8
$\begingroup$

I'm struggling with the concept of a "pseudo-observation." I can't find any material out there describing what it is in a simple, concise manner. Does it have something to do with observation's ordinal rank? And if so, why is it requisite?

Side note: this confusion stems from the use of R's VineCopula library's "pobs" function.

Edit to the question:

Is pseudo-observation required for all copula models?

Improve this question
$\endgroup$

1 Answer 1

Reset to default
7
$\begingroup$

Copula models based on pseudo-observation (normalized ranked data), not on the original dataset. That due to the Sklar's theorem (the backbone of the copula model). From Sklar's theorem, copula is a function of uniform margins. Hence, you need to transform the margins of your dataset to the standard uniform margins, in order to obtain copula data. For RVineCopula, if you simulate your data from RVineSim, then you do not need to transform the margins, however, if your data is a real data, then make sure that you transform it to the uniform distribution using pobs function.

Improve this answer
$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.