Discussion in 'Ford F-150 Raptor General Discussions [GEN 2]' started by jaz13, Jul 15, 2017.
3/29/17 build date. Leak at 2,000. Haven't been to dealer yet for repair.
Build date 1/20 no leaks
Sent from my SAMSUNG-SM-T337A using Tapatalk
I hate to break the news to you, but you need approx. over 2000 respondents to be within +/- 3% and over 700 to be +/- 5% and over 200 to be within +/- 10%. (which +/- 10% is pretty much a meaningless survey)
This is based on approx 20,000 raptors sold. These numbers go up if they sold more.
That does not even take into account that it is more likely that owners with problems will be on this forum!!! (huge point by the way that invalidates even the numbers I posted above)
Your idea and effort are applauded, but this is a useless exercise as I doubt you reach even a 100 respondents.
So those with leaks appear to be with the oil pan gasket, as best I can tell from the thread. For those with leaks, how did you notice it? Was it significant enough that you noticed drips on the garage floor, or was it the oil plan was oily? This thread has me wondering if I need to take a closer look at my own truck.
"a little knowledge is a dangerous thing".
Sample size and confidence interval has nothing to do with population size. Thousand, million, or billion, it doesn't matter. If you look it up, you will notice population size is not a variable in the confidence interval formula. This is why pollsters can determine how millions of us will vote from a couple thousand respondents and Neilson influences billions of dollars of advertising with just a few thousand households.
This makes sense intuitively if you think about sampling M&Ms to determine the ratio of colors. Bag, bathtub, swiming pool, lake, or ocean of M&Ms, it doesn't change how many you need to count to have a good idea of the proportions. Only varience affects sample size, ie how well mixed up is the pile of M&Ms. Well mixed up, small sample size; colors all bunched together, large sample size.
Another example is your doctor only needs one blood sample because the variance in your blood is very low. The results from one blood sample will be identical to five samples or fifty samples. Lucky for you your doctor doesn't need to take 2,000 blood samples to determine your cholesterol.
Finally, this survey is conducting "explatory research" and is most definitely not a scientific or representative. But it is ignorant to discount its usefulness. This website is a hub for Raptor enthusiasts and is probably fairly representative. I have no reason to believe enthusiasts are more likely to experience a leak than a non-enthusiast. It's not as if I am sitting in the waiting room of a Ford service department asking if people are having problems with their vehicle.
For QC purposes, you want a failure rate in the small fractions of a percent. Six Sigma is something around 0.0001% failure rate. Given this exploratory survey, it is clear that Ford has a problem and the oil pan failure rate is in multiple percentage points. I'd most likely between 5 and 20%. That is a devastatingly horrible failure rate for manufacturing.
Of course the numbers will only grow because there are many who have not experienced the leak yet that will have one, or those that have a leak but haven't noticed it yet.
Be careful the next time you go spouting off about things you don't really understand.
I discovered my leak while I was under the truck looking at the rust package that was inadvertently included with my truck. The leak wasn’t enough to drip on the floor but it was enough that it covered the top side of one of the skid plates and it would blow back on other components of the drivetrain.
I hate to tell you something else, but you have no idea what you are talking about.
But I do agree with you that a little knowledge is dangerous. And I also agree with you that your survey is not scientific nor representative. It may or may not be explatory, (I admit I dont know what that word means).
"this survey is conducting "explatory research" and is most definitely not a scientific or representative."
Since you do not understand how polls work, it might be easier for you to grasp if I just give you a couple questions to ponder.
Do you think sasquatch (who doesnt own a raptor) voted in your poll??? Do you think he voted more than once since he uses several different id's??? Does it matter to you if he voted???
Do you think that your poll results would have a different meaning if there were only 100 raptors sold total or if there were 100,000 sold???
Is this site just a hub for enthusiasts or also do customers with problems or gripes tend to be more frequent and vocal on websites?
No need to get your panties in a wad, was just trying to make sure you took any poll results for what they are worth.
As you mentioned, the relevancy of the sample is less than ideal (though still a valiant effort; realistically, there isn't a better way that I can think of for Joe Raptorowner to gather this info), but even at that, I would say that 17%+ is still indicative of an issue. While (obviously) a given random truck is much less likely to have a leak than to not have one, if I were the guy in charge of oil system integrity (that's a real thing, right?? ) on this vehicle, the frequency of this issue would definitely be a concern to me.
So, while the issue isn't as widespread as perhaps some would like us to believe, it's certainly more widespread than I would think would be acceptable to Ford (at least the product team... which will have a VASTLY different take on things than the folks who approve warranty work).
3/5 build date, no leaks.
Oil leak discovered at 1100 miles (First oil change)
Confirmed leak at second oil change (4400 miles)
Fixed immediately after, no questions asked.
It's a super small weep. No oil ever on floor of garage.
Separate names with a comma.