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

81–90 of 116 posts

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

#81

Post by asfasgasg »

hanoz wrote: post #79
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…

> Most folks took 70% to mean that she would certainly win and were bitterly disappointed the morning after. Surely, given the outcome, more of those folks were pleasantly surprised at the outcome than "bitterly disappointed".

Given that Clinton won the popular vote, and by a substantial margin, it is probable that more people were disappointed.

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

#82

Post by asfasgasg »

DINKDINK wrote: post #31
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…

>Hillary Clinton had a >70% of winning the US presidential election Probabilities without confidence intervals[1] are by-and-large meaningless (She has a 90% chance of of winning with a confidence interval of +11% -100%). No amount of d3.js on 538's blog will change this. https://en.wikipedia.org/wiki/Confidence_interval

I've been confused by this in the past too, so let me clarify for you.

Confidence intervals are for predictions of a given value. They are not for probabilities. It doesn't make sense to say, "I think she has a 70% chance of winning, plus or minus 5%." On the other hand, it does make sense to say, I think she will get 48% of the vote, with an interval of +-1%.

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

#83

Post by caf »

arendtio wrote: post #54
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. My everyday example for that is the weather forecast and the question 'will it rain' often answered with a precipitation probability? - Probability: How likely is it that I will be hit by at least one rain drop - Severity: How many rain drops will hit me It sounds a little abstract, but whenever I see some everyday weather forecast I wonder what…

Some forecasts show both the "chance of any rain" as well as various percentiles of the expected rainfall amount, eg this one:

http://www.bom.gov.au/places/vic/melbourne/forecast/detailed...

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

#84

Post by caf »

safgasCVS wrote: post #55

"Lesson 1: Use probabilities instead of words to avoid misinterpretation." Probabilities are meaningless unless it’s a repeatable experiment otherwise its a ludic fallacy eg "There's a 70% chance of Hillary winning". This is an un-provable statement. Either she wins and prediction was right, or she loses and it counts as part of the 30%. This is Nate Silver's get-out-of-jail-free card so even when he's wrong he comes…

It is true that you cannot evaluate a single probabilistic prediction as being right or wrong (so you cannot say that Nate Silver was either wrong or right in some example - he gave a probability, and that probability was either accurate or inaccurate, but in isolation that cannot be evaluated).

However, if a consistent process is used to generate a sequence of probabilistic predictions, the accuracy of the predictions generated by that process certainly can be evaluated.

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

#85

Post by Reedx »

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…

> according to the most responsible analyses (see 538: https://projects.fivethirtyeight.com/2016-election-forecast/)

Yeah, it was amazing to see the storm of hate that poured down on Nate Silver as a result. Thousands of people calling him a fraud (and worse), saying they would never trust him again, etc. Even if he had said there was a 99% chance, that still leaves 1%!

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

#87

Post by dionidium »

arendtio wrote: post #54
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. My everyday example for that is the weather forecast and the question 'will it rain' often answered with a precipitation probability? - Probability: How likely is it that I will be hit by at least one rain drop - Severity: How many rain drops will hit me It sounds a little abstract, but whenever I see some everyday weather forecast I wonder what…

If you ask Alexa, "will it rain today?" she'll respond, "it probably won't rain today" for any probability below 50%. I always thought this was an interesting and illustrative example. If there's a 40% chance of rain, I wouldn't in casual conversation say that, "it probably won't rain today."

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

#88

Post by scythe »

DINKDINK wrote: post #31
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…

>Hillary Clinton had a >70% of winning the US presidential election Probabilities without confidence intervals[1] are by-and-large meaningless (She has a 90% chance of of winning with a confidence interval of +11% -100%). No amount of d3.js on 538's blog will change this. https://en.wikipedia.org/wiki/Confidence_interval

"Speaking of unknown probabilities or of probability of a probability must be forbidden as meaningless. "

- Bruno de Finetti, 1977

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

#89

Post by oculusthrift »

sp332 wrote: post #24
lifeisstillgood wrote: post #13

Earlier quoted context omitted.

That's probably the first time I have mapped Russian Roulette odds to percentages - and 83% chance used to look pretty good. Now I understand Robert Downey Jrs maths skills in Kiss Kiss Bang Bang.

Pascals' Wager: multiply the odds by the cost or benefit of each outcome. The higher the potential cost, the less good your odds look even if the percentage is the same.

Not sure what that has to do with Pascal’s wager? This is just basic “expected value” in probability terms.

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

#90

Post by other_herbert »

dionidium wrote: post #87
arendtio wrote: post #54

Earlier quoted context omitted.

> In everyday life, one conflates probability with severity of outcome. My everyday example for that is the weather forecast and the question 'will it rain' often answered with a precipitation probability? - Probability: How likely is it that I will be hit by at least one rain drop - Severity: How many rain drops will hit me It sounds a little abstract, but whenever I see some everyday weather forecast I wonder what…

If you ask Alexa, "will it rain today?" she'll respond, "it probably won't rain today" for any probability below 50%. I always thought this was an interesting and illustrative example. If there's a 40% chance of rain, I wouldn't in casual conversation say that, "it probably won't rain today."

At least where I am in the summer 40% or higher is just about a guarantee that there will be rain... That seems like something that might need to change based on location and season
Post reply on HN