Exactly. I remember asking a prof in undergrad what the spectrum of a single time sample would be. He didn't give me a straight answer, but I realized later that question was equivalent to asking what the average age of a single person was.
Hm... I think I get what you're saying, but isn't computing the average age of a person over their lifetime pretty straightforward? integral of their age divided by their total lifespan, which would be their (total lifespan)/2.
Yeah. It's misworded. It's more like, given a particular person, and a given instant in time, compute the average of an ensemble of people. It makes no sense.
Seems like a few folks here know how to project a single sample onto a vector valued function. Brilliant people.