refuting common wisdom on scales everybody knows

[kasnavada]

Think of it like this: Growth gives a static precentage bonus to population, every turn. To test Growth scale, you can run a test with 9 provinces for 30 turns, or a test with 270 provinces for 1 turn. The results will be different.

You don't know what you're talking about. What you just did was a perfect example of a strawman argument : the events you get from luck or misfortune from turn n do not affect turn n+1. Growth from turn n affects turn n + 1, therefore as you justly said, you can't compare growth that way. But you can compare luck effects since they are independant from one turn to the next. Same with order and production (and negative counterpart).

That's the reason why the only difference between testing luck for 30 turns on 9 provinces and testing luck in 270 province is the cap limitation for events... which should be gone.

Your ideas are interesting though, but a better solution would be to group the events :
Example : your followers found some water gem in provinceA, fire gem in provinceB instead of 2 messages. Even more since it doesn't matter where the gems are found.

Same for gold : it could be summed. For the loss of gold, it should also be. I always found strange that losing 200 gold in a province that gives 14 gold result in a loss of 14 gold...

Luck should scale with territory since more territory means more chances for luck to happen.

And, as far as militia events being useless, they've been mostly replaced by national troops events AFAIK... so your wish has been heard.