Changes in version 1.3.4 (2019-11-14)

New features

- added preliminary support for specification search (for the optimal set of
  predictors to include in the model specification) as an enhancement for
  cross validation

Changes

- tolerance of lp solver changed slightly

- added some flexibility (for the labels) to the ggplot method

- removed some unused (and unexported) code

- improveSynth now also checks whether the donor weights of synth()'s solution
  sum up to 1 (which they often do not!) and now also works when custom.v 
  is set in the preceding synth()-call. Checks for optimality are now (solely)
  based on relative suboptimality. This leads to a slight change in the
  corresponding vignette.


Bug fixes

- added missing author information for LINPACK/SLATEC Fortran code (many 
  thanks to Prof. Brian D. Ripley for the hint)


Changes in version 1.3.3 (2018-05-04)

Changes

- minor documentation update (references)

Bug fixes

- Fixed a bug in mscmt for multivariate applications introduced in
  version 1.3.2


Changes in version 1.3.2 (2018-02-19)

New features

- added list element 'predictor.table' containing aggregated statistics of
  predictor values to output of 'mscmt' (feature request)
  
Changes

- list element 'dataprep.scaled' (in output of 'mscmt') now contains unscaled
  variants 'X0.unscaled' and 'X1.unscaled' of (aggregated) predictor values


Changes in version 1.3.1 (2018-01-04)

Changes

- minor documentation update (references)

Bug fixes

- some fixes/increased robustness for edge cases (e.g. single predictor)

- progress bar fixed (thereby eliminating compiler warnings)


Changes in version 1.3.0 (2017-08-17)

New features

- cross validation is now supported by function mscmt, see the corresponding
  documentation.

Changes

- point size is now settable in ggplot.mscmt.

- lp's in ill-conditioned problems are now tackled with the help of various
  lp solvers to improve robustness. Packages Rglpk and lpSolveAPI are required
  now.

Bug fixes

- 'no sunny donors' case fixed.

- gamma-factors fixed.

- some small bug fixes in ggplot.mscmt.


Changes in version 1.2.0 (2017-01-30)

New features

- automatic repeated estimation with different outer optimizers and random 
  seeds, optionally on a cluster.

Changes

- reasonable default parameters and documentation for outer optimizers
  have been added.

- improved cluster support: (malfunctioning) load balancing with parLapplyLB 
  replaced by load balancing via clusterApplyLB.

Bug fixes

- fixed special treatment of 'one sunny donor' case.


Changes in version 1.1.0 (2016-11-29)

New features

- newly supported outer optimizer "none" to implant 'artificial' solutions 
  (fixed w and optionally fixed v).

- many new outer optimizers are now supported, more documentation will follow.
  
- function compare() for comparison of estimation results, 
  including corresponding updates for print.mscmt and ggplot.mscmt.

Changes

- names of agg.fns (component of mscmt results) are now set automatically.

- user-defined agg.fns are now automatically exported to the cluster.

- changed default optimizer to DEoptC.

- predictor weights are not printed any more as verbose output in estimations.

- some packages were moved from "Imports" to "Suggests".

- number of calls to inner optimizer is now counted for benchmarking purposes.

- package startup message added.

Bug fixes

- objective function weights alpha/beta/gamma are now treated correctly.

- calls to the lp solver are now more robust.

- some typos in vignettes have been corrected.

- all data had to be sorted chronologically, this is now optional.

- improveSynth reported wrong 'True' W*(V) if W*(V) was not optimal.


Changes in version 1.0.0 (2016-07-25)

New features

- first public release of this package.

Changes

- no changes yet

Bug fixes

- no bugfixes yet
