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

Suspicious Discontinuities

danluu.com

Post reply on HN
Print view View original

41–50 of 307 posts

Re: Suspicious Discontinuities

#41

Post by CydeWeys »

lkbm wrote: post #12

OKCupid has a graph of reported height for men[0]. It's both shifted 2 inches to the right of average, but also slightly flattened at the normal peak of 5'10". It's not nearly as pronounced as the graphs in this post, but it's still notable. [0] https://theblog.okcupid.com/the-big-lies-people-tell-in-onli...

Can confirm. I'm 5'9" but listed myself as 5'10" on dating sites. Adding that extra digit really seems to matter, and when I'm wearing shoes I am that tall anyway. Because of heels women often come off as much taller than they actually are.

Rounding up to 6' definitely would've been stretching the truth too much though.

Re: Suspicious Discontinuities

#42

Post by TeMPOraL »

jacques_chester wrote: post #13
ww520 wrote: post #11

IRS would do well catching tax evasion by running some statistic models to find suspicious discontinuities.

They do. Tax agencies worldwide have used statistical techniques for decades.

Benford's law is probably the most known example.

https://en.wikipedia.org/wiki/Benford%27s_law

Re: Suspicious Discontinuities

#43

Post by hn_throwaway_99 »

tracker1 wrote: post #18
lkbm wrote: post #12

OKCupid has a graph of reported height for men[0]. It's both shifted 2 inches to the right of average, but also slightly flattened at the normal peak of 5'10". It's not nearly as pronounced as the graphs in this post, but it's still notable. [0] https://theblog.okcupid.com/the-big-lies-people-tell-in-onli...

I really miss the more technical blog posts that OKCupid used to do like this... then after selling out to Match Inc, they wen't through that weird woke period... and radio silent for over a year... The technical insights were far more informative in terms of dating trends.

The technincal insights were great but man I loved the writing, too:

> Apparently, an online dater’s imagination is the best performing mutual fund of the last 10 years.

Re: Suspicious Discontinuities

#45

Post by robocat »

hammock wrote: post #35
robocat wrote: post #24

Earlier quoted context omitted.

Average height changes significantly depending upon your age cohort. If few older people sign up to OKCupid, that would be a sample bias and the average height would be noticeable higher. Edit: “Adjusting for age, adults ages 18-74 years with an annual income of $15,000 and over were observed to be 1.2 inches taller than those with an annual income under $4,000”, amongst other serious biases (whiteness, education) th…

The difference in height for US age cohorts (among adults, obviously) is driven by ethnicity- and younger cohorts are shorter on average.

Where did you see that? From the link I gave it looks like the average 25 year old is about 2” taller than the average 55 year old. Even anecdotally, the height difference is noticeable (although I am in NZ, the variation between cohorts depends strongly upon what country you are in).

Re: Suspicious Discontinuities

#46

Post by nl »

alexis_fr wrote: post #29
eloff wrote: post #3

Earlier quoted context omitted.

I was always small until about age 16, and I always sucked at sports and never really got into them - partly as a result. I wonder if we shouldn't group kids by size for sporting activities instead of by age. There's a famous statistic in Canada that NHL players are much more likely to be born in January and February than September-December. The reason being is they were nearly a year older than other kids they were…

> The reason being is they were nearly a year older than other kids they were paired with. I’m amused that the kids who did worse are absolutely necessary for the kids who do better. They end up getting wasted by the process, demotivated, but they are a necessary brick to step upon. It’s the same consideration when talking about male suicide. Are they necessary for others to feel good? We could solve a good part of i…

It’s the same consideration when talking about male suicide. Are they necessary for others to feel good?

No.

There's no evidence at all to support this view. In fact there is evidence to support the view that people who feel good when others feel bad are more likely to have suicidal tendencies.

Re: Suspicious Discontinuities

#47

Post by __s »

DavidVoid wrote: post #25
lkbm wrote: post #12

OKCupid has a graph of reported height for men[0]. It's both shifted 2 inches to the right of average, but also slightly flattened at the normal peak of 5'10". It's not nearly as pronounced as the graphs in this post, but it's still notable. [0] https://theblog.okcupid.com/the-big-lies-people-tell-in-onli...

Slightly off-topic but this reminded me of what is perhaps their most depressing pair of graphs. Look at "A woman's age vs. the age of the men sho look best to her" https://i.kinja-img.com/gawker-media/image/upload/1439100617... and then compare that with "A man's age vs. the age of the women who look best to him" https://i.kinja-img.com/gawker-media/image/upload/1439100617...

"look best" is open ended. Why should my "looks best" evaluation alter as I age? Just because I think a young woman looks good doesn't mean I want to marry her

Re: Suspicious Discontinuities

#48

Post by okusername »

DavidVoid wrote: post #25
lkbm wrote: post #12

OKCupid has a graph of reported height for men[0]. It's both shifted 2 inches to the right of average, but also slightly flattened at the normal peak of 5'10". It's not nearly as pronounced as the graphs in this post, but it's still notable. [0] https://theblog.okcupid.com/the-big-lies-people-tell-in-onli...

Slightly off-topic but this reminded me of what is perhaps their most depressing pair of graphs. Look at "A woman's age vs. the age of the men sho look best to her" https://i.kinja-img.com/gawker-media/image/upload/1439100617... and then compare that with "A man's age vs. the age of the women who look best to him" https://i.kinja-img.com/gawker-media/image/upload/1439100617...

Do you have a link to the study? I'd love to check the study design

Re: Suspicious Discontinuities

#49

Post by christiansakai »

lkbm wrote: post #12

OKCupid has a graph of reported height for men[0]. It's both shifted 2 inches to the right of average, but also slightly flattened at the normal peak of 5'10". It's not nearly as pronounced as the graphs in this post, but it's still notable. [0] https://theblog.okcupid.com/the-big-lies-people-tell-in-onli...

I did not know that people actually added 2 inches to their actual height in dating profiles, a practice I discovered later when actually meeting the people.

Nevertheless, I always use real height (5’3”) in dating profiles, thankfully my current wife didn’t care (we met on OkCupid). Given that me and her only put exactly 1 or 2 profile pictures and zero description and we still able to meet, should be considered anomaly.

Re: Suspicious Discontinuities

#50

Post by hn_throwaway_99 »

cs702 wrote: post #5

Any rules that can be gamed, sooner or later, inevitably, will be gamed. The "suspicious discontinuities" shown in this fantastic post are evidence for it. It seems to be an Iron Law of Human Nature.

This 'Iron Law of Human Nature' is a corollary of Goodhart's Law: https://en.wikipedia.org/wiki/Goodhart%27s_law
Post reply on HN