approximation for a function which appears in Maximum Likelihood equation. These estimates are shown to perform better, in the sense of simplicity of calculation than the one based on linear approximation for the same function. In this paper we identified the MMLE method of estimations and associated results using Half Logistic Distribution and Exponential Distribution are similar. These estimates are used in SPC to find the control limits to predict the software reliability. A comparison of software reliability using Statistical Process Control for a small sample is also presented

[1]  Thong Ngee Goh,et al.  Some effective control chart procedures for reliability monitoring , 2002, Reliab. Eng. Syst. Saf..

[2]  Edward F. Weller.  Applying statistical process control to software , 2002 .

[3]  David N. Card.  Statistical process control for software? , 1994, IEEE Software.

[4]  Mitre Corp.  CMM Level 4 Quantitative Analysis and Defect Prevention Al Florence , 2001 .

[5]  Edward F. Weller.  Practical Applications of Statistical Process Control , 2000, IEEE Softw..

[6]  Moti L. Tiku,et al.  A new method of estimation for location and scale parameters , 1992 .

[7]  Betty Jones Whitten,et al.  Modified moment and maximum likelihood estimators for parameters of the three-parameter gamma distribution , 1982 .

[8]  M. Tiku,et al.  Time Series Models in Non‐Normal Situations: Symmetric Innovations , 2000 .

[9]  Pankaj Jalote,et al.  CMM in Practice: Processes for Executing Software Projects at Infosys , 1999 .

[10]  Holger Rootzén,et al.  Simple and highly efficient estimators for a type I censored normal sample , 1977 .

[11]  William A. Florac,et al.  Statistical Process Control: Analyzing a Space Shuttle Onboard Software Process , 2000, IEEE Softw..

[12]  M. L. Tiku.  Modified maximum likelihood estimation for the bivariate normal , 1988 .

[13]  D. N. Card,et al.  An industrial engineering approach to software development , 1989, J. Syst. Softw..

[14]  Mutsumi Komuro,et al.  Experiences of applying SPC techniques to software development processes , 2006, ICSE.

[15]  K. G. Mehrotra,et al.  Unbiased estimation of parameters by order statistics in the case of censored samples , 1974 .

[16]  R. Satya Prasad,et al.  Software Reliability Measuring using Modified Maximum Likelihood Estimation and SPC , 2011 .

[17]  M. Tiku,et al.  Estimating the mean and standard deviation from a censored normal sample. , 1967, Biometrika.

[18]  Robert L. Glass,et al.  Measuring software design quality , 1990 .

[19]  Mark C. Paulk.  APPLYING SPC TO THE PERSONAL SOFTWARE PROCESS , 2000 .

[20]  Ed Weller.  Applying Quantitative Methods to Software Maintenance , 2000 .

[21]  K. Rosaiah,et al.  ESTIMATION IN TRUNCA TED TYPE-I GENERALIZED LOGISTIC DISTRIBUTION , 2009 .

[22]  R. Satya Prasad,et al.  Monitoring Software Reliability using Statistical Process control: An MMLE approach , 2011, ArXiv.