1

Let me explain my use case with an example. Let's say some phone manufacturer such as apple iphone monitors hardware failure rates. I have a hypothesis that says the latest ios version is resulting in a higher failure rate. How can I validate this test? Note that the hardware might have run several versions of ios over it's life time. The catch here is that the hardware gets older over time - so we cannot say that the newer ios is causing a higher failure rate. What kind of tests or methodologies can I use to test this hypothesis?

kjetil b halvorsen
  • 63,378
  • 26
  • 142
  • 467
Prasanth Regupathy
  • 119
  • 1
  • "I have a hypothesis that says the latest ios version is resulting in a higher failure rate"... ***higher than?*** – Alexis Oct 19 '21 at 17:36
  • 1
    failure rates analysis always includes age, so the age is not a problem if you handle it appropriately. – Aksakal Oct 19 '21 at 17:39

1 Answers1

-1

Using time based covariates with survival analysis turned out to be an appropriate method to solve this problem. Here are some useful links.

https://cran.r-project.org/web/packages/survival/vignettes/timedep.pdf

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6015946/

Prasanth Regupathy
  • 119
  • 1
  • Welcome to CV Prasanth! The CV community generally does not value link-only (or predominantly link-based) answers. Can you edit your answer to include substantive details speaking directly to the OP's question? – Alexis Oct 19 '21 at 17:37
  • Your answer could be improved with additional supporting information. Please [edit] to add further details, such as citations or documentation, so that others can confirm that your answer is correct. You can find more information on how to write good answers [in the help center](/help/how-to-answer). – Community Oct 19 '21 at 17:57