In order for us to "believe you", you would need to test your hypothesis at least once - for example, by selecting a small number the startups you invest in at random and see how they fare compared to the other startups. Keep in mind that most stock pickers would respond exactly like you even though their choices are rarely (if ever) better than chance.
If I was to walk for the first time into your kitchen and tell you that your hotplate was turned on, would you not believe me until I'd also experienced your hotplate turned off? You would discount my previous experiences with hotplates, because maybe, just maybe, your hotplate is hot enough to boil water when it's unpowered?
The idea that the null hypothesis is the only source of information needs to die.
But on the other hand, there are well-known cognitive biases and counterintuitive facts that can cause people (including extremely intelligent people and even people aware of the biases and facts) to believe things that scientific experiment can show to be false.
Figuring out that a hotplate is turned on can be done though a very simple and direct observation, so most likely I would take your word for it.
Figuring out what makes people successful at starting companies is extremely complex. And without objective evidence, no level of expertise, be it PG or other VCs, will convince me to take someone's word for it.
