0
$\begingroup$

I have a dataset with multiple cars from the same brand and some of them they develop some problems but not really broke down. For example, tires are operating at 70% in 2000 and then 60% in 2005. Can I find their life expectancy in 2010? I have only two-time data points (2000-01-01 and 2005-01-01) but many different observations in this year.

Can I predict how tires life expectancy will be developed in 2010?

What would be the best method?

$\endgroup$
  • $\begingroup$ I'm not an expert on this topic, but this sounds like survival analysis. $\endgroup$ – Sycorax Jul 28 '18 at 15:29
  • $\begingroup$ You have no data on the outcome, the status as of 2010? $\endgroup$ – rolando2 Jul 28 '18 at 15:36
0
$\begingroup$

You can certainly make predictions. The problem is that you can make many predictions. When you have only two time points, then you can fit a straight line. But it's unlikely that tires degrade linearly over time. So, those predictions are unlikely to be very good.

However, if you had theoretical or substantive knowledge of the general shape of the curve of tire degradation, you might be able to use the data you have to make that shape for your particular case.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.