View Single Post
      01-14-2019, 09:12 PM   #82
IK6SPEED
Banned
United_States
4487
Rep
10,473
Posts

Drives: BMW M3 / AH3
Join Date: Jan 2013
Location: Cali

iTrader: (23)

Quote:
Originally Posted by alphakinase View Post
I made an account to answer the survey. Currently own a 2015 M4 DCT with no SCH problems.

But it's worth mentioning that a survey such as this has really low power to determine the actual percentage of failures in a given model year run.

As an example, if there were 2000 M4 DCTs in the 2014 - 2015 run (actual production may be a bit higher) and we managed to survey 100 people about their SCH problems, at a 95% confidence interval that gives a margin of error of 10%....

Let's say we get 100 responses (quite optimistic) for that run and get a failure rate of 5%. At a margin of error of 10%, all we can say is that the rate of SCH failure is less than or equal to 15%. Quite an absurd number - if 15% of those vehicles were failing, there likely would have been a recall or service bulletin in my opinion.

We may get enough responses to generate some statistical power by summing responses across all model years and WHP levels, but because the mods and years may themselves affect the rate of SCH failure, it's hard to say with any confidence what such data means in the real world.

In other words, only BMW will ever know the real rate of SCH failure.

That said, I'm all for this survey and hope as many people as possible fill it out!
It’s not a random survey of BMW S55 owners so no matter the n= count, it will not be scientific.

You cannot accurately predict margin of error [B]to the real world[B] in a non-random sample survey. You can only predict margin of error to the universe of owners that opted in on Bimmerpost.
Appreciate 0