Giters

SMAC-Group / gmwm

Generalized Method of Wavelet Moments (GMWM) is an estimation technique for the parameters of time series models. It uses the wavelet variance in a moment matching approach that makes it particularly suitable for the estimation of certain state-space models.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Scaling issues with single timeseries for GMWM2

stefangachter opened this issue · comments

commented

When using gmwm in gmwm2, the time scale is not treated properly.
If computing model with gmwm(model, timeseries, freq=100) then frequency argument is ignored:
image
If computing first wavelet variances wvar(imu_obj) and then the model gmwm(model, wv, freq=100) , the time scale is correctly considered for the wavelets but not the model:
image
If models are estimated for multiple time series with mgmwm, the scaling works:
image
Would be great if this could be fixed!