Comment by 0xfffafaCrash | Hacker News Reader

Comment by 0xfffafaCrash | Hacker News Reader

It would be interesting to see a list of unsuccessful small teams as a point of reference. Oh wait… it probably wouldn’t. Then again, a list of unsuccesful large teams may not offer much insight either.

There may be many advantages to small teams and yes there are cases where they have wild financial success, but in general these may just be outliers. Are these outliers because they have the secret sauce worth emulating? Maybe, and maybe their stories will show why they succeeded where so many failed. Success is rarely all luck, but we’ll likely also invent myths around their exceptionalism as we tend to do. Not the type of exceptionalism which precludes the rest of us from having a similar shot of course, but one about cleverness and grit or other characteristics we can fairly easily attribute to ourselves.

Everyone likes a good narrative, I suppose. And narratives about scrappy small teams achieving success meritoriously are more attractive than ones about how the massive organizations usually tend to eat them for lunch (despite having their own types of problems) or ones about the frequencies with which the scrappy teams fail. Cherry-picking data points is the key to any good narrative.

It's just probability theory meets survivorship bias. The larger the team the more it will trend towards the average because the joint probability that everyone in the team is simultaneously awesome (or awful) becomes lower and lower as a function of team size.

Same thing happened with "small schools perform better" so they got funded. But turns out it's possible for them to perform terribly for the same reason it is for them to perform well.

> Same thing happened with "small schools perform better" so they got funded. But turns out it's possible for them to perform terribly for the same reason it is for them to perform well.

And reason(s) would be?

Joint probability all members are either all excellent or all terrible is higher when the number of people is smaller.

Probability changes with sample size? Any source for that claim?

AFAIK only variance changes with sample size.

Otherwise statistics would be quite useless in general as I understand it.

Say in the general population 10% are excellent. If I look at 10 randomly selected people I expect that one of them is excellent. If I look at 10 000 people should I really expect that more than 1 000 are excellent? That claim does not make sense to me.

> Probability changes with sample size? Any source for that claim?

The post only suggests this if you ignore the word "Joint" before the word "probability".

Otherwise, you seem to be arguing that the probability of getting "all heads" would be identical when flipping two coins as when flipping 100.

Even in smallish teams the probability that all members are excellent (or terrible) is almost zero, imho. In a bigger selection it's just closer to zero.

In fact in any sample the distribution of "excellent, average, and terrible" will be more or less the same. Namely more or less like the distribution in the general population. (Otherwise we can stop looking at statistics in general as they would be worthless).

The probability for the most unlikely event (namely a result that is maximally far away form the expected one) may be a little bit greater given smaller sample sizes (a result of broader variance), but this is irrelevant as the probability for such outcome is in almost any case infinitesimally small.

Looking at the verges of a distribution to draw conclusions is misleading, imho. You need to look at the middle of the curve as there are the most likely outcomes of some selection.

So, if I put some random people in a group the most likely outcome is that the ratio of excellent people to others is similar to the ratio of excellent people to other in the general population. This is the most likely outcome, independent of sample size.

Smart people often have smart friends, so a small team of mostly smart people isn't that unlikely.

The problem is when you get a few degrees of separation, at that point the original signal is mostly lost and you will get the same kind of people as everyone else who uses the same hiring bar as you.

This argument does not make much sense to me.

If you pick only "the best" people by hand you could create a team with only excellent members of any size.

All the statistical arguments become mot in such a scenario!

You would get a team of only excellent people with a guarantied probability of 1, at any sample size.

Your argument doesn't work, nobody knows enough people to staff up a big company with only people they know. At some point they will have to go by surface signals or by word of mouth, talking to a person in an interview isn't enough.

On the other hand for a small team, lets say 10 people, you could go back and pick the 10 best people you have worked with in your life. That will be a good team if you actually tries to get good people instead of people you like. That doesn't scale, other people will take people they like and quality suffers, it always happens at scale, but an individual kan make better choices.

Yes, getting only "the best of the best" doesn't scale. I fully agree.

But it also doesn't work for smaller teams, because people are people.

Now we're back to my previous argument: The probability to get a team of only excellent (or terrible) people is near zero in reality independent of team size.

Everything put together finally invalidates the original:

> > Same thing happened with "small schools perform better" so they got funded. But turns out it's possible for them to perform terribly for the same reason it is for them to perform well.

> Joint probability all members are either all excellent or all terrible is higher when the number of people is smaller.

Trying to approach this conclusion by statistics just doesn't work as we see.

But the non stochastic arguments why small teams are always in advantage, which I presented in my other post, hold.

"Near zero" is an extremely misleading term.

For small teams it's 0.1%. For large teams it's 0.001%.

Both are near zero. But one is 100 times more likely than the other.

>AFAIK only variance changes with sample size.

And what explains the change in variance as sample size changes?

> It would be interesting to see a list of unsuccessful small teams as a point of reference

You can just go look at Steam indie games. Those are all small teams. They are mostly all failures.

The median small team on Steam generates $4,000 in lifetime revenue. 2/3rds never cross $10,000 in lifetime revenue. Only the top 10% even cross $200,000. Which is more like "barely paid salaries" rather than some kind of F-U money.

The number of small teams on indie games that come anywhere close to the success of big teams on AAA games is minuscule.

> It would be interesting to see a list of unsuccessful small teams as a point of reference.

I guess it depends on what you call success. Most businesses are mom and pop businesses that generate enough revenue to pay their employees the market rate in the long run. And I’m including tech businesses.

Most flourishing economies in the world are composed essentially of small successful and sustainable businesses.

To me, that is success.

I know that a lot of people here live in the SV echo chamber (nothing pejorative, we all live in an echo chamber) but in fact being big is the exception, not the norm.

I’d even argue that most "rich/comfortable" people in the world are not tech founders but are just at the head of 0 to 10 employees businesses. I’d guess they call this success.

Small teams often move faster than big teams, that is why small teams are bought by big teams instead of big teams just building their own and quickly taking market share and crushing them with better designs, features, pricing, marketing budget and iteration speed.

Big stuff is slow by nature. Lots of moving parts.

Reply on news.ycombinator.com