relspne {bvhar} | R Documentation |
This function computes relative estimation error given estimated model and true coefficient.
relspne(x, y, ...)
## S3 method for class 'bvharsp'
relspne(x, y, ...)
x |
Estimated model. |
y |
Coefficient matrix to be compared. |
... |
not used |
Let \lVert \cdot \rVert_2
be the spectral norm of a matrix,
let \hat{\Phi}
be the estimates,
and let \Phi
be the true coefficients matrix.
Then the function computes relative estimation error by
\frac{\lVert \hat{\Phi} - \Phi \rVert_2}{\lVert \Phi \rVert_2}
Spectral norm value
Ghosh, S., Khare, K., & Michailidis, G. (2018). High-Dimensional Posterior Consistency in Bayesian Vector Autoregressive Models. Journal of the American Statistical Association, 114(526).