Changes in version 1.6.10 (2021-09-16) o update URLs Changes in version 1.6.9 (2017-04-01) o fixed a bug that made it possible that in very rare cases the shrinkage intensity can become negative o DOIs for all references added Changes in version 1.6.8 (2015-07-08) o import statements added required by R-devel Changes in version 1.6.7 (2014-09-29) o change of maintainer email address Changes in version 1.6.6 (2013-05-15) o is.positive.definite() and make.positive.definite() now use eigen() with option symmetric=TRUE, so that it works under R 3.0.0 (thanks to Roberto Ugoccioni for reporting this issue) Changes in version 1.6.5 (2013-03-27) o License file removed o Dependencies updated Changes in version 1.6.4 (2012-09-02) o estimate.lambda() now also works if the input data matrix has two columns (thanks to Manuela Hummel for reporting this bug) Changes in version 1.6.3 (2012-05-09) o substantially faster estimate.lambda() for small sample size and large dimensions (new algorithm suggested by Miika Ahdesm\"aki) Changes in version 1.6.2 (2012-01-22) o new public functions estimate.lambda() and estimate.lambda.var() returning the shrinkage intensities for correlation and variance shrinkage o some internal code reorganization Changes in version 1.6.1 (2012-01-20) o NAMESPACE file added o small changes in de documentation Changes in version 1.6.0 (2011-06-27) o collapse option removed from: powcor.shrink, cor.shrink, invcor.shrink, cov.shrink, invcov.shrink o default minimum R version changed to 2.10.0 o new function crossprod.powcor.shrink() to efficiently compute R_shrink^alpha y without the need to explicitly compute R_shrink^alpha Changes in version 1.5.7 (2010-08-07) o the function mvr.shrink() has been removed (for a related function see the "care" R package). o mpower() now keeps row and column names. Changes in version 1.5.6 (2010-03-10) o cor.shrink() now also works if the input data matrix only has a single column. Changes in version 1.5.5 (2010-01-14) o a numerical problem with symmetry check in invcor.shrink() and related functions has been resolved (thanks to Gad Abraham). o following an idea by Miika Ahdesm\"aki the procedures for estimating the shrinkage intensities have been rewritten in pure R without employing any C code any more (w/o speed penalty!). Changes in version 1.5.4 (2009-12-16) o mpower() now has an option to exclude nonzero eigenvalues and also checks whether the input matrix is symmetric. Changes in version 1.5.3 (2009-10-11) o small corrections to pass checks for R version 2.10. o reference to Zuber and Strimmer (2009) added. Changes in version 1.5.2 (2009-01-26) o small corrections in the help pages, to pass the more stringent checks on .Rd files introduced in R in January 2009. Changes in version 1.5.1 (2008-12-23) o powcor.shrink() now collapses the identity matrix if alpha=0 and collapse=TRUE. o help page for powcor.shrink was revised. o package description was also revised. Changes in version 1.5.0 (2008-12-02) o new function powcor.shrink() computes (very efficiently!) an arbitrary power of the correlation shrinkage matrix (i.e. R_shrink^alpha). o invcor.shrink() is now a special case powcor.shrink() with alpha=-1. o invcov.shrink() now also uses powcor.shrink(). o new mpower() utility function to estimate the matrix power of a real symmetric matrix. Changes in version 1.4.8 (2008-11-17) o new "collapse" option in cor.shrink, cov.shrink, invcor.shrink, invov.shrink to allow memory savings when lambda equals 1. o to simplify code base two rarely used options were removed: "protect" and "scale.by" (wt.scale is now always done using "sd"). o package depends now on R 2.7.0. o documentation was polished. Changes in version 1.4.7 (2007-10-21) o change of license from "GPL 2 or later", to "GPL 3 or later". Changes in version 1.4.6 (2007-10-19) o following a suggestion (and a patch) by Nicola Soranzo internal big objects are now explicitly removed when they are not needed anymore. As a result, the package now needs less computer memory, and larger (partial) correlation matrices can be computed. Changes in version 1.4.5 (2007-04-08) o when partial correlations are computed using pcor.shrink() the returned matrix now has the standardized partial variances (i.e. PVAR/VAR) attached under the attribute "spv". o updated references in the help pages Changes in version 1.4.4 (2006-09-18) o the function wt.scale() is now *much* faster, especially for large p, due to using colSums() rather than apply() .. note that this indirectly speeds up most other functions in the corpcor package! o typos in the documtation were corrected and references updated Changes in version 1.4.3 (2006-07-17) o the shrinkage target for the variance is now the median (previously, variances were shrunken towards the mean). o var.shrink now also has a"protect" argument. o limited translation shrinkage is now turned off by default (i.e. protect has value zero). Changes in version 1.4.2 (2006-06-05) o limited translation estimator implemented for the shrinkage estimate of the correlation matrix. This prevents excessive component risk. o new functions for decomposing the covariance matrix and its inverse: decompose.cov(), decompose.invcov(), rebuild.invcov() o new function pvar.shrink() to estimate partial variance. o in the documentation the definition of partial variance and partial covariance are corrected (following Whittaker 1990) o the functions cov2pcov(), pcov2cov(), pcov.shrink() have been removed. o functions sm2vec(), vec2sm(), sm.index() back (from GeneTS) o is.positive.definite() checks for complex eigenvalues. Changes in version 1.4.1 (2006-04-25) o fast.svd() now doesn't use any more the LAPACK routines DGESVD to compute the singular value decomposition (this routine is deprecated from R version 2.3.0) o weighted.var(), weighted.moments(), weighted.scale() are now called wt.var(), wt.moments(), wt.scale() Changes in version 1.4.0 (2006-04-16) o New functions mvr.shrink() and mvr.predict() for multivariate shrinkage regression. o All shrinkage estimate now carry the class attribute "shrinkage. This allows for a more informative output via print.shrinkage() o Removed functions: sm2vec(), vec2sm(), sm.indexes() Changes in version 1.3.1 (2006-04-01) o This versions fixes a bug present in "corpcor" version 1.3.0 and 1.2.0 but not in earlier versions. This bug leads to a (probably negligible) small bias in the computation of the optimal shrinkage intensity. o The functions cov.bagged(), cor.bagged(), and pcor.bagged() have been removed. o Typographical errors in the documentation were corrected. Changes in version 1.3.0 (2006-03-28) o New function "var.shrink" to compute shrinkage estimates of variances (target: average empirical variances. o cov.shrink() and pcov.shrink() are now also based on shrunken variances. o Estimation of shrinkage intensities are now done in C. This greatly decreases the computational costs. o Options "check.eigenvalues" and "exact.inversion" have been removed in cor2pcor() and pcor2cor() o The functions have been modified so that data sets with zero-variance variables may also be analyzed (these will be in effect ignored in estimating correlation but taken into account when estimating variances). Changes in version 1.2.0 (2006-03-10) o Greatly reduced memory and faster computations. o New code on fast inversion using Woodbury identity. o Consequently, pcor.shrink() is now much faster . o New functions for computation of weighted variances, weighted moments, and weighted rescaling. o All covariance etc. estimators now also have the option to supply data weights". o varcov() function removed (not necessary any more). o Several parts of documentation updated. o Juliane's Web address updated. Changes in version 1.1.2 (2005-12-12) o Minor typos in documentation corrected. o From this version is.positive.definite() works with arbitrary matrix (previously it required symmetric matrix). Changes in version 1.1.1 (2005-11-26) o Reference to shrinkage covariance paper is updated. Changes in version 1.1 (2005-09-28) o cor.shrink() is now the central estimator, and cov.shrink is derived. Changes in version 1.0 o First stand-alone release (20 August 2005). This package contains various functions shrinkage estimation of (partial) correlation and covariance. Prior to release in this package the functions were part of the GeneTS package.