The question of the advisability using a control chart for this kind of
tracking may not be answerable in the affirmative. The viability of a
control chart depends on measuring a representative sample of the
population, whereas it appears that Lenin is interested in estimating the
confidence limits for individual pieces of equipment. This is I believe
better accomplished using the customary Reliability and Maintenance
procedures.
There are well-documented control chart procedures for ratios. I don't
recall offhand whether any have addressed the particular distributions
associated with up and downtime but they certainly have addressed Poisson
and exponential distributions.
Kwenda mzuri,
Frank Isackson
===========================================================================
This list is open to everyone. Occasionally, people lacking respect
for other members of the list send messages that are inappropriate
or unrelated to the list's discussion topics. Please just delete the
offensive email.
For information concerning the list, please see the following web page:
http://jse.stat.ncsu.edu/
===========================================================================
