Movatterモバイル変換

MixMatrix 0.2.7

• Fix Doxygen update to _PACKAGE issue
• Fix names in DESCRIPTION
• Fix “if (class(x) == …)” issue.

MixMatrix 0.2.6

• Update to fix M_PI issue with Rcpp update.
• Fix some non-HTTPS URLs.

MixMatrix 0.2.5

• Update with DOI for associated paper.
• Fix an issue with AR(1) and CS covariances. The way these arespecified means that in case of mis-specification, they may benon-monotonic if they are mis-specified and results are near the theboundary. The functions were written such that it would not stop in thiscase.

MixMatrix 0.2.4

• Fixed a minor bug in DF calculation for mixture models.
• Fixed a minor bug in log likelihood calculation for mixturemodels.

MixMatrix 0.2.2

• Added more citations and references.
• Added reference to the paper this package accompanies.
• A small series of bug fixes and internal function updates to moreeasily support restrictions on means and variances differentfunctions.

MixMatrix 0.2.1

• Added a number of citations and references to manuals and vignettes,including clarifying sources of any other functions.
• AddedlogLik functions for LDA, QDA, and MixMatrixobjects

MixMatrix 0.2.0

• Start to add mixture modeling - currently support unconstrainedvariances only and fixednu parameters for themodel = "t" option..
• Remove list support for matrix LDA and QDA, since they were just apain to support for thepredict methods.

MixMatrix 0.1.0

• Preparing for CRAN submission
• Add pkgdown (https://gzt.github.io/MixMatrix/)
• Add ORCID
• Minor documentation changes
• Fixnu bug formatrixlda andmatrixqda when using normal distribution
• Add vignette fort distribution

MixMatrix 0.0.0.9949

• changing name to MixMatrix

matrixdist 0.0.0.9927

• include EM algorithm (actually an ECME) for estimation of parametersof matrix-variatet-distributions
• include variance specifications for EM for t distribution
• include the possibility of restricting covariance matrices to acorrelation structure.

matrixdist 0.0.0.9926

• split Wishart functions into CholWishart package
• migrate some internal functions toRcppArmadillo toimprove speed
• add support for multiple observation input todmatrixnorm function
• add support for multiple observation input todmatrixtanddmatrixinvt
• dmatrix function now have large components in C++
• add error checking todmatrixinvt - density onlydefined when matrix is positive definite
• improve speed ofMLmatrixnorm by migrating more to C++and fixing some R bottlenecks

matrixdist 0.0.0.9925

• add multivariatedigamma
• add a couple tests formatrixt
• new plan: add fitting for t-distribution, LDA fort-distribution

matrixdist 0.0.0.9924

• Wrote density functions for the Wishart and InvWishartdistributions. Broke the Wishart functions andmvgammafunctions into a separate file just for them as they are all related andI may break them into their own package.

matrixdist 0.0.0.9923

• RewroterInvCholWishart to fix a bug where it was notactually a Cholesky decomposition - while upper triangular,tcrossprod() was InvWishart, notcrossprod().The method is a little slower since it involves computingrInvWishart and then taking the Cholesky decomposition, butit is faster than doing it in R.

matrixdist 0.0.0.9922

• Added LDA and QDA functions withpredict() methods.These functions are relatively fragile.
• Marked some functions as internal to clean up the NAMESPACE

matrixdist 0.0.0.9921

• Added support for using IID structure for covariance matrices
• correction on restricted means - only true if known variance

matrixdist 0.0.0.9920

• added change to mean estimation to account for restricted means
• added changes to documentation

matrixdist 0.0.0.9919

• Added aNEWS.md file to track changes to thepackage.
• Changed the name of the maximum likelihood parameter fittingfunction toMLmatrixnorm sincemle.--- couldbe confused for a method.