Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

If You Say Something Is “Likely,” How Likely Do People Think It Is?

hbr.org

Post reply on HN
Print view View original

41–50 of 116 posts

Re: If You Say Something Is “Likely,” How Likely Do People Think It Is?

#41

Post by csours »

tinalumfoil wrote: post #35
roter wrote: post #27

For what it is worth, the Intergovernmental Panel on Climate Change uses the following definitions[0]: virtually certain: 99-100% extremely likely: 95-100% very likely: 90-100% likely: 66-100% about as likely as not: 33-66% more likely than not: >50-100% more unlikely than likely: 0- unlikely: 0-33% very unlikely: 0-10% extremely unlikely: 0-5% exceptionally unlikely: 0-1% [0]: https://ipcc.ch/pdf/assessment-report/a…

> virtually certain: 99-100% Hopefully whoever wrote that never works in a data center, builds cars, sells insurance, gambles, works on crypto, does scientific computing, or is ever responsible for someone's life.

If you do any of those things, you use actual numbers with your words - which, if you actually care about the subject at hand, you should have used numbers in the first place.

Re: If You Say Something Is “Likely,” How Likely Do People Think It Is?

#42

Post by ori_b »

resu_nimda wrote: post #19
kashyapc wrote: post #6

That impreciseness is one reason why William Zinsser in his book, On Writing Well , argues: - "Get rid of the adjective-by-habit." - "Don't hedge your prose with little timidities. Good writing is lean and confident."

"Don't hedge your prose with little timidities. Good writing is lean and confident." This is a separate issue, and one I would disagree with. In fact I feel like this is a problematic attitude in our culture. Too many people overconfidently asserting their subjective viewpoints. Real life is full of nuance, gray area, second-guessing, and different perspectives; simple bold assertions usually don't hold water. David…

> This is a separate issue, and one I would disagree with.

It's possible to state a lack of certainty with confidence and clarity.

Re: If You Say Something Is “Likely,” How Likely Do People Think It Is?

#43

Post by edbaskerville »

fragsworth wrote: post #38
OscarCunningham wrote: post #34

Earlier quoted context omitted.

From a Bayesian perspective, or from a betting one, it doesn't make sense to put probabilities in a confidence interval. You might be uncertain about the world, but you can be certain about how much uncertainty you have, since it's a property of your own mind.

How do we quantify the difference between coin tosses, which we are very certain is 50% likely to end up heads, from political elections, where we only have a few examples to go off of?

In terms of predicting what's going to happen next, it really isn't that different if your model's any good. Looking backwards, if the 2016 election had been determined by two coin tosses both coming up heads, would we be surprised? And yet 538's polling model indicated that the probability was even better than two coins coming up heads.

They probably should have just written that right there: "71%, better odds than two coins coming up heads."

But: in order to understand if the model is any good, you need to try to build a good model, describe your model, and describe what you know about the underlying processes. With words, visuals, and math. Which is pretty much what 538 does better than most.

Re: If You Say Something Is “Likely,” How Likely Do People Think It Is?

#44

Post by icedchai »

tinalumfoil wrote: post #35
roter wrote: post #27

For what it is worth, the Intergovernmental Panel on Climate Change uses the following definitions[0]: virtually certain: 99-100% extremely likely: 95-100% very likely: 90-100% likely: 66-100% about as likely as not: 33-66% more likely than not: >50-100% more unlikely than likely: 0- unlikely: 0-33% very unlikely: 0-10% extremely unlikely: 0-5% exceptionally unlikely: 0-1% [0]: https://ipcc.ch/pdf/assessment-report/a…

> virtually certain: 99-100% Hopefully whoever wrote that never works in a data center, builds cars, sells insurance, gambles, works on crypto, does scientific computing, or is ever responsible for someone's life.

You're not much of a risk taker, are you?

Re: If You Say Something Is “Likely,” How Likely Do People Think It Is?

#45

Post by throwawaymath »

tinalumfoil wrote: post #35
roter wrote: post #27

For what it is worth, the Intergovernmental Panel on Climate Change uses the following definitions[0]: virtually certain: 99-100% extremely likely: 95-100% very likely: 90-100% likely: 66-100% about as likely as not: 33-66% more likely than not: >50-100% more unlikely than likely: 0- unlikely: 0-33% very unlikely: 0-10% extremely unlikely: 0-5% exceptionally unlikely: 0-1% [0]: https://ipcc.ch/pdf/assessment-report/a…

> virtually certain: 99-100% Hopefully whoever wrote that never works in a data center, builds cars, sells insurance, gambles, works on crypto, does scientific computing, or is ever responsible for someone's life.

Implicit in your statement is the claim that you cannot acknowledge the existence of a percentile without believing any given feature of your domain can easily satisfy that percentile. That's a non sequitur. The conclusion that follows from that one is also very strange, because it would mean we shouldn't bother quantifying things (or having a name for them) if they can only be expected to happen extremely rarely.

Re: If You Say Something Is “Likely,” How Likely Do People Think It Is?

#46

Post by dguo »

1123581321 wrote: post #25
dguo wrote: post #23

Earlier quoted context omitted.

I don't think he/she did. "I would disagree with" and "I feel" make it clear this is a personal opinion. Also note the presence of "usually" in "simple bold assertions usually don't hold water."

Yes, but the actual opinions run quite lean and are unqualified except for the “usually,” which the reader understands is placed to head off anecdotal contrary examples. The last one ends with a blunt insult. It’s certainly not DFW’s style of writing.

You are certainly entitled to your interpretation, but I don't think the writer put in "usually" just to head off anecdotal counterexamples. The principle of charity leads me to assume the writer genuinely believes that simple bold assertions are occasionally fine.

Though I do strongly agree with the original comment, so maybe that is the real reason why I am defending it.

Re: If You Say Something Is “Likely,” How Likely Do People Think It Is?

#47

Post by moolcool »

crispyambulance wrote: post #11

It depends on the context. Hillary Clinton had a >70% of winning the US presidential election according to the most responsible analyses (see 538: https://projects.fivethirtyeight.com/2016-election-forecast/ ). Most folks took 70% to mean that she would certainly win and were bitterly disappointed the morning after. On the other hand no sane person would (willingly) play Russian roulette with a 70% or even 5 of 6 cha…

The analysis after the elections was interesting-- think pieces asking things like "How could the stats have been so wrong?!". A fair dice has a roughly 83% chance of landing on a number between 1 and 5, but if you roll a 6 you don't ask yourself the same question.

Re: If You Say Something Is “Likely,” How Likely Do People Think It Is?

#48

Post by hueving »

jmount wrote: post #14

Another fun one: Fermi's definition of "remote possibility" as a chance of no more than 1 in 10. (Scary when talking about the odds of initiating a chain reaction, making a small atomic weapon, or even igniting the atmosphere in the first atomic test.) https://books.google.com/books?id=2G2TlJOhGI8C&pg=PA280&lpg=...

0 in 10 is still "no more than 1 in 10", so I don't see why that's scary.

Re: If You Say Something Is “Likely,” How Likely Do People Think It Is?

#49

Post by sanbor »

In my experience, putting numbers to your gut feeling probabilities causes people to not take them seriously. Example: "I think there is 30% chances that I will get a promotion next month". If I say 30% people ask how I came up with that number. If I say "not very likely" then it gets accepted as an educated guess. Probably because we're used that those numbers must come from some dataset. Or should I say "I think there is a chance of 40% that things are like that because we're used that those numbers must come from some dataset".

Re: If You Say Something Is “Likely,” How Likely Do People Think It Is?

#50

Post by denzil_correa »

crispyambulance wrote: post #11

It depends on the context. Hillary Clinton had a >70% of winning the US presidential election according to the most responsible analyses (see 538: https://projects.fivethirtyeight.com/2016-election-forecast/ ). Most folks took 70% to mean that she would certainly win and were bitterly disappointed the morning after. On the other hand no sane person would (willingly) play Russian roulette with a 70% or even 5 of 6 cha…

> In everyday life, one conflates probability with severity of outcome

In other terms, "Expected Value" can help in this case where you factor in the magnitude along with the frequency of occurrence.

Post reply on HN