Thread: Am I Too Sensitive?

Originally Posted by debruiser

Agreed it's too easy to make stats say whatever you want!

But without statistics all we have is hearsay. I am a scientist - you need statistical evidence to prove or disprove anything. When I hear people say that you can get statistics to say anything you want I get nervous. That's the same bull**** sentiment underlying the anti-science movement in the US.

For any statistics to imply causation we need random sample. In the case of Land Rovers and reliability of new vehicles - you get the case where you can actually track the whole sample under warranty.

With older cars you need to conduct a random sample of owners. It would be great to fund some research into this - until we do, we can only discuss correlation - which doesn't imply causation.

Here is a a great quote on correlation/causation:

"Statistics experts and educators spend a lot of time refuting claims of causation. “Correlation does not imply causation” has become a catch cry of people trying to avoid the common trap. This is a great advance in understanding that even journalists (notoriously math-phobic) seem to have caught onto."

We also need a large sample size - the larger the sample, the more you can infer about an entire population. So the reliability of 100 land rovers would give you an idea. The reliability of 100,000 land rovers would give you a much better result.

What I also hate is the portrayal of statistics by journalists who are too stupid to understand them and say you can get statistics to say what you want. Well you can if they were gathered badly, or it wasn't a randomised trial, or you had a small sample size or you include subjectivity. In truth, proper statistics is the ONLY answer. It's just that we are hardly ever presented with proper statistics by the media. And no one (to my knowledge) is gathering them on things like the reliability of older cars.

All we need is a 4 or 5 million dollars are we can get this done. Who's up for it?

Originally Posted by rammypluge

My dad had a 77 rangie for over 330k, no probs great run.

....

my '79 ended up with 650K klms. (I got it with a supposed 148K on the clock in '88, but with the lack of enough digits, could have easily been 248K. 15K klms/year sounds kind'a reasonable tho)
Had to do centre diff at about the 400K mark, but then seeing Ashcrofts video (explanation) of how they can be abused so quickly .. it then made sense.
Just prior to the centre diff crapping out, my dad's 8 ton fridge truck needed a tow start every morning for about a week, till the mechanic could fix the starter/electircal issue.
A few weeks later I was getting binding. It never 'let me down' in the traditonal sense .. I just drove it around and then one day drove it the 100klms to my mechanic and he guessed what the problem was.
I ended up putting an LT77+LT230, and did the other 200K+ klms that it finally ended up with.
ONLY reason I got rid of it was that it was 2 door, I had a growing family and a bung knee(couldn't get bubs into back seats) .. so I had to grow up a bit. Ended up with a V6 Rodeo that was neither more reliable, nor less reliable than a 79 RRC of all things.

I'd also question the 'statistics' too. While statistics themselves don't lie, and can be construed to mean different things to different interest groups .. Having once seen what constitutes a reliability issue in a JD Powers survey, they're claiming cup holders that fall off as a 'reliability issue'

Anyhow, my RRC took me to all manner of remote places(mainly outback SA, but parts of western NSW too), always on my own, and I had full confidence that it'd get me back. Always did.
I'm getting more and more confident that the D1 Tdi should give me the same service for either 600K and/or 20 years, whichever comes first (got 360K now).