Changes in version 1.3.9 (2025-04-08) o updated Authors@R field. o updated URLs. o fixed errors flagged by R-devel in documentation. Changes in version 1.3.8 (2021-11-21) o update URLs. Changes in version 1.3.7 (2015-07-08) o add import statements as required by R-devel. Changes in version 1.3.6 (2015-03-21) o fix "S3 generic/method consistency" NOTE raised by R-devel. Changes in version 1.3.5 (2014-11-18) o the example R scripts (Khan SRBCT and Singh prostate cancer data) are now provided in R notebook format. o change of maintainer email address. Changes in version 1.3.4 (2014-07-28) o change of maintainer email address. o corrections to index.html file in inst/doc folder. Changes in version 1.3.3 (2014-04-18) o an import() statement has been added to NAMESPACE to address warnings of R 3.1.0. o added example scripts for Singh et al. (2001) and Khan et al. (2002) gene expression data. o now suggests "crossval" package for estimating prediction accuracy. Changes in version 1.3.2 (2014-01-10) o sda() now also works with a single predictor (previously two predictors were necessary). o plot.sda.ranking() now has three new options to allow customization (zeroaxis.col, ylab, and main). Changes in version 1.3.1 (2013-09-01) o centroids() now also estimates class frequencies (in addition to simply reporting the samples size per class). The frequencies are estimated using a shrinkage approach (set lambda.freqs=0 for empirical estimates). The pooled mean is now computed using the estimated frequencies. o catscore() now has a lambda.freqs argument and uses shrinkage estimates of class frequencies to compute the scaling factor (to use empirical scaling factors set lambda.freqs=0). o the estimated frequencies returned by sda() are now contained in the variable "freqs" (which previously was called "prior"). o in sda.ranking() there is now also a lambda.freqs argument o in addition, sda.ranking() now offers three types of summary statistics for ranking variables in the multi-class case. Changes in version 1.3.0 (2013-04-28) o predict.sda() has been rewritten and is now *much* faster for large numbers of test samples. o the format of object returned by sda() has changed for more efficient prediction. Note that it is *not* compatible with earlier versions. Changes in version 1.2.4 (2013-04-03) o License file removed. o Dependencies updated. o plot.sda.ranking() is not based on "lattice" graphics any more (new code contributed by Sebastian Gibb). o sda() now allows to specify the shrinkage intensity for the class frequencies. Changes in version 1.2.3 (2012-11-24) o plot.sda.ranking() now checks for duplicated row names. o feature.idx argument removed from predict.sda() function. o sda.ranking() now allows to specify lambda and lambda.var as in the catscore() function. o sda() also has parameters to set lambda and lambda.var, as well as shrink.freqs=TRUE/FALSE. Changes in version 1.2.2 (2012-08-20) o centroids() function allows to specify the shrinkage intensity for estimating the variances. Default is now shrinkage rather than empirical estimates. o catscore() also includes options to specifify shrinkage intensities. The default is now using shrinkage rather empirical estimates. o sda.ranking() now uses fdrtool to compute higher criticism scores o in the output of sda(), the order of entries in the regularization vector is now lambda, lambda.var, lambda.freqs. Changes in version 1.2.1 (2012-01-22) o NAMESPACE file added o updated requirements for "corpcor" and "entropy" Changes in version 1.2.0 (2011-06-28) o requires now corpcor 1.6.0 and R version 2.10.0 o new function catscore() o centroids() function has been streamlined and simplified o updated documentation o employs function crossprod.powcor.shrink() of corpcor which leads to reduced memory imprint and increased speed in functions catscore(), sda.ranking() and sda() Changes in version 1.1.0 (2009-03-12) o new sda.ranking() function o plot function for "sda.ranking" objects o additional to FDR values computation of higher-criticism scores o reference to Ahdesm\"aki and Strimmer (2009) paper added o Singh et al. (2002) example data added o improved help pages and examples o the data khan.x is now on log-scale Changes in version 1.0.3 (2008-12-08) o sda() now provides ranking of features. o fdr values can optionally be computed for each feature. o centroids() now reports number of samples and features. o sda() function has been rewritten, and a bug introduced in version 1.0.2 has been corrected. Changes in version 1.0.2 (2008-12-03) o predict.sda() is now very much faster, and the object returned by sda() needs much less memory. o the centroids() function now additionally computes the pooled mean and arbitrary powers of the correlation matrix (not just alpha=-1). o the microarray data from Khan et al. 2001 are now used as example. o bug fix: for shrinkage DDA the inverse correlation matrix is not computed unnecessarily any more. Changes in version 1.0.1 (2008-11-22) o new centroids() function to compute group-wise centroids, (pooled variances), and inverse pooled correlations. o uses the "collapse" option in corpcor >= 1.4.8 to save memory when estimated correlation is diagonal (effectively turning LDA into DDA if the estimated shrinkage intensity lambda=1). Changes in version 1.0.0 (2008-10-26) o This package implements LDA and DDA classification, where the training of the classifier is done via Stein-type shrinkage of frequencies, variances, and correlation. This approach is particularly suitable for high-dimensional classification. o This is the first public release (27 October 2008).