skpr v0.61.3 (Release date: 2019-09-18): ================ Minor changes: • Added `reorder_factors` argument to eval_design() as an option to iteratively search for the most conservative reference level and report that power for effect power skpr v0.61.2 (Release date: 2019-08-12): ================ Minor changes: • `gen_design()` Fix blocking issue • `skprGUI()` Add lmerTest to code pane • `extractPvalues()` Fix test issue with >1 length logical • Linting changes (adding spaces) skpr v0.61.2 (Release date: 2019-05-29): ================ Minor changes: • Add error message for binomial effect sizes outside of allowable range skpr v0.61.0 (Release date: 2019-03-11): ================ Major changes: • `eval_design_mc()` Added option to retrieve simulated responses by setting advancedoptions = list(save_simulated_responses = TRUE) • `eval_design()` Fixed degrees of freedom when intra-plot interaction terms present Minor changes: • `eval_design_mc()` Suppress warning messages for effect power calculations during Monte Carlo power simulations and handle case when Anova cannot be fit skpr v0.60.0 (Release date: 2019-03-11): ================ Major changes: • Add empirical alpha correction in non-Gaussian Monte Carlo simulations to correct for inflated type-I error Minor changes: • Added code to always clean up parallel R sessions skpr v0.59.0 (Release date: 2019-02-12): ================ Major changes: • Fixed issues when intercept not included in model but categorical factor present Minor changes: • Compartmentalized code in eval_design to make it easier to understand • Documentation improvements skpr v0.58.0 (Release date: 2018-12-21): ================ Major changes: • Updated eval_design to adjust degrees of freedom as specified in Pinheiro and Bates Minor Changes/Bug fixes • Removed warning about tibbles • Changed blocking structure warning to message • Adjusted attribute names skpr v0.57.0 (Release date: 2018-09-21): ================ Major changes: • Changed "RunMatrix" argument to "design" in evaluation functions. Minor Changes/Bug fixes • Fixed bug with model ordering when augmenting an existing design • Reduce replication in code and improve documentation skpr v0.56.1 (Release date: 2018-09-21): ================ Major changes: • Major code clean-up to standardize style and spacing within code • `magrittr` pipe %>% now imported by default Minor changes/Bug fixes: • Split-plot design generation bugfixes for interactions between whole and subplots skpr v0.54.3 (Release date: 2018-08-08): ================ Major changes: • Added Monte Carlo effect power through the `car` package's Anova function Minor changes/Bug fixes: • Change correlation plot palette to viridis • Bugfix for disallowed combinations between nesting levels in split-plot designs • Fixed missing varianceratios documentation in eval_design_mc • Changed file paths to use file.path() skpr v0.53.4 (Release date: 2018-07-11): ================ Bug fix: • Fixed uninitialized memory issue in C++ code skpr v0.53.3 (Release date: 2018-07-11): ================ Major changes: • `gen_design()` Added design augmentation • `gen_design()` Removed all limitations to split-plot design generation--all optimality criteria are now available • `gen_design()` Added `randomized` argument if the user does not want the design randomized • Added `skprGUIserver()`, the asynchronous version of `skprGUI()`. Implemented with a custom version of async based on the future package to support progress bars Minor changes/Bug fixes: • Moved `progressBarUpdater` argument into new `advancedoptions` argument for `eval_design_mc()` • Added partial separation warning to console for non-GUI binomial monte carlo evaluations in `eval_design_mc()` • Changed `gen_design()` so that user doesn't have to fill out `splitplotsizes` argument unless they want to manually specify the block sizes--skpr will try to create the most balanced design for the given number of trials • Standardized skprGUI, skprGUIbrowser, and skprGUIserver • Fixed bug with non-disappearing "block" pane in skprGUI when no htc factors. • Fixed `.` treatment in GUI to work properly in all cases with split-plot designs. • `gen_design()` Fixed bugs with I, A, and G-optimal split-plot design generation. • Added seed to test_that script. • `gen_design()` Fixed bug(s) in computing I and A-optimality for the design attributes. • `gen_design()` Fixed bug related to disallowed combinations with split-plot designs. • `gen_design()` Improved G-optimality search speed with rank-2 update formula. • `plot_correlations()` Fixed missing variance-covariance matrix • `plot_correlations()` Added `drop=FALSE` arguments to prevent conversion of dataframes to vectors • `plot_correlations()` Updated to accept arguments to the `par` function in base R Deprecations: • `eval_design_mc()` Removed deprecated "binomialprobs" argument. skpr v0.49.1 (Release date: 2018-05-30): ================ Bug fixes: Fixed memory access issue for the CRAN. skpr v0.49.0 (Release date: 2018-05-16): ================ Major changes: • Switched underlying linear algebra library from Armadillo to Eigen. Significant speed-up for all design searches. Added rank-2 update formula to speed-up Alias-optimal, I-optimal, and A-optimal designs. • `gen_design()` now rearranges the levels for categorical factors from fewest to most number of observations for unbalanced designs (default ordering in R if equal). • `gen_design()` argument "advancedoptions" now has an option to turn off alias-based tie breaking. • Re-implemented `.` handling in formulas to align more with `lm()`. Minor changes/Bug fixes: • Fixed Alias-tie breaking non-linearity. • Updated GUI code pane to show actual model being used (instead of dots). • Improved error handling of code pane. • Fixed conservative anticipated coefficient bug that occurred when 3+ parameter powers were equal. • Fixed bug with generation of anticipated coefficients for interactions with quadratic effects. Deprecations: • `quad(.)` function support removed. skpr v0.47.4 (Release date: 2018-03-16): ================ • Implemented several optimizations that vastly improve speed and performance for D-optimal design generation. • Added support for bookmarking in the GUI. • Added advanced options argument to control tolerances for the design search and optimal tie-resolution, and an option to specify which power of aliasing should be used in resolving ties. • Removed references to deprecated delta argument. • Fixed conservative anticipated coefficients bug. • Fixed bug with comparison of floats • Fixed issue with non-reproducibility of generating parallel designs by using the doRNG package. • Updated documentation with changes. skpr v0.45.2 (Release date: 2018-01-22): ================ Major changes: • Changed optimal search algorithm to return design with best aliasing structure (as determined by the alias matrix) when there is a tie between optimal designs. Increases likelyhood of producing an orthogonal design. • Added support for mixture designs in evalulation functions. Generation is already supported in gen_design by removing the intercept from the model. • Added support for backticked variables in evaluation functions and plotting functions. Made non-support for backticked variables explicit in gen_design. • Added user-defined "custom" optimality option, where the user can define their own optimality criterion as an R function of the model matrix. This will be slower than the built-in criteria, but provides a great deal of flexibility--especially because the optimality functions can be written without any C. Function needs to be named "customOpt" and be in the global environment. • Updated split-plot design generation to support Alias-optimal, T-optimal, and user-defined custom optimal designs. For custom designs, user needs to create a function named "customBlockedOpt" that is a function of the model matrix, as well as the variance-covariance matrix vInv. Should look like the following: customBlockedOpt = function(customdesign, vInv) {calculate optimality criterion} • Implemented support for plot_correlations and plot_fds in output of eval_design_mc. Added required attributes to output. Minor changes: • Changed minDopt to 0.8 to return better screening designs. • Changed default number of repeats to 20. • Changed plot_correlations to use two-color scheme by default. • Changed G-optimal design search to start from a D-optimal design. • Added color to GUI design. Added ability to change color palettes. • Added option to remove design randomization in GUI. • Major UI updates for the GUI, changing the style away from default Shiny app. Bug fixes: • Changed singularity testing to use more robust function. • Fixed E-optimal split-plot design generation. • Fixed bug in split-plot non-singular design generation. • Fixed is.numeric bug with plot_correlations in Shiny. • Fixed bug with missing contrast list with hard-to-change factors. Fixed bug where factors were converted to integers with split-plot designs. • Fixed bug in eval_design_survival_mc with contrast generation after reducing the run matrix. • Fixed subsetting bug in automatic blocking column detection, turning on drop=FALSE. Fixed bug when external blocking columns were not ordered correctly. Changed name of internal block columns (Block# to skprBlock#) to make sure they don't interfere with user-generated columns. • Fixed uninformative error message when optimality criterion not recognized when generating designs. Standardized input for optimality criterion to always use upper case. • Updated/fixed/added unit tests. skpr v0.40.1 (Release date: 2017-10-20): ================ • Fixed significant bug with parallel design generation that broke automatic detection of the number of cores available. • Changed non-split-plot D-optimal design search to use modified Fedorov's algorithm with delta function (changed from modified Fedorov's, without delta function). Decreases search time for complex designs or designs with many trials. • Turned off OPENMP warning for all c++ files. skpr v0.39.0 (Release date: 2017-10-15): ================ • All the evaluation functions will now respect pre-set contrasts for categorical factors. If a contrast isn't set for a factor, it will use the contrast set in the contrasts argument. • Added the ability for the user to specify the number of cores manually by setting options(cores=). Otherwise, gen_design will use all cores available if parallel=TRUE. • Added the ability for the user to interrupt the design search in gen_design for both single core and multicore searches. When user interrupts parallel search, gen_design will properly stop and close all connections. • Added calculation of effect power for interaction terms and higher order terms. • Changed eval_design so that the output always reports parameter power even if all factors are continuous. • Fixed bug in eval_design_custom_mc which resulted in imported designs overwriting the generated list of contrasts with NULL. • Changed delta argument to more descriptive "effectsize". Updated documentation and codebase to reflect this change. Effect size now accepts a length-two vector to either explicitly specify the difference in the high and low levels, or to specify GLM-family specific effect sizes. Updated GUI to reflect effectsize change. • Changed Monte Carlo simulated estimates plot for exponential GLMs to show mean parameter rather than rate. • Fixed bug when tibble was converted to data frame and didn't convert the character columns to factors. Turned off OPENMP warning in compilation • Added support for ~.*. operator, allows user to specify full interaction model (no quadratic terms). • Updated documentation. skpr v0.35.1 (Release date: 2017-08-17): ================ Initial release.