NEW: A new optimizer, which uses generalized simulated annealing, has been implemented.IMPROVED: WLS moved to the backend: 10x faster!.IMPROVED: parallel processing improved by addition of ConcurrentQueue.
Critical ops hack 4.0.1 how to#
A paper describing how to use it to analyze molecular genetic data is in preparation. EXPERIMENTAL: mxComputeLoadData supports high-throughput data analyses.IMPROVED: mxOption has a reset argument, to reset all options to their on-load defaults.IMPROVED: mxOption model now conveniently defaults to NULL.IMPROVED: mxTryHard progress reporting much improved!.
IMPROVED: mxRun progress printing is now much easier to read.IMPROVED: mxData allows non-positive-definite observed covariance matrix if type = “acov”.NEW: mxJiggle: emulate the effect of keyword JIGGLE from classic Mx, or (default) function as a wrapper to the pre-existing imxJiggle().IMPROVED: omxSetParameters warns if you don’t ask to do anything.NEW: omxReadGRMBin loads a genomic-relatedness matrix into R’s workspace from a GCTA-format binary file.IMPROVED: summary now reports a p-value of 1 if the chi-square test statistic has zero degrees-of-freedom.IMPROVED: WLS summary statistics now taking advantage of multiple CPU cores: 40x faster :-).HELP: mxRefModels now raises a warning if it is used on an MxModel that contains definition variables, or is a multilevel model.EXPERIMENTAL: mxAlgebra gives users the option of populating an MxAlgebra with initial values, and of only recomputing the MxAlgebra when specifically called-for.NEW: vcov works with models that contain MxConstraints (so does `m1$vcov’).NEW!: SEs for models with constraints! (used not to be calculated.IMPROVED: mxPowerSearch supports un-equal N in multi-group models, as specified by user’s trueModel.IMPROVED: mxPower Clarify N reported by mxPower is total N, not average/group.IMPROVED: mxGenerateData returns data of the type in the model (when `returnModel = TRUE``).FIXED: Bug mxPower where we were not respecting requested p-values.FIXED: Bug mxPowerSearch was ignoring the user N.FIXED: Bug mxFactorwhere RAM regression scores did not always include the means.FIXED: Bug prevented estimation of factor score when there was more than one latent factor (v2.14.11-87-g6af1bf6fe).FIXED: Bug affecting RAM models: cov data was not reordered correctly to match model.IMPROVED: mxRun informs user about any unrecognised parameters (… parameters).IMPROVED: Better error messages in several functions.IMPROVED: WLS fit statistics much faster.IMPROVED: SLSQP can calculate gradients in parallel when optimizing the WLS models.FIXED: Bug leading to random number of threads being used for SLSQP gradient elements.FIXED: Bug in mxTryHard returning incorrect chi-square for WLS fixed.FIXED: Bug in mxGenerateData where use.miss was ignored if nrowsProportion was set.NEW: suport for count variables Poisson or negative-binomial distribution, with or without zero-inflation.NEW: predict implemented (only) for state-space models.CHANGE: mxRun throws an error if OMP_NUM_THREADS is exceeded.
Critical ops hack 4.0.1 free#
Critical ops hack 4.0.1 update#
OpenMx developers, being lazy and incorrigible, often forget to update the NEWS file.