6.6.1. statsmodels.sandbox.panel.correlation_structures¶
Correlation and Covariance Structures
Created on Sat Dec 17 20:46:05 2011
Author: Josef Perktold License: BSD-3
6.6.1.1. Reference¶
quick reading of some section on mixed effects models in S-plus and of outline for GEE.
6.6.1.2. Functions¶
corr2cov(corr, std) |
convert correlation matrix to covariance matrix |
corr_ar(k_vars, ar) |
create autoregressive correlation matrix |
corr_arma(k_vars, ar, ma) |
create arma correlation matrix |
corr_equi(k_vars, rho) |
create equicorrelated correlation matrix with rho on off diagonal |
whiten_ar(x, ar_coefs) |
Whiten a series of columns according to an AR(p) covariance structure. |
yule_walker_acov(acov[, order, method, df, inv]) |
Estimate AR(p) parameters from acovf using Yule-Walker equation. |
6.6.1.3. Classes¶
ARCovariance([ar, ar_coefs, sigma]) |
experimental class for Covariance of AR process |