Live data from Hacker News

Eastern Antarctica sees record temperatures 70 degrees above normal

washingtonpost.com

51–60 of 90 posts

Re: Eastern Antarctica sees record temperatures 70 degrees above normal

#51

“Eastern Antarctica”. East of what? I have no idea where that is.

draw an imaginary line from right around London, UK to the South Pole... imagine standing on that line, looking towards London from the sunny shores of the world's oldest forests under that ice, East is on your right side.. optional singing of national songs or worship according to your conscience

Re: Eastern Antarctica sees record temperatures 70 degrees above normal

#53
post #29

Earlier quoted context omitted.

The probability that an observation is beyond 5 standard deviations is https://en.wikipedia.org/wiki/Chebyshev's_inequality https://en.wikipedia.org/wiki/Cauchy_distribution

4% would imply that we should expect about two weeks of such weather every year, in total. Which would make this article somewhat clickbait — nothing more than “wowza, July 15th is another hot one in California!” Since it’s currently summer, in the Southern Hemisphere.

That's a bound not an expectation.

Re: Eastern Antarctica sees record temperatures 70 degrees above normal

#54

that is 39 Celsius above minimum average, or 27 Celsius on the conservative side: Instead of temperatures being minus-50 or minus-60 degrees (minus-45 or minus-51 Celsius), they’ve been closer to zero or 10 degrees (minus-18 Celsius or minus-12 Celsius)

Without knowing the variance, that really says nothing.

Re: Eastern Antarctica sees record temperatures 70 degrees above normal

#55
post #29

Earlier quoted context omitted.

Do you know the temperature probability distribution in Antartica? Not all distributions are normal and not all even have a standard deviation.

The probability that an observation is beyond 5 standard deviations is https://en.wikipedia.org/wiki/Chebyshev's_inequality https://en.wikipedia.org/wiki/Cauchy_distribution

An observation bound below by 5 standard deviations is at best a one in a million on a standard normal distribution.

Re: Eastern Antarctica sees record temperatures 70 degrees above normal

#56
post #54

that is 39 Celsius above minimum average, or 27 Celsius on the conservative side: Instead of temperatures being minus-50 or minus-60 degrees (minus-45 or minus-51 Celsius), they’ve been closer to zero or 10 degrees (minus-18 Celsius or minus-12 Celsius)

Without knowing the variance, that really says nothing.

"five standard deviations above normal." -- from the article

Re: Eastern Antarctica sees record temperatures 70 degrees above normal

#58
post #54

Earlier quoted context omitted.

Without knowing the variance, that really says nothing.

"five standard deviations above normal." -- from the article

Calculated conditioned on calendar day or just treating it as one time series?

Re: Eastern Antarctica sees record temperatures 70 degrees above normal

#60
post #42

Earlier quoted context omitted.

If the observed variable is “the mean temperature in a given day”, 4% can be expected to occur relatively frequently. Anyway until we know the probability distribution, and my intuition says that it’s definitely not Normal for wide periods of time, we can’t say if it’s significant or not.

You’re the only one introducing the normal distribution here.

When discussing standard deviations, what meaning is there for non-normal distribution?

https://stats.stackexchange.com/questions/108578/what-does-s...

Post reply on HN