Covariance is of universal prevalence across various disciplines within statistics. CovTools package aims at providing a rich collection of geometric and statistical tools for a variety of inferences on covariance structures. See the sections below for a comprehensive list of functions provided from the package.
From inference on manifolds perspective, we have following functions,
| name of a function | description |
CovDist |
compute pairwise distance of covariance matrices |
We provide statistical methods for (1) Covariance Matrix Estimation,
| name of a function | description |
CovEst.adaptive |
Adaptive Thresholding |
CovEst.hard |
Hard Thresholding |
CovEst.hardPD |
Hard Thresholding under Positive-Definiteness Constraint |
CovEst.nearPD |
Nearest Positive-Definite Matrix Projection |
(2) Precision Matrix Estimation
| name of a function | description |
PreEst.banded1 |
Bayesian Estimation of a Banded Precision Matrix (Banerjee 2014) |
PreEst.banded2 |
Bayesian Estimation of a Banded Precision Matrix (Lee 2017) |
PreEst.banded3 |
Banded Precision Matrix Estimation via Bandwidth Test |
(3) Frequentist Hypothesis Tests
| name of a function | description |
CovTest1 |
1-sample Covariance Tests |
(4) Bayesian Hypothesis Tests
| name of a function | description |
(5) Others
| name of a function | description |