I wouldn't say so. It's probably the best guess you can make in the absence of context, since all the unknown factors average out to make our one piece of info (it rained today) meaningless.
Conversation
Replying to
They don’t average out is the point, and one piece of information can be a lot
1
1
Replying to
Sometimes, but not in this case. If you don’t know which direction they’re weighted, then you don’t know which direction it’s going to shift the probability. Acting on this information is nothing more than a guess with a 50% chance of being wrong.
1
Replying to
Read the rest of the thread, especially the last bits. Zero mean additive noise is a strong assumption when there’s more circumstantial evidence of correlation than anti correlation.
Quote Tweet
If this approach bothers you, try snow rather than rain. Snow is more obviously and strongly seasonal.
Even more obvious: You’re at an indeterminate location where Christmas music plays in public X days a year. You heard Christmas music today, will you hear it tomorrow?
Show this thread
1
Replying to
The difference here is that there's less complexity w/ Christmas music than weather patterns. There's a best guest to be made in either situation, but Christmas music is vastly simpler since it's relatively immune to feedback (calendar-based) and bound by predictable tradition.
1
The point you're trying to make is that there's always a best guess that can be made. The difference is with weather systems, you need massive foundational knowledge and access to advanced systems to make that guess.
1
People who don't have that knowledge (all of us) would be foolish to answer a Twitter survey with anything other than 1/3.
1
Replying to
That’s my point. This is not advanced expert knowledge. It’s lay common knowledge. Seasonality is common knowledge. You don’t need to know how the meteorology works to know that rain tends to cluster.
1
Replying to
See, and this proves my point, because rain _doesn't_ tend to cluster. It may tend to cluster where you live, but that doesn't make it true everywhere. Head to the rainforest and you'll find rain is periodic with very little seasonality and no clustering.
1
It's never good to act on information you have without knowing what you don't know. And the only way to know what you don't know is to be an expert. And if you're answering a Twitter poll, you're not an expert. And so a rational person can only answer 1/3.
1
Replying to
Equatorial rainforests have rain >>122 days in a year. Tropical ones have stronger seasonality. But never mind. I’m not going to persuade you.

