-
There are different problems when we reparameterize for optimization
for SARIMAX: https://github.com/statsmodels/statsmodels/issues/#2252#issuecomment-74252465
for MixedLM: #2231
frequently used des…
-
Statsmodels is using joblib in a few places for parallel processing where it's under our control. Current usage is mainly for bootstrap and it is not used in the models directly.
However, some of the…
-
This library achieves very high success rates, though it takes a very long time to optimize and train. This could be improved if we could figure out a way to utilize the GPU more during optimization/t…
-
Starting an issue to discuss the longer-term roadmap for `tsa` with some of my thoughts / questions. The major theme I have in mind is making `tsa` more consistent in terms of inputs, outputs, and met…
-
I got LinAlgError: LU decomposition error
while training and forecasting in UCM with exog variables
-
Leaving an issue here to consider whether we might integrate the functionalities I have in [Stranbo](https://github.com/Baffelan/Stranbo.jl) and `arfima`.
Stranbo is designed for generating time se…
gvdr updated
8 months ago
-
Call used:
```
SARIMAX(endog=endog, exog=exog, order=order
seasonal_order= (0,0,0,4),
trend= 'n',
enforce_stationarity=True,
enforce_invertibility=True,
time_varying_regression=True,
…
-
A nice extension to the ARIMAX fit functionality would be to be able to choose a non-Gaussian distribution for the innovations (for example a t-distribution).
-
A common part of post-estimation work for statespace models is looking at how the state variable means/variances change over time. Both UnobservedComponents and RecursiveLS have really nice helper fu…
-
**Describe the bug**
A forecaster which contains a transformer for both X and Y and converts series to panel, cannot be used.
**To Reproduce**
```python
from sktime.datasets import load_airline
…