Changes in version 2.9-11 (2024-08-22) Bug-fixes o Fix Rd formatting issues o Use R_Calloc Changes in version 2.9-10 (2024-04-29) Bug-fixes o Fix Rd formatting issues o Disable tests requiring kangar00 Changes in version 2.9-9 (2023-12-07) Bug-fixes o Fix Rd formatting issues Changes in version 2.9-8 (2023-09-06) Bug-fixes o S3 argument mismatch o include R_ext/BLAS.h Changes in version 2.9-7 (2022-04-26) Bug-fixes o Don't escape & Changes in version 2.9-6 (2022-04-08) Bug-fixes o Fix BLAS problem. o More \dontrun in manual packages Changes in version 2.9-5 (2021-04-13) Bug-fixes o btree(..., by = ) caused problems when restricting the number of boosting iterations. Miscellaneous o Speed-up vignettes. o Use less precision in numerical vignette outputs. Changes in version 2.9-4 (2020-12-10) User-visible changes o New maintainer: Torsten Hothorn follows Benjamin Hofner, who curated the 2.6-2.9 series, as maintainer. All authors thank Benny for 4 years of package maintainance! o Added by argument to btree; only binary factors are allowed. Bug-fixes o Add missing rclass function to derive class predictions from conditional class probabilities to Binomial() family. o Plot correct x-axis in plot(cvrisk(...)) (closes #102). Changes in version 2.9-3 (2020-08-06) Bug-fixes o Removed deprecated argument LINPACK from all calls to solve. Fixes #109. Changes in version 2.9-2 (2020-02-18) Bug-fixes o Fixed minor bug in plot.cvrisk. Fixes #96. o Really check for leave-one-out crossvalidation if CoxPH was used. o Fixed minor bug in documentation: ... was described in documentation but was not used in function. Fixes #105. o Fixed a minor issue with special contrast "contr.dummy". Miscellaneous o Fixed typo in vignette. Changes in version 2.9-1 (2018-08-22) Bug-fixes o Dropped \itemize in ins/NEWS.Rd. Fixes #94. Changes in version 2.9-0 (2018-06-13) User-visible changes o Added family RCG for ratio of correlated gammas and downstream test, see Weinhold et al. (2016). Closes #86. o Removed corrected cross-validation for Cox models (Verweij and van Houwelingen, 1993) as it was not working. Closes #85. o Use partykit::ctree instead of party::ctree in btree and blackboost. This is slower but more flexible. o Allow multivariate negative gradients. Note that all elements are updated simultaneously, which in most cases is NOT what you want (but in rare cases it is the right thing to do). o Allow the specification of either mstop or grid in stabsel. o Allow leave-one-out crossvalidation (via type = "kfold"). Bug-fixes o Throw error when data is not compatibel (instead of silently recycling the vector). Fixes #79. o Fixed handling of offset for families NBinomial and Hurdle. Closes #88. o Replace cBind (now deprecated) with cbind. Fixes #90. o Fix predict with zero iterations (names were not correctly assigned). Fixes #87. o Fixed labels in plot function for categorical base-learners. Miscellaneous o Added further tests / checks. o Removed unused functions (response) and arguments (bnames from extract.glmboost). o Update email address and added ORCIDs. Changes in version 2.8-1 (2017-07-23) User-visible changes o Added all possible options to the specific boosting functions instead of passing the options via ... to mboost_fit. Closes #81. Miscellaneous o Minor speed ups in df2lambda (i.e., when computing penalty parameter for the defined degrees of freedom). Changes proposed by Benjamin Christoffersen. o Updated kernel boosting reference. Closes #84. o Rebuilt package with LF instead of CRLF to fix cleanup script as requested by CRAN. Fixes #82 o Use "old" definition of degrees of freedom in vignette("mboost", package = "mboost") to make results reproducible. Bug-fixes o Fix handling of missing values in mboost and gamboost when weights are specified. Fixes #80. Changes in version 2.8-0 (2017-05-04) User-visible changes o Models with zero steps (i.e., models containing only the offset) can now be fitted. Furthermore, cross-validation can now also select a model without base-learners. Fixes #64, #66, and #69. o Binomial now uses link functions by making use of make.link. Furthermore, an alternative implementation of Binomial models along the lines of the glm implementation can be used via Binomial(type = "glm"). Additionally, it works not only with a two-level factor but also with a two-column matrix containing the number of successes and number of failures. Fixes #34, #63 and #65. o Added new base-learner bkernel for kernel boosting as described in S. Friedrichs, J. Manitz, P. Burger, C.I. Amos, A. Risch, J.C. Chang-Claude, H.E. Wichmann, T. Kneib, H. Bickeboeller, and B. Hofner (2017), Pathway-Based Kernel Boosting for the Analysis of Genome-Wide Association Studies. _Computational and Mathematical Methods in Medicine_. 2017(6742763), 1-17. doi:10.1155/2017/6742763 . o Removed check if df2lambda is stable. Hence, options(mboost_check_df2lambda) (introduced in mboost 2.5-0) is no longer used. Closes #26. Miscellaneous o Added Andreas Mayr as contributor. o Updated references and added reference to citation("mboost"). o Fixed code of India example, which can be used to reproduce the data analysis presented in N. Fenske, T. Kneib, and T. Hothorn (2011), Identifying risk factors for severe childhood malnutrition by boosting additive quantile regression. _Journal of the American Statistical Association_, *106*:494-510. (see system.file("India_quantiles.R", package = "mboost")) o Fixed package citation. o Register C routines to make CRAN happy (again). Fixes #77. Bug-fixes o Make sure that family = Multinomial is only used with Kronecker product base-learners. Fixes #46. o Use argument PACKAGE in .Call. Fixes #72. o If center is specified as boolean value in bols, we now throw an error. Fixes #70. o Fixed AUC family which expected fit to be equal to a constant in the first iteration. o Check for new data, e.g., in predict, was broken. Fixes #68. o Make sure that newdata is discarded in fitted. Fixes #76. Changes in version 2.7-0 (2016-11-23) User-visible changes o New Cindex family to optimize survival models w.r.t. the concordance index. Fixes #53. o Added function varimp to extract variable importance. A dedicated plot function exists (plot(varimp())). Code was provided by Tobias Kuehn and Almond Stoecker. See pull request #29. o Improved plot function for boosting models: • plot fails earlier in case of multiple levelplots, i.e., maps (thanks to Mikko Korpela). See pull request #39. • Provide sensible defaults for xlab and ylab and allow user-specified axis labels for bi- and multivariate plots. Fixes #51. • Export plot functions (plot.glmboost, plot.mboost, lines.mboost, plot.varimp and plot.cvrisk) for better usability and visibility. Miscellaneous o Updated manual regarding the usage of families and clarified the usage of argument qoffset. o Updated manual for base-learners: • Highlight that x should be centered if bols(x, intercept = FALSE) is used. • Discourage using bbs(, constraint != "none"); Preferably use bmono for constrained effect estimates. Fixes #36. o Improved vignettes (thanks to Mikko Korpela). See pull request #38. Bug-fixes o Solve potential problem with IPCweights(). Fixes #54. o Drop unobserved factor levels from bols(). Fixes #47. o Adapt btree to changes introduced in package party. Fixes #58. o Improved cvrisk to be more robust in various use cases (thanks to Mikko Korpela). See pull request #42. o Be more careful regarding namespace scoping rules. Fixes #45. Changes in version 2.6-0 (2016-03-12) User-visible changes o New maintainer: Benjamin Hofner follows Torsten Hothorn as maintainer. o Package party is now imported. mboost no longer directly relies on unexported functions. o Allow extrapolation for predictions if kronecker products, tensor products or sums are used. Fixes #23. o Development now hosted entirely on github as boost-R/mboost. o Started using testthat. Miscellaneous o Improved checks for newdata: Warnings are no longer issued if data has just different types of numeric values (i.e., integer vs. double). Resolves issue #17. o Fixed CITATION by removing duplicated string 'R package version' (spotted by Heidi Seibold). o predict: Improve warning when length(offset) > 1. Closes issue #20. o Added test coverage using package covr. o Better error handling in cvrisk also for parallel processes. o Suppress warning of rankMatrix. (Resolves issue #24). o Stop exporting internal functions for FDboost. Use mboost_intern() instead. Caution: Do not use this function. Bug-fixes o Handling of missing values has been improved. Resolves issue #12. o Minor bug fixed in vignette mboost_illustrations.Rnw. o Throw an error if model cannot be fitted. Fixes issue #18. o Fixed bug in bkronecker with dense matrices. Resolves issue #30. Changes in version 2.5-0 (2015-08-14) User-visible changes o Added documentation for plot.mboost function and moved documentation of plot.glmboost to the same help page. Resolves issue #14. o bbs and bmono no longer allow data outside of the boundary.knots during model fitting. o Predictions for bbs and bmono now use linear extrapolation (user request inspired by mgcv::Predict.matrix.pspline.smooth). o Better handling of errors in (single) folds of cvrisk: results of folds without errors are used and a warning is issued. o Parallel computing via mclapply: Set mc.preschedule = FALSE per default. o Added new option options(mboost_check_df2lambda = TRUE), which controls if a stability check in df2lambda is performed. If set to FALSE this might speed up the computation of df2lambda especially with large design matrices. o Prediction now also possible with newdata = list(). Resolves issue #15. Miscellaneous o PropOdds(): Updated manual for proportional odds model. o Multinomial(): Updated manual for multinomial logit model. Predictions for new data are now possible (resolves issue #13, thanks to Sarah Brockhaus). o inst/CITATION: Added subheadings and tutorial paper. o Stopped computing the singular vectors in df2lambda as the singular values are sufficient and as “computing the singular vectors is the slow part for large matrices” (proposed by Fabian Scheipl). Bug-fixes o Fixed bug in PropOdds() which occurred if offset was specified: nuisance parameters delta and sigma were not properly initialized (spotted by Madlene Nussbaum). o Bug in plot.mboost() fixed which occurred if a factor with equal effect estimates for different categories was plotted. o Bug in df2lambda fixed: Make sure that A is symmetric if it is Matrix-object (spotted by Souhaib Ben Taieb). o Bug in df2lambda fixed. Design matrices were always assumed to be of full rank. o Truncate output of complete data structure when model is printed. Resolves issue #11. o Adhere to CRAN policies regarding import of base packages (closes #9). Changes in version 2.4-2 (2015-02-12) User-visible changes o Export df2lambda, hyper_bbs and bl_lin to make package FDboost happy. Note: These functions usually should not be called directly by users. Miscellaneous o Added Hothorn et al (2010) to inst/CITATION Bug-fixes o Changes in inst/CITATION to make CRAN happy: Citations can now be extracted without the need to install the package. o Removed EISPACK = FALSE from eigen() as the argument is defunct and ignored. o Changed require to requireNamespace Changes in version 2.4-1 (2014-12-16) Miscellaneous o Moved generic definition of selected to stabs which is required anyway (thus, stabs >= 0.5-0 is now required) o load AML dataset (AML_Bullinger.rda) from package TH.data o Updated references (for stability selection, confidence intervals and constrained regression) o fixed inst/CITATION o Refer to news(package = "mboost") instead of to the NEWS file. Bug-fixes o Cross-validation was potentially wrong for CoxPH() models. Users can now choose if they want the naive cross-validation or the improved version by Verweij and van Houwelingen (1993); (spotted by Holger Reulen ) o Examples in \dontrun are now executable and all dependencies are properly stated in DESCRIPTION Changes in version 2.4-0 (2014-10-02) User-visible changes o Added confint function to compute (bootstrap) confidence intervals together with plot and print methods o stabsel() now depends on the new package stabs where the back end and methods such as plot and print are implemented o Improved plot method for varying coefficients (ylim now suitable) and base-learners of factor variables. o Tweaked update function: we now can turn the trace on and off, and specify the type of risk as well as the oobweight to update() Miscellaneous o Updated vignette mboost_tutorial to reflect latest changes in mboost. o Changed plain text NEWS to inst/NEWS.Rd o Removed links to archived package mfp. o Explicitly specify the packages for functions that are implemented in packages that are listed as Suggests:, e.g we now use party::ctree_control etc. Bug-fixes o glmboost()$model.frame() was broken o glmboost()$update() was broken o predict() for models with non-scalar offsets was broken Changes in version 2.3-0 (2014-06-26) User-visible changes o stabsel was recoded and now uses different terminology, much more options and a better tested code base o new replacement function mstop<- as an alternative to [i] (suggested by Achim Zeileis). o bmono • new and faster algorithm to compute monotonic P-splines (type = "quad.prog") • new constraints added for positive and negative spline estimates o bbs • allows monotone T-splines (experimental) • new argument deriv to bbs for computing derivatives of B-splines o bmrf can now also handle neighborhood matrices as an argument to bnd o added new families Hurdle and Multinomial o boost_control: added new argument stopintern for internal stopping (based on oobag data) during fitting o All data sets have been moved to the new package set TH.data Miscellaneous o added new argument which to variable.names() o added new method risk to extract risks o brandom now checks that a factor is given o speed improvements when updating a model via mod[mstop] o changed \dontrun to \donttest o updated references Bug-fixes o fixed a problem with extract() of single base-learners o fixed bug in AIC.mboost: df = "actset" can only be used with glmboost models o fixed package start up messages o fixed a problem in mboost_fit (when names of base-learners were missing) Changes in version 2.2-3 (2013-09-09) o fixed bugs in survival families: • offset in all survival families was based on max(survtime) instead of max(log(survtime)); • offset in CoxPH can't be computed from Cox Partial LH as constants are canceled out; Use fixed offset instead; o speed up checking of manual by changing some computations (e.g. reduce mstop) or exclude code from checking via \dontrun{} o removed dependency on ipred (replaced with TH.data) o small improvements in manual Changes in version 2.2-2 (2013-02-08) o bbs(..., center = "spectralDecomp") computes the spectral decomposition of the penalty matrix and the penalized part of the design matrix is defined by this decomposition. Experiments show that bols(x) + bbs(x, center = "spectralDecomp") is a little better in recovering the true underlying functions than the default bols(x) + bbs(x, center = TRUE) or, equivalently, bols(x) + bbs(x, center = "differenceMatrix"). For bbs(x, y, center = TRUE) or bmrf(x, center = TRUE), the spectral decomposition is (and was) always used. o fixed bug in stabsel: '...' was not passed to cvrisk and thus one could not specify options for mclapply o fixed bug in brandom: now really use contrasts.arg = "contr.dummy" per default. o removed tests/ folder and .Rout.save files for vignettes from the CRAN release o small improvements in manual Changes in version 2.2-1 (2013-01-15) o included warnings in stabsel() for better guidance of the user: • A warning is issued if the upper bound for the FWER in stability selection is greater (by a certain margin) than the specified bound. • A warning is also issued if mstop is too small to select q variables. o improved output of errors and warnings in stabsel. o suppress the notes from package Matrix about method ambiguity ("Note: method with signature ... chosen, ... would also be valid") o updated manual on base-learners to reflect the change in the default for degrees of freedom (additionally, all options are now discussed in a separate section of the base-learner manual) o updated vignette mboost_tutorial o updated mboost_package.Rd: now all important changes since mboost 2.0 are documented there o changed roles of contributors to ctb o suggested packages are now only used inside if(require(pkg)) statements o changed start up message Changes in version 2.2-0 (2012-11-27) o switch from packages multicore and snow to parallel o changed behavior of bols(x, intercept = FALSE) when x is a factor: • now the intercept is simply dropped from the design matrix • coding can be specified as usually for factors. o changed default for options("mboost_dftraceS") to FALSE, i.e., degrees of freedom are now computed from smoothing parameter as described in B. Hofner, T. Hothorn, T. Kneib, M. Schmid (2011). o changed computation of B-spline basis at the boundaries: now also use equidistant knots in the boundaries (per default) o improved plot function when dealing with spatial plots (now builds suitable grid based on the observations if no newdata is given) o increased default number of subsampling replicates in stabsel to 100 o [experimental] bmono() now implements constraints at the boundaries of (monotonic) P-splines o [experimental] added family Gehan() for rank-based estimation of survival models in an accelerated failure time framework (contributed by Brent Johnson ) Changes in version 2.1-3 (2012-09-27) o matrices with one column are now handled as vectors in base-learners o improved manual o fixed error that occurs with R (>= 2.16) due to internal changes in R Changes in version 2.1-2 (2012-02-29) o improved handling of missing values (throws warnings and fixed a bug that occurred for missings in the response) o improved manual for the handling of contrasts in bols o added tutorial vignette o updated references Changes in version 2.1-1 (2011-11-29) o new option "mboost_eps" for factor in Demmler-Reinsch orthogonalization Changes in version 2.1-0 (2011-11-15) Base-learners o added base-learners for smooth monotonic (or convex/concave) functions of one or two variables (bmono()) o added base-learners for radial basis functions (brad()) o added base-learners for Markov random fields (bmrf()) o bbs(x, cyclic = TRUE) for cyclic covariates ensures that predictions at the boundaries coincide and that the resulting function estimate is smoothly joined o bols(x, intercept = FALSE) only reasonable if x is centered. A warning is now issued if x is not centered. o changed default for degrees of freedom in bspatial() to df = 6 o added checks in bbs (and brandom) to ensure that the specified degrees of freedom are greater than the range of the (unpenalized) null space o bolscw can be mixed with other base-learners (although not yet exported and not via the formula interface) o new experimental base-learner %O% for smoothing matrix-values responses Families o add Binomial(link = "probit") and general cdf's as link functions (experimental) o added new families: • AUC() for AUC loss function • GammaReg() for gamma regression models Methods o added extract() methods for base-learners and fitted models o added residuals() function to extract residuals from the model o improved predict.mboost(): added names where missing and the offset as attribute where applicable. o fixed bug in predict() with glmboost.matrix(..., center = TRUE) o coef now also works with tree base-learners (returns NULL in this case) o changed coef.gamboost to coef.mboost o various improvements in plot.mboost function Miscellaneous o changed default in glmboost() to center = TRUE o speed up glmboost() a little bit o changed behavior of cvrisk() if weights are used: out-of-bag-risk now weighted according to "weights" as specified in call to mboost o added warning if df2lambda is likely to become numerically unstable (i.e. in the case of large entries in the design matrix) o improved storage, speed and stability using Matrix technology for bols() for factors with many levels and brandom(); further improvements in base-learners that are combined via %+%. o various improvements and fixes in manuals Changes in version 2.0-12 (2011-08-22) o minor bug-fixes to make mboost work with gamboostLSS o replaced writeLines with packageStartupMessage in .onAttach() o replaced partially matched function arguments by full arguments o minor fixes in manuals Changes in version 2.0-11 (2011-04-13) o fix problem in bl_lin when using dense matrices from package "Matrix" Changes in version 2.0-10 (2011-02-20) o add rqss results for India childhood malnutrition data Changes in version 2.0-9 (2010-11-19) o add gbm to Suggests Changes in version 2.0-8 (2010-11-15) o make survival package happy again Changes in version 2.0-7 (2010-09-30) o vignette "mboost" updated o remove problem with R CMD check that occurred on some 64bit systems Changes in version 2.0-6 (2010-05-22) o no not use multicore functionality in R CMD check, really. Changes in version 2.0-5 (2010-05-22) o no not use multicore functionality in R CMD check Changes in version 2.0-4 (2010-04-15) o new vignette "mboost" describing 2.0-x series features o fixed bug in bols(): contrast.arg was ignored if not a named list (which is wasn't per default) o added (missing) response functions to families Weibull(), Loglog(), Lognormal() and NBinomial() o fixed bug in family CoxPH which occurred with NAs o improvements and corrections in documentation Changes in version 2.0-3 (2010-03-10) o glmboost(..., center = TRUE) now also centers columns of the design matrix corresponding to contrasts of factors when an intercept term is present leading to faster risk minimization in these cases. o coef.glmboost: New argument off2int = TRUE adds the offset to the intercept. In addition, the intercept term is now adjusted for centered covariates. o check for infinite residuals in mboost_fit(). Especially for family = Poisson(), something like boost_control(nu = 0.01) fixes this problem. o "by" (in bols() and bbs()) can now handle factors with more than two levels o improved plot.mboost() for varying coefficients o minor improvements in documentation Changes in version 2.0-2 (2010-03-05) o fixed bug in helper function get_index, which caused (in some circumstances) wrong handling of factors in gamboost() (spotted by Juliane Schaefer ) o reduce memory footprint in blackboost (requires party 0.9-9993) Changes in version 2.0-1 (2010-03-01) o fixed bug in coef( , aggregate = "cumsum"): fraction "nu" was missing Changes in version 2.0-0 (2010-02-01) o generic implementation of component-wise functional gradient boosting in mboost_fit, specialized code for linear, additive and interaction models removed o new families available for ordinal, expectile and censored regression o computations potentially based on package Matrix (reduces memory usage) o various speed improvements o added interface to extract selected base-learners (selected()) o added interface for parallel computations in cvrisk with arbitrary packages (e.g. multicore, snow) o added "which" argument in predict and coef functions and improved usability of "which" in plot-function. Users can specify "which" as numeric value or as a character string o added function cv() to generate matrices for k-fold cross-validation, subsampling and bootstrap o new function stabsel() for stability selection with error control o added function model.weights() to extract the weights o added interface to expand model by increasing mstop in model[mstop] o alternative definition of degrees of freedom available o Interface changes: • class definition / Family() arguments changed • changed behavior of subset method (model[mstop]). Object is directly altered and not duplicated • argument "center" in bols replaced with "intercept" • argument "z" in base-learners replaced with "by" • bns and bss deprecated; Changes in version 1.1-4 (2009-11-18) o fixed bug in prediction with varying coefficients for binary effect modifiers Changes in version 1.1-3 (2009-09-23) o better x-axes in plot.cvrisk and possibility to change xlab o parallel cvrisk on Unix systems only (multicore isn't safe on windows) o included new penalty for ordinal predictors (in bols()) o corrected bug in bspatial (centering was not used for Xna) o removed output of dfbase (which is seldom used) in gamboost o changed manual for coef.gamboost o make sure NAs are handled correctly when center = TRUE in glmboost Changes in version 1.1-2 (2009-07-21) o better weights and boundary knots handling in bspatial o cvrisk runs in parallel if package multicore is available o errors removed and minor improvements in the manuals o center = TRUE in glmboost did only apply to numeric (not integer) predictors o for safety reasons: na.action = na.omit again (causes slight changes in wpbc3 example) Changes in version 1.1-1 (2009-04-22) o new quantile regression facilities. o fix problem with bbs base-learner and cvrisk Changes in version 1.1-0 (2009-03-27) o bbs instead of bss is the default base-learner in gamboost o make sure bbs with weights and expanded observations returns numerically the very same results o btree can now deal with multiple variables o new gMDL criterion (contributed by Zhu Wang ) o make survival package happy again Changes in version 1.0-6 (2009-01-09) o bols allows to specify non-default contrasts. Changes in version 1.0-5 (2008-12-02) o remove experimental memory optimization steps Changes in version 1.0-4 (2008-11-13) o negative gradient of GaussClass() was wrong, spotted by Kao Lin Changes in version 1.0-3 (2008-11-07) o Date was malformed in DESCRIPTION Changes in version 1.0-2 (2008-11-06) o improved memory footprint in gamboost() and cvrisk() o option to suppress saving of ensembles added to boost_control() o bbs(), bns(), bspatial(): default number of knots changed to a fixed value (= 20) o changed default for grid (now uses all iterations) in cvrisk() and changed plot.cvrisk() o bols: works now for factors and can be set-up to use Ridge-estimation. Intercept can be omitted now (via center = TRUE). o new btree() base-learner for gamboost() available o fix inconsistencies in regression tests o add coef.gamboost o new generic survFit o cosmetics for trace = TRUE Changes in version 1.0-1 (2007-12-09) o inst/mboost_Bioinf.R was missing from mboost 1.0-0 Changes in version 1.0-0 (2007-11-13) o documentation updates Changes in version 0.9-0 o tests update and release the new version on CRAN o predict(..., allIterations = TRUE) returns the matrix of predictors for all boosting iterations Changes in version 0.6-2 o move mboost to R-forge o improvements in gamboost: o P-splines as base learners available o new formula interface for specifying the base learner o new plot.gamboost o add the number of selected variables as degrees of freedom (as mentioned in the discussion of Hastie to Buehlmann & Hothorn) o status information during fitting is now available via boost_control(trace = TRUE) but is switched off by default o acknowledge contributions by Thomas Kneib and Matthias Schmid in DESCRIPTION Changes in version 0.6-1 o gamboost() now allows for user-specified base learners via the formula interface o gamboost.matrix(x = x, ...) requires colnames being set for x o na.action = na.omit fix for g{al}mboost() Changes in version 0.5-8 (2007-05-31) o gamboost(..., weights = w) was broken Changes in version 0.5-7 (2007-05-30) o extract response correctly in fitted.blackboost o hatvalues (and thus AICs) for GLMs with centering of covariates may have been wrong since version 0.5-0 o add paper examples to tests Changes in version 0.5-6 (2007-05-07) o fix Rd problems Changes in version 0.5-5 (2007-04-25) o westbc regenerated o LazyLoad: yes (no SaveImage: yes) Changes in version 0.5-4 (2007-04-19) o plot() method for glmboost objects visualizing the coefficient path (feature request by Axel Benner ). o predict(newdata = ) was broken for gamboost(), thanks to Max Kuhn for spotting this. Changes in version 0.5-3 (2007-03-23) o predict() for gamboost(..., dfbase = 1) was not working correctly o small performance and memory improvements for glmboost() Changes in version 0.5-2 (2007-02-28) o some performance improvements for glmboost() o blackboost() is now generic with formula and x, y interface o plot() method for cvrisk() and AIC() output now allows for ylim specification without troubles Changes in version 0.5-1 (2007-02-02) o depends party 0.9-9 Changes in version 0.5-0 (2007-02-01) o new baselearner argument to gamboost allowing to specify difference component-wise base-learners to be used. Currently implemented: "ssp" for smoothing splines (default), "bsp" for B-splines and "ols" for linear models. The latter two haven't been tested yet. o The dfbase arguments now applies to each covariate and no longer to each column of the design matrix. o cvrisk() for blackboost() was broken, totally :-( o centered covariates were returned by glmboost() and gamboost() o Poisson() used an incorrect offset o check for y being positive counts when family = "Poisson()"[B o checks for Poisson() logLik() and AIC() methods o fire a warning when all u > 0 or u < 0 o update vignette mboost_illustrations Changes in version 0.4-17 (2007-01-15) o fix problem with dfbase in gamboost, spotted by Karin Eckel Changes in version 0.4-16 o work around stats4:::AIC Changes in version 0.4-15 (2006-12-06) o fix plot problems in plot.cvrisk o allow for centering of the numerical covariates in glmboost and gamboost Changes in version 0.4-14 (2006-10-27) o AIC(..., "classical") is now faster for non-Gaussian families Changes in version 0.4-13 (2006-10-04) o predict(..., newdata) can take a matrix now Changes in version 0.4-12 (2006-09-13) o predict(, type = "response") did not return factors when the response was actually a factor o report offset in print methods o add offset attribute to coef.glmboost Changes in version 0.4-11 (2006-09-07) o add contrasts.arg argument to glmboost.formula o more meaningful default for grid in cvrisk o R-2.4.0 fixes Changes in version 0.4-10 (2006-08-31) o add checks for CoxPH (against coefficients and logLik of CoxPH) o add weights to CoxPH o the ngradient function in Family objects needs to implement arguments (y, f, w), not just (y, f) o check for meaningful class of the response for some families Changes in version 0.4-9 (2006-07-18) o some small speed improvements in gamboost o handle factors in gamboost properly (via a linear model) o the dfbase argument can take a vector now (in gamboost) o update and improve entries in DESCRIPTION o documentation updates Changes in version 0.4-8 (2006-07-05) o Huber() is ‘Huber Error’, not ‘Huber Absolute Error’ o added CoxPH family object for fitting Cox models o remove inst/LaTeX o use NROW / NCOL more often (now that y may be a Surv object) o implement cvrisk, a general cross-validation function for the empirical risk and a corresponding plot method o unify risk computations in all three fitting functions o unify names for gb objects o allow for out-of-bag risk computations o some cosmetics o update keywords in Rd-files o risk was always 0 in Huber()@risk when d was chosen adaptively o pData(westbc)$nodal.y has levels negative and positive (lymph node status) Changes in version 0.4-7 (2006-06-19) o add src/Makevars (required for Windows builds) o make sure objects that are modified at C-level get _copied_ in blackboost Changes in version 0.4-6 (2006-06-14) o some minor codetools fixes: removed unused variables and an out-dated function o add codetools checks to regression tests o fix xlab in plot.gbAIC o mboost version 0.4-5 published on CRAN 2006-06-13