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

What if successful startups are just lucky?

blog.ploki.info

Post reply on HN
Print view View original

91–100 of 183 posts

Re: What if successful startups are just lucky?

#91

Post by jbooth »

nwhitehead wrote: post #87
pg wrote: post #71

All successful startups are lucky, but they're never just lucky. If they were, we could save ourselves a lot of work reading applications and doing interviews. We could just pick randomly instead. If we did that for one batch, you'd really be able to tell the difference, believe me.

I would absolutely love to see a double-blind randomized experiment with controls for YC applications. In one batch, randomly and secretly assign CONTROL or EXPERIMENT to each application (in whatever proportion you are comfortable with). Of the CONTROL batch, do regular reviews. For the EXPERIMENT batch, randomly accept the same percentage of groups as the control. Then have people outside of the reviewers try to la…

It'd be unfair to great startups in the experiment batch -- not that it's pg's job to make life fair for people, but it'd put a big dent in YC's reputation. Why spend time flying out there if there's a chance your interview doesn't even matter?

Re: What if successful startups are just lucky?

#93

Post by Amadou »

FD3SA wrote: post #63

One important point to realize for the author is that games are not services, they are works of art. As such, you can't say this is an incredible game with the same objectivity as this is an incredible service . Ryzom was a great game, but MMOs are built on one thing: atmosphere. Blizzard made WoW precisely because WarCraft was its longest running and most popular brand to date. Blizzard already had a massive fan bas…

Don't regret making works of art. It is all that succeeds us when we leave this realm.

Until someone turns off the hosting servers.

Re: What if successful startups are just lucky?

#94

Post by fragsworth »

nwhitehead wrote: post #87
pg wrote: post #71

All successful startups are lucky, but they're never just lucky. If they were, we could save ourselves a lot of work reading applications and doing interviews. We could just pick randomly instead. If we did that for one batch, you'd really be able to tell the difference, believe me.

I would absolutely love to see a double-blind randomized experiment with controls for YC applications. In one batch, randomly and secretly assign CONTROL or EXPERIMENT to each application (in whatever proportion you are comfortable with). Of the CONTROL batch, do regular reviews. For the EXPERIMENT batch, randomly accept the same percentage of groups as the control. Then have people outside of the reviewers try to la…

How can you really do any experiments on this kind of shit, when the real winning investments exist in front of a zipf curve?

You get one or two huge winners out of hundreds, and they are so huge that they are bigger than all the others combined. The investors care most about getting these rare winners, and if YC does any kind of controlled study on who becomes these winners, I don't believe there will be any statistical significance to speak of.

Re: What if successful startups are just lucky?

#96

Post by nwhitehead »

jbooth wrote: post #91
nwhitehead wrote: post #87

Earlier quoted context omitted.

I would absolutely love to see a double-blind randomized experiment with controls for YC applications. In one batch, randomly and secretly assign CONTROL or EXPERIMENT to each application (in whatever proportion you are comfortable with). Of the CONTROL batch, do regular reviews. For the EXPERIMENT batch, randomly accept the same percentage of groups as the control. Then have people outside of the reviewers try to la…

It'd be unfair to great startups in the experiment batch -- not that it's pg's job to make life fair for people, but it'd put a big dent in YC's reputation. Why spend time flying out there if there's a chance your interview doesn't even matter?

You could also accept groups with good interviews in the experiment batch, but not include them in the experiment.

Re: What if successful startups are just lucky?

#97

Post by fleitz »

fragsworth wrote: post #94
nwhitehead wrote: post #87

Earlier quoted context omitted.

I would absolutely love to see a double-blind randomized experiment with controls for YC applications. In one batch, randomly and secretly assign CONTROL or EXPERIMENT to each application (in whatever proportion you are comfortable with). Of the CONTROL batch, do regular reviews. For the EXPERIMENT batch, randomly accept the same percentage of groups as the control. Then have people outside of the reviewers try to la…

How can you really do any experiments on this kind of shit, when the real winning investments exist in front of a zipf curve? You get one or two huge winners out of hundreds, and they are so huge that they are bigger than all the others combined. The investors care most about getting these rare winners, and if YC does any kind of controlled study on who becomes these winners, I don't believe there will be any statist…

If there is no statistical significance then it means that there is no difference in picking randomly and doing interviews for the rare winners.

Since the winners are what they are after they can omit the interview process.

Re: What if successful startups are just lucky?

#98

Post by dllthomas »

fleitz wrote: post #97
fragsworth wrote: post #94

Earlier quoted context omitted.

How can you really do any experiments on this kind of shit, when the real winning investments exist in front of a zipf curve? You get one or two huge winners out of hundreds, and they are so huge that they are bigger than all the others combined. The investors care most about getting these rare winners, and if YC does any kind of controlled study on who becomes these winners, I don't believe there will be any statist…

If there is no statistical significance then it means that there is no difference in picking randomly and doing interviews for the rare winners. Since the winners are what they are after they can omit the interview process.

That's not what "no statistical significance" means.

Re: What if successful startups are just lucky?

#100

Post by jbooth »

nwhitehead wrote: post #96
jbooth wrote: post #91

Earlier quoted context omitted.

It'd be unfair to great startups in the experiment batch -- not that it's pg's job to make life fair for people, but it'd put a big dent in YC's reputation. Why spend time flying out there if there's a chance your interview doesn't even matter?

You could also accept groups with good interviews in the experiment batch, but not include them in the experiment.

But then they're effectively excluding the best-interviewing groups from the random experiment.
Post reply on HN