- Fixed a crash when ignoring categoric factors with no data.
- Values smaller than 3.0E-12 can now be used for factor low and high settings.
- Fixed missing legend in contour plot with binary data.

- Changes made to the histogram axes are now saved with the design file.
- Factor and response names can now be toggled on in the graph legend, via the right-click menu.
- Axis settings will now restore correctly when loading a file saved with the comma decimal separator.
- Fixed an issue that was causing 2FI process terms to always be selected in certain combined designs.
- Fixed a crash that would occur in the diagnostics node when using an overspecified model with logistic regression.

- Fixed incompatibility with macOS Sierra and earlier.
- Fixed crash when analyzing a Simple Sample design with binomial data.
- Fixed crash selecting a term for the DFBETAS plot using the enter key.

- Fixed crash when inserting a response.
- Fixed a bug preventing copying to the clipboard in macOS.
- Design Wizard font is now white when in Dark Mode on macOS.
- The “Equal To” criteria setting should now display properly with discrete factors.
- The contour value list in the Edit Contour menu now updates when the default button is pressed.
- The alias report now shows block aliases when building a blocked factorial design.
- Pasting data from Excel in macOS no longer inserts unwanted blank lines.

- Added support for Dark Mode in macOS.
- Resized dropdown lists that were too small in macOS.
- Contour labels are now draggable.
- Removed unnecessary information from the Box-Cox legend.
- Categoric level names are now shown on the Residuals vs Factor plot.
- Removed the option to delete criteria contours from the Graphical Optimization graph.
- Fixed a bug where the Cube plot would show incorrect observed values in certain situations.
- Long factor names are now truncated in the graph legends.
- You can now copy the Effects table to the clipboard.
- The navigation pane will no longer scroll up when analyzing a response.
- Fixed a crash in the Histogram plot when there are no response data.
- Fixed a crash that occurred when cancelling an augment.
- Fixed a crash when entering an invalid response equation.

- Histogram bin settings are now stored for each column plotted.
- Model Graphs will now start on the previously selected graph (if any).
- The evaluation correlation matrices now have a legend that updates when clicking on a cell.
- Fixed erroneous warning when building certain RSM designs.
- Evaluation graph settings are now saved with the file.
- The design layout will no longer scroll to the top every time it is displayed.
- Fixed crash in logistic regression after editing a discrete level.
- Categorical factors with one or more levels ignored will now show up properly in Graph Columns.
- Fixed display of the level grid when editing a discrete numeric.
- Fixed crash when deleting criteria contours in Graphical Optimization.
- Fixed crash rebuilding a design in which all categorical factors have been changed to discrete numerics.
- Fixed crash when changing a Cube plot to Observed values, then using the Pop-out function.

- Removed KCV model from designs where it was not applicable.
- The graph selection toolbar will now be more compact for smaller resolutions.
- When a toolbar is undocked the close button will now toggle the toolbar off.
- Fixed the coloring of the standard error gradient in the legend.
- Adjusted size and position of graph elements when exported to bitmap or enhanced metafile to better match the on-screen graph.
- Legend position and toggled legend items are now saved with the file.

- Initial macOS release.
- The legend will now dock in the nearest corner.
- Fixed colors in legend when coloring by > 2 categories in the 3d scatterplot.
- Removed Pearson’s chi-squared value from logistic regression fit statistics.
- Fixed display of high order terms in model selection log.
- The curvature term will no longer appear when analyzing a response where an entire factor has been left out of the model.

Logistic Regression

- Responses with binary data will have a
**Logistic Regression**option on the Transform tab. - Chi-squared tests for logistic regression model term significance.
**McFadden**,**Adj. McFadden**, and**Tjur**pseudo-R-squared statistics are available for logistic regression.- Binary responses can be optimized using criteria based on the probability of success or failure.

Graphs

- Model Graphs have been moved to a notebook interface.
- You can create
**multiple graphs**simultaneously in side by side views. - All graphs now have a
**dockable legend**that can be moved independently of the graph. - The legend can also be docked to the right or bottom of the graph via the right-click menu.
- Elements in the legend can be toggled individually via the right-click menu.
- The font size of the legend can be increased or decreased by hovering over it, holding control, and using the mouse scroll wheel.
- A
**histogram**of any column of data can be generated in the Graph Columns node. - You can set a third axis on the Graph Columns scatterplot to make it into a
**3d scatterplot**. - Effects graphs have been moved to a notebook interface and can be compared side by side.
- The Cube plot can now be toggled between observed and predicted values.
- Pairwise comparisons when clicking on a point in Interaction or One Factor plots are now available in a separate toolbox.

Categoric Coding

- Categoric variables can now use
**Helmert contrasts**, which compares each level to the mean of the remaining levels. **Treatment contrasts**are also available, which compares each level to a user-selected control, or reference level.**Ordinal contrasts**no longer need to be numeric. If they are not numeric they are assumed to be evenly-spaced (e.g. “Low”, “Medium”, “High”).- The choice of contrast types for categoric factors is shown in the ANOVA.

Combined Models

**Kowalski-Cornell-Vining (KCV) models**are available as a Model Order choice.- KCV models provide a more efficient alternative to a full crossed model when building.
- KCV models can be selected during the analysis as well.

Bug Fixes

- Fixed graphical corruption that would sometimes appear on contour plots when Banded shading is selected.
- The 3d Surface graph title is now editable.
- Fixed incorrect coloring of symbols in the legend when verification points present.
- Areas of the contour and 3d plot that are invalid due to an impossible reverse transformation (e.g. sqrt of predictions < 0) are no longer colored.
- You can now change the font size in the simulation editor, via the Dialog Control font preference.
- The factors tool now appears in optimization graphs for single factor designs.