Website Navigation:
Home >
Journal of Research (Science)

Email Address: jrscience@bzu.edu.pk


<< JRScience Home     Volume 17 No.2   April  2006     << Back to Volume Home

DISCRIMINATION BETWEEN WEIBULL AND LOGNORMAL DISTRIBUTIONS FOR LIFETIME DATA

G.  R.  Pasha

Department of Statistics Bahauddin Zakariya University, Multan

Email: drpasha@bzu.edu.pk

M. Shuaib Khan

Department of Statistics Govt Zamindar College, Gujrat

Email: fahad_9_2@yahoo.com

Ahmed Hesham Pasha

Department of Electrical Engineering, Bahauddin Zakariya University, Multan

Email: hesham01@gmail.com

Abstract:

Reliability and failure data, both from life testing and from in-service records, are often modeled by the Weibull or Lognormal distributions so as to be able to interpolate and/or extrapolate results. The aim of this research is to discriminate between the Weibull and Lognormal distributions for complete samples. Both reliability models Weibull and Lognormal are then illustrated. Median rank regression (MRR) and maximum likelihood estimation (MLE) data- fitting methods are described and goodness-of-fit using maximum likelihood ratio (MLR) and most powerful invariant (MPI) tests. We find the Weibull distribution better for fitting to lifetime data when comparing with the Lognormal distribution.

Keywords: Maximum likelihood ratio test, median rank regression, most powerful invariant test, Weibull and Lognormal distributions.