running into people - calculating probabilities

[gusl]

I just ran into my Amsterdam housemate Elena on the bus. When I said hello, she recognized me rightaway, even though it's been almost 5 years. What a small world we live in! (similar story: When I moved to London in 1994, I ran into my tennis teacher from Angola rollerskating at Kensington Gardens)

I'd love to see an estimate of the probability of such things: how many new people one sees per day, how often people they live abroad, how much do they mix, etc. It's easy to do back-of-the-envelope calculations, but how could one approach this more seriously?

--

My current commute is just short of 2 hours each way.
Port Moody -(ride)- Kootenay loop -(135)- Burrard Station -(44)- UBC

Currently I'm taking a refueling break at Blenz Coffee. The Internet here is working better than anywhere I've been in the last 48h.

--

Then, on the 44, I ran into a student of mine from last semester.

Comments

[http://users.livejournal.com/_wirehead_/]

it happens a lot in NYC, too.

there are only a few thousand real people in the world.

but more seriously, i think it has to do with the fact that our brains are wired REALLY well to do pattern-recognition on things like faces, and to pick friends out of crowds of strangers.

also the fact that people who are similar to you (on whatever axes) are likely to hang out in the same places and do the same sorts of things you will be doing; so the world is not as large as it is alleged to be.

[gustavolacerda.livejournal.com]

I agree.


<< also the fact that people who are similar to you (on whatever axes) are likely to hang out in the same places and do the same sorts of things you will be doing; so the world is not as large as it is alleged to be. >>

True, but riding an 8am bus in East Vancouver is hardly a niche. I'd say it's a rather representative sample.

Also, I have the impression that the two people I mentioned above hang out in pretty different places from me... although probably similar cities.

The implication is that if you live in a city like Vancouver for a year, you'll probably come into sighting-distance of >50% of the 20-something population (50% of 300K people).

[http://users.livejournal.com/_wirehead_/]

"the same places" also means cities, not just places within cities.

riding an 8am bus in East Vancouver is hardly a niche. I'd say it's a rather representative sample.

is it really a representative sample? what about people who own cars?

spotting me on an 8am bus anywhere would be highly improbable, but i don't know if you can generalize about time in any reasonable way. (i was going to say i'm far more likely to run into someone i know when out and about in the evening than during the morning, but once you include groups like co-workers and classmates, i think even that metric goes to hell.)

[gustavolacerda.livejournal.com]

Even if only 10% of Vancouverites ride buses regularly, I still had to pick her out of 200K people (and I almost never ride earlier than 9am).

In any case, I'd love to get some actual numbers.

[http://users.livejournal.com/_wirehead_/]

numbers, i can't help ya with. though i got idle speculation out the wazoo. :D

(would be interested to see whatever you come up with)

i CAN tell you, though, that given the population of the planet... an event with a "one in a million" chance will happen to several hundred people every day!

[gustavolacerda.livejournal.com]

I like how you use "real" as an abbreviation of "reachable".

"A Bayesian's Guide to Guesstimation"

[gustavolacerda.livejournal.com]

http://gustavolacerda.livejournal.com/333977.html

I want to write a methodology book titled "A Bayesian's Guide to Guesstimation". The inspiration was when, yesterday, I tried to combine several pieces of information in order to estimate the number of people were on this huge party complex near Ostbahnhof last night. I had:
* seen crowds of young people walking towards
* I roughly knew the size of the complex
* I roughly know Munich's population, and I had heard of this place twice from "random" strangers.

I could have stood and counted the people coming out of the station... and, using common sense priors about what time people go out, etc., I could have made a better guesstimate.

How can we combine common sense knowledge, intuitions, etc., before we have a formal model of the relationship between all the different pieces of information that one has? This is probably very relevant to the study of expert decision-making, i.e. "intelligence analysis".

[easwaran.livejournal.com]

Very weird - when I was in the Portland airport a day or two before or after New Year's, I was leaving the men's room and ran into a woman coming in, and was about to correct her, and then we both realized that we recognized each other, having lived in the same co-op in Berkeley several years earlier. Very weird.

[surrey-sucks.livejournal.com]

What a gross commute.

[bhudson.livejournal.com]

I had just gotten off the plane to home yesterday, idly looked down into the baggage claim area that I was ignoring, and saw the top of Danny Sleator's head. My first reaction was that it was Danny Sleator. My second reaction is that Midway airport was an odd place to be bumping in to him.