[R] compare performance behavior over a lifecycle

From: Prew, Paul <Paul.Prew_at_ecolab.com>
Date: Fri, 14 Nov 2008 12:47:33 -0600


Dear all,

I would like to characterize the behavior of a certain product over its lifetime. The purpose is to compare the behavior of experimental versions of the product vs. a baseline version. It's known that the behavior of the product follows a roughly trapezoidal pattern: start-up effect where the performance ramps up, then steady state performance, finally a degradation at the end of the life. A sensor captures the performance every two minutes. Is anyone aware of a package that can be used for such a cradle-to-grave comparison? This is not quite survival analyses, because I'm interested in more than just 'length of life'. Interest is in 'length of ramp-up', 'length & amplitude of steady-state' and 'length of degradation'. I've considered Time Series with seasonality or Fourier analyses to deconstruct the behavior into periodic component. However, the I'm not aware of TS or Fourier comparisons for contrasting two populations. Such comparisons are probably common in image analysis, but that's a foreign field to me.

Thank you,
Paul

Paul Prew
Ecolab R&D
Eagan, MN

CONFIDENTIALITY NOTICE: \ This e-mail communication an...{{dropped:11}}



R-help_at_r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Received on Fri 14 Nov 2008 - 18:49:39 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Fri 14 Nov 2008 - 19:31:40 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive