How to convince someone of statistical probibilities

  • Context: Undergrad 
  • Thread starter Thread starter Pengwuino
  • Start date Start date
  • Tags Tags
    Statistical
Click For Summary

Discussion Overview

The discussion revolves around the comparison of statistical probabilities related to accidents in cars versus small airplanes. Participants explore the appropriate basis for these statistics, debating whether to consider miles traveled or the number of engine startups as the relevant metric for assessing risk.

Discussion Character

  • Debate/contested

Main Points Raised

  • One participant argues that accidents should be statistically assessed based on miles traveled, claiming that driving a longer distance increases the likelihood of an accident compared to the infrequency of airplane startups.
  • Another participant counters that the number of airplane crashes is more closely related to the number of engine startups, suggesting that the nature of airplane accidents does not correlate with miles traveled.
  • A third participant emphasizes that mechanical issues leading to crashes are critical, indicating that problems can arise independently of the distance traveled.
  • One participant introduces the concept of "passenger-mile" statistics, noting that exposure time and the number of flights (takeoffs and landings) are also important metrics, while suggesting that there may not be a definitive right or wrong in this debate.

Areas of Agreement / Disagreement

Participants express differing views on the appropriate statistical basis for comparing risks between cars and airplanes, indicating that multiple competing perspectives remain unresolved.

Contextual Notes

The discussion highlights the complexity of defining risk in transportation, with participants noting that different factors may influence accident rates in cars and airplanes, leading to ambiguity in the statistical analysis.

Pengwuino
Gold Member
Messages
5,112
Reaction score
20
Ok I am having a really annoying time with my father here. Now statistically, you are much more likely to get in an accident in a car then in a small airplane per mile traveled. Now my father thinks that its better to say that its more dangerous to have a small airplane since you are more likely to get in an accident based on the number of times you start your engine.

Now i say, the statistic should be based on miles, he says on startup and I'm almost positive my statistic is the correct basis since people's accidents occur while driving and not when they start-up their car. Extrapolate the idea out and someone who drives 100000 in one trip has a faaaaaaaaaaaaar larger chance of getting in an accident then someone who turns his car on once and drives across the street and back.

Now i want to really verify that my statistical basis is correct... and if it is, how can you convince someone that you are right.

This may be more reasonably put in the GD section.
 
Physics news on Phys.org
the number of planes that will crash will depend on the number of times the engine has started, by the nature of their crashes (AFAIK, a longer trip does not imply a greater risk, since the plane would have a problem due to something else, ie mechanical failure when starting).
For cars, however, it is the opposite; a longer trip brings a greater risk.

If you compare them using only the statistics from the miles travelled, then you don't take into account the fact that the planes' accidents do not depend on the number of miles travelled, but rather on the number of flights.
 
Yah but the fact it has a problem is the thing. When it has a problem, there's a possibility of a crash (thus, an accident).
 
Think takeoffs and landings! :)

People who want to convince you that flying is safe use the "passenger-mile" model. Exposure time (time in transit) and number of trips (takeoffs and landings) are also valid measures but the airlines and FAA don't want to alarm people. I don't think there is a strict "right or wrong" on this issue.
 

Similar threads

High School Convince Covid-19 Vaccine Efficiency Through Statistics
  • · Replies 12 ·
Replies
12
Views
2K
Undergrad Specific question re Bayesian statistics/analysis
  • · Replies 9 ·
Replies
9
Views
2K
Undergrad Statistical analysis of COVID reinfection
  • · Replies 13 ·
Replies
13
Views
2K
Undergrad Making Sense of Notation Confusion in Statistical Digital Signal Processing
  • · Replies 6 ·
Replies
6
Views
2K
Undergrad Can Ockham’s razor be used to make quick qualitative predictions?
  • · Replies 23 ·
Replies
23
Views
3K
MHB Probability Value Question (left-tailed test)
  • · Replies 10 ·
Replies
10
Views
3K
Undergrad Tell me how scientific journals scrutinize statistical work
  • · Replies 3 ·
Replies
3
Views
1K
Undergrad How to convince someone that an event repeating an infinite number of times does not guarantee every outcome?
  • · Replies 23 ·
Replies
23
Views
4K
Undergrad How Often Will I Meet the Mailman at the Same Mailbox?
  • · Replies 9 ·
Replies
9
Views
2K
Undergrad Monte Carlo for uncertainty estimation
  • · Replies 2 ·
Replies
2
Views
2K