-
-
Notifications
You must be signed in to change notification settings - Fork 2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Improve default GaussianRandomWalk and AR init distributions #5744
Comments
Decision: Raise warning if not specified, increase standard deviation to 100. |
I'll take this on |
Is it Possible to set it to the stationary distribution? At least for the AR? |
Another alternative is to set it to a Dirac delta at 0 |
@lucianopaz I think the initial point does not affect the stationarity? |
I meant to set the initial distribution to the AR stationary distribution. For AR1 there’s a formula in terms of the coefficients. I don’t know what happens for AR(p) though |
Won't that perhaps introduce very strong constraints on the initial point? Btw, a DiracDelta would break everything, as no draws would ever be accepted unless we implemented a custom sampler (or transform) for the AR alone |
When refactoring the GaussianRandomWalk to V4, we set the
init
to default toNormal(mu, sigma)
, which does not make much sense.mu
is the drift parameter, and says nothing about the expected starting location of the series.sigma
probably also makes little sense, as it assumes the uncertainty about the initial location has anything to do with the innovations noise.Possible alternatives:
init = Normal.dist(0, 1)
init = Flat.dist()
, which was the default in V3, but it means that prior and posterior predictive will fail by default.We should also rename
init
toinit_dist
to emphasize this parameter must de a distribution.pymc/pymc/distributions/timeseries.py
Line 239 in c76b9b9
A similar question arises in the AR, where we again reuse the innovation noise
sigma
for the uncertainty about the initial location of the series.pymc/pymc/distributions/timeseries.py
Line 429 in c76b9b9
The text was updated successfully, but these errors were encountered: