Changes in version 1.1.54 (2026-03-01) o Replace (direct) calls to Rf_error() with Rcpp:stop() (cf https://github.com/RcppCore/Rcpp/issues/1247). o Trivial code and doc tidying, and updated links to now public gitlab repository. Changes in version 1.1.46 (2023-12-08) o Resolve -Wsometimes-uninitialized, -Wformat-zero-length and -Wformat-security compiler warnings. o Resolve "lost braces" issue in a documentation page. Changes in version 1.1.43 (2023-05-03) NEW FEATURES o Much faster init_grid() (and likely more minor gains in other functions too). o New init_grid(., maxmin) argument. DEPENDENCIES o New dependency 'matrixStats'. Changes in version 1.1.32 (2020-04-20) USER-LEVEL CHANGES o Checks of invalid input (and resulting screen output) adapted to non-Migraine usage. DEPENDENCIES o 'lbfgsb3' is replaced by 'lbfgsb3c' as a suggested package. o Requests a more recent (>= 3.1.0) version of 'spaMM'. Changes in version 1.1.27 (2019-08-20) CORRECTED BUGS o Long-standing glitch that substantially slowed blackbox down (though with correct results). Changes in version 1.1.25 (2018-06-08) USER-LEVEL CHANGES o (Migraine-specific) New composite parameters and profile computations for migration parameters. o Dependency on 'ff' package removed, assuming a recent version of spaMM (here >= 2.4.8). o Dependencies changed for parallel computations. See help("blackbox.options") for details. CORRECTED BUGS o (Migraine-specific) writeFinalInfo() now correctly writes the results when sampleByResp() has not been run. o (Migraine-specific) CKrigcoefs() could fail when minSmoothness=maxSmoothness. o (Migraine-specific) user-given 'CovFnParam' were ignored. o (Migraine-specific) now computes Dgmu parameter only when Dg/2N is a parameter of the model (e.g. not a for a discrete change in pop size). o (Migraine-specific) resetCHull() handles input points in linear space of lower dimension than the number of fitted parameters, now avoiding a bug in the rare case where there are many profile points, all of them in such a space. Changes in version 1.1.7 (2017-11-03) USER-LEVEL CHANGES o No user-level changes. OTHER CHANGES o Changes for compatibility wth Rcpp::compileAttributes() in Rcpp >= 0.12.12 o Other internal changes for compatibility with planned changes in other packages. Changes in version 1.1.2 (2017-09-05) USER-LEVEL CHANGES o (Migraine-specific) Parallel computation is implemented for profile point computations. Changes in version 1.1.0 (2017-07-05) USER-LEVEL CHANGES o Less primitive convergence diagnostics are implemented in bboptim(). o (Migraine-specific) New mesures of ''goodness of prediction'' implemented. o (Migraine-specific) add logscale for 1D profile plots CORRECTED BUGS o blackbox.options() did not return old values. o (Migraine-specific) Return code modified for consistency with documentation (but this does not really affect the analyses). o (Migraine-specific) variables names could be lost in generateNewPoints(). o (Migraine-specific) Invalid requests by users for CIs for some composite variables could lead to an execution error. OTHER CHANGES o Added native routine registration. Changes in version 1.0.18 (2017-02-02) BUGS o More C++ portability issues fixed. o (Migraine-specific, without any impact on inferences) optimization convergence diagnostic (actually nloptr()'s return status) was missing from the output_...txt file, resulting in lines with different number of values. o (Migraine-specific) toCanonical() corrected to handle single-candidate input matrix. o (Migraine-specific) fixed parameter space issues in generateNewPoints() and canonize(). USER-LEVEL CHANGES o Modified init values of some smoothing parameters may change bboptim() results for rough response surfaces. OTHER CHANGES o Some function definitions has been moved from the spaMM package to blackbox. Changes in version 1.0.8 (2016-05-25) BUGS o (Migraine-specific) Wrong variable spaces in generateNewPoints() and toCanonical() corrected. o (Migraine-specific) Calls to Rf_error() removed from Rcpp code. o (Migraine-specific) An invalid cbind() that affected the generation of 'nextpoints' has been corrected. o (Migraine-specific) Within subHullWrapper(), the scdd() results with double precision are now checked and replaced by a computation with rational arithmetic if they are inaccurate. o (Migraine-specific) "samplingSpace=,Nb," has been broken for a long time. This is corrected. o (Migraine-specific) sampleNextPars() could stop when called with non-default 'samplingSpace'. This is corrected.