Wizard Pro Changelog

New in version 1.7.5

May 20th, 2015
  • Fix a crash when creating numeric columns via the Refresh button
  • Faster importing of large SAS files

New in version 1.7.4 (May 13th, 2015)

  • Fix a display issue in the Summary view when unchecking filters
  • Fix a crash in the Predict view when a model has either no outcome variables or no explanatory variables
  • Fix "Can't connect" error when attempting to connect to a database using a password containing special characters
  • Support for connecting to databases over IPv6
  • Support for schemas in PostgreSQL
  • Support for character types in PostgreSQL
  • Improved support for importing CSV files with improperly quoted values
  • Improved support for importing variable labels and frequency weights from SPSS files
  • Increased maximum length of exported SPSS variable labels from 120 characters to 256 characters

New in version 1.7.2 (April 22nd, 2015)

  • Import and export case weights (a.k.a. frequency weights, a.k.a. "Treat as Row Counts") from SPSS files
  • Import missing-value definitions from SPSS files
  • Improved support for reading compressed SAS files
  • New "between" operator for defining missing values

New in version 1.7.1 (April 15th, 2015)

  • Fix minor issues in the Numbers and SAV importers
  • Fix an issue when attempting to import a custom-delimited file without a document open
  • Fix an issue where some of the Summary exporters did nothing

New in version 1.7.0 (March 31st, 2015)

  • 1-click Data Refresh: Suppose you've imported and cleaned your data, perhaps built a few models -- and then your data changes. Now, thanks to the new "Refresh" button in the toolbar, you can instantly update all of your analyses using fresh data from the original source. Customize how columns are matched up with a convenient popover, and feel free to move or rename the source data file on your computer -- Wizard will automatically keep an eye on it. Command-R to refresh the data, Command-E to configure the link.
  • Revamped menu system: Wizard has a new modular architecture that means you'll only see menus relevant to what you're doing -- that is, Raw Data, Pivot, Summary, Model, and Predict each have their own menu now. Most of the menus are more concise, so you can find what you're looking for faster.
  • JSON support: by popular request, Wizard 1.7 can import JavaScript (JSON) data files. Make sure your data is encoded as an array of objects and Wizard will do the rest. Export any table or result as JSON, too.

New in version 1.6.8 (March 12th, 2015)

  • Fix an issue with the application failing to launch after several weeks
  • Custom-interval partitions now accept duration strings (e.g. "1d 3h")
  • The CSV importer now accepts timestamps in UTC format
  • Columns imported from Numbers '13 documents were sometimes missing or out of order
  • Added support for importing values from multiple-choice cells in Numbers '09 and Numbers '13 documents
  • Added support for more character encodings when importing SAS and SPSS files
  • Exported SAV files now work better with SPSS
  • Added support for importing large (2GB+) SAS files

New in version 1.6.7 (February 27th, 2015)

  • Fix a crash when exporting a Pivot table containing missing values to Excel
  • Fix a crash when copying a Stacked table
  • Performance improvements when importing large SPSS files
  • Improved support for SPSS command files
  • Improved support for dates, times, value labels, and character encodings in SAS files

New in version 1.6.6 (February 14th, 2015)

  • Fix a crash in the SPSS importer

New in version 1.6.5 (January 31st, 2015)

  • Improved support for non-ASCII characters in sas7bdat files

New in version 1.6.4 (January 22nd, 2015)

  • Fix a crash when viewing box-plots in the Summary view

New in version 1.6.3 (January 15th, 2015)

  • Performance and stability improvements on Yosemite

New in version 1.6.2 (January 9th, 2015)

  • New ability to export "The Bottom Line" (image, test statistic, p-value, etc.)
  • New ability to select multiple Pivot functions at once
  • Use the standard definition of median in case of ties (average of 2 tied values)
  • Improved support for importing number-format information from Excel and Numbers documents
  • Improved support for sas7bdat files
  • Fix bug when attempting to overwrite an existing document
  • Fix a bug with binary response models exported as XLS
  • Minor interface improvements

New in version 1.6.1 (January 3rd, 2015)

  • Fix a number of minor interface bugs
  • Improved support for sas7bdat files

New in version 1.6.0 (December 9th, 2014)

  • Duration data: Support for importing and formatting time durations as HH:MM:SS or other formats. Great for analyzing e.g. race results.
  • Combine Pivot functions - You can now add, subtract, multiply, and divide columns in the Pivot table for more insightful reports.
  • Organize filter sets: If you spend a lot of time with Filters, the new version will let you name and organize an unlimited number of filter sets easily. That way you can switch between subsets of the data without having to reselect all the filter conditions individually.
  • Indicator Variables with "OR" conditions: In previous versions, Indicator Variables were equal to 1 when all of the conditions are true. In this version, you have a new option to set the value to 1 when any condition is true.
  • Reorder categories: If you don't like the default ordering of categories in a particular column, you can now drag and drop to rearrange.
  • This release also includes a number bug fixes and stability improvements.

New in version 1.5.7 (December 3rd, 2014)

  • Fix a bug in the way missing values were handled in two-way ANOVA tests

New in version 1.5.6 (November 25th, 2014)

  • Support DATETIME columns when importing SQLite files
  • The .db extension is now recognized as SQLite
  • Fix a few minor interface bugs
  • Fix a few obscure crashes

New in version 1.5.5 (November 12th, 2014)

  • Fix several crashes:
  • Viewing confidence intervals of the mean under 10.7 and 10.8 caused a crash
  • Non-ASCII text in SPSS files sometimes caused a crash
  • Creating a custom covariate partition in the Summary view caused a crash
  • Very long text values sometimes caused a crash
  • Proportional Hazards models with a specified cause of failure caused a crash
  • New features for Contingency Table Analysis:
  • McNemar Test (2 repeated binary measures)
  • Cochran's Q (3 or more repeated binary measures)
  • Stuart-Maxwell Test (2 repeated category measures)
  • "Show Estimation Command" now works in the Summary view, too. (Generates commands for SPSS, SAS, Stata, and R)
  • Pivot tables have improved support for hierarchical data
  • Column > Subtract now works on date columns
  • Summary view supports cross-column comparisons of category and survival-time data
  • Proportional Hazards models are much faster

New in version 1.5.4 (November 6th, 2014)

  • Survival curves: dotted lines for censored values, and more grid lines for large graphs
  • Accept percentage values in CSV files
  • Support for importing DBF (dBase) files

New in version 1.5.3 (October 31st, 2014)

  • Support for Numbers 3.5 documents
  • New repeated-measures tests: Wilcoxon signed-rank test for 2 numeric columns, Friedman test for 3 or more numeric columns
  • Improved support for SAS7BDAT files created with Stat/Transfer
  • Many speed improvements throughout the program
  • Fix a freeze when customizing filters
  • Some date/time values in CSV files were ignored
  • Preserve date/time semantics when creating a new table from a Pivot table
  • Fixed-effect models exported as XLS didn't work properly

New in version 1.5.2 (October 17th, 2014)

  • A new "Treat as Survival Times" option, which lets you produce survival (Nelson-Aalen) curves, view confidence bands, and perform log-rank tests. Survival analysis is perfect for analyzing failure, relapse, and mortality data, as well as other kinds of event data.
  • Paired t-tests and repeated measures ANOVA: To analyze "before and after" data, just selecting multiple columns in the Summary view and checking the box labeled "Repeated Measures"
  • Text partitions: Now you can group non-category text data into groups, e.g. A-G, H-M, and N-Z.
  • Export image data: The data behind all the graphics in the Summary view can now be exported as CSV or XLS.
  • Zoom to filtered values: There's a new magnifying glass button in the top-right corner of the Data Filters pane that lets you zoom all the graphics to the filtered values.
  • Improved prediction intervals: The Predict view will now draw prediction intervals in the response curve, in addition to displaying the numeric values.
  • Interaction terms: Models can now include separate interaction terms between two explanatory variables. For continuous variables, this is the product of the two terms; for category variables, this is an extra set of dummy variables representing all possible combinations of the two terms. Interaction terms will "just work" in the Predict view and in export XLS models.
  • Reorder outcome categories: If your outcome categories aren't ordered properly, now you can just drag and drop to rearrange them. This should make Ordered Probit models more immediately useful without having to create ad-hoc columns.

New in version 1.5.1 (October 9th, 2014)

  • Keep popovers open as you switch windows.
  • New option to hide charts in the Summary view (View > Hide Summary Charts)
  • Improvements to the SAS command importer
  • Fix a crash when using a date/time column as a covariate
  • Fix a crash when importing values of infinity or negative infinity

New in version 1.5.0 (October 1st, 2014)

  • A new "Treat as Survival Times" option, which lets you produce survival (Nelson-Aalen) curves, view confidence bands, and perform log-rank tests. Survival analysis is perfect for analyzing failure, relapse, and mortality data, as well as other kinds of event data.
  • Paired t-tests and repeated measures ANOVA: To analyze "before and after" data, just selecting multiple columns in the Summary view and checking the box labeled "Repeated Measures"
  • Text partitions: Now you can group non-category text data into groups, e.g. A-G, H-M, and N-Z.
  • Export image data: The data behind all the graphics in the Summary view can now be exported as CSV or XLS.
  • Zoom to filtered values: There's a new magnifying glass button in the top-right corner of the Data Filters pane that lets you zoom all the graphics to the filtered values.
  • Improved prediction intervals: The Predict view will now draw prediction intervals in the response curve, in addition to displaying the numeric values.
  • Interaction terms: Models can now include separate interaction terms between two explanatory variables. For continuous variables, this is the product of the two terms; for category variables, this is an extra set of dummy variables representing all possible combinations of the two terms. Interaction terms will "just work" in the Predict view and in export XLS models.
  • Reorder outcome categories: If your outcome categories aren't ordered properly, now you can just drag and drop to rearrange them. This should make Ordered Probit models more immediately useful without having to create ad-hoc columns.

New in version 1.4.15 (September 4th, 2014)

  • Improve handling of formulas containing errors when importing XLSX files.

New in version 1.4.14 (September 1st, 2014)

  • Fix incorrect sorting of non-ASCII text
  • Fix a bug in the display of confidence intervals for odds ratios in models

New in version 1.4.13 (August 27th, 2014)

  • NEW select 2 or more covariates in the Summary view by Command-clicking
  • NEW test for interaction effects with two-way ANOVA (see Help file for details)
  • NEW test 2 or more model coefficients for equality (Wald test)
  • Fix a crash when exporting Pivot tables that use the "Count Distinct Values" function
  • Fix a rare crash when closing a document

New in version 1.4.12 (August 21st, 2014)

  • New option to display prediction intervals for multivariate models.

New in version 1.4.11 (August 16th, 2014)

  • NEW: Select a subset of a MySQL / PostgreSQL database using the new graphical query builder. (Or enter your own SQL statements.)
  • NEW: View and optionally exclude the constant term from models
  • NEW: Perform joint significance tests by selecting (Command-clicking) two or more coefficients in the Model view
  • NEW: Control the number of displayed decimal places for predicted values in Preferences
  • Bug fixes:
  • Fix a crash when connecting to a PostgreSQL server under Lion and Mountain Lion
  • Fix a bug where linear regressions couldn't be weighted
  • Fix a bug in the display of R² values for linear models
  • Fix a bug in linear models exported as XLS

New in version 1.4.8 (July 26th, 2014)

  • More convenient links for sending feedback to the developer

New in version 1.4.7 (July 12th, 2014)

  • Fix a few glitches in the Predict tab

New in version 1.4.5 (June 27th, 2014)

  • Fix a crash when opening Wizard Pro under Lion and Mountain Lion
  • Improvements to the SAV data exporter

New in version 1.4.3 (June 18th, 2014)

  • Fix an issue importing dates from CSV files
  • Fix a crash when exporting XLS data
  • Improve Excel compatibility of exported XLS data
  • Fix an issue when attempting to save after sorting by an aggregate value and then deleting a Pivot
  • Improved handling of non-ASCII text in exported SAV files (Pro only)
  • Properly export category labels to SAV files with text columns (Pro only)

New in version 1.4.2 (June 10th, 2014)

  • Bug fixes and stability improvements.

New in version 1.4.1 (May 6th, 2014)

  • Bug fixes and stability improvements.

New in version 1.4.0 (April 29th, 2014)

  • FEATURES:
  • Database support: import from SQLite, MS Access, MySQL, and PostgreSQL
  • Numbers '13 support
  • Timestamp / time-of-day support
  • Customizable data partitions. Separate numeric data into groups of equal size, intervals of equal width, or user-defined intervals
  • Best-fit lines on scatterplots, and reference lines on Q-Q plots
  • Visualize critical values and p-values with the new Bottom Line popover (see screenshots)
  • New "Copy Predicted Values" menu item applies a predictive model to the full data set
  • CHANGES:
  • Histograms are much sharper now
  • More tick marks and labels on all the graphics
  • Full access to the Column tools from inside the Raw Data view
  • New preference option: choose a "Friendly" or "Neutral" font for The Bottom Line
  • Filtered and frequency-weighted models run much faster than before
  • Excel output is much prettier -- with bold, italics, and indentation for clarity.
  • NICE TOUCHES:
  • Exporting data now has a progress bar and a Cancel button
  • Support for up to 6 data filters
  • Support for up to 5 pivot columns

New in version 1.3.28 (April 24th, 2014)

  • Import Boolean (true/false) values from XLS files
  • Fix a display glitch in the Pivot table when applying filters
  • Fix an #N/A! error in exported XLS models
  • Fix an issue exporting missing category values to DTA files (Pro only)

New in version 1.3.27 (February 15th, 2014)

  • Fix a few #VALUE! errors in exported XLS models

New in version 1.3.26 (February 10th, 2014)

  • Improved support for reading SAS7BDAT files

New in version 1.3.25 (February 3rd, 2014)

  • Improved support for reading SPSS command files

New in version 1.3.24 (January 23rd, 2014)

  • Fix a discrepancy in the displayed p-values in models with a small number of observations

New in version 1.3.23 (January 18th, 2014)

  • Bug fix: Columns imported from CSV files were sometimes out of order
  • Bug fix: Blank header cells in XLSX documents caused some columns not to be imported
  • Fix a few display glitches in the Raw Data view

New in version 1.3.22 (January 6th, 2014)

  • Fix a crash when importing XLS files with more than 32,000 rows
  • Fix an issue when importing Numbers '09 documents with many blank footer cells

New in version 1.3.21 (December 9th, 2013)

  • Fix an unusual crash in the Pivot view
  • Dates imported from CSV files were sometimes off by one day for users in Europe, Asia, and Australia

New in version 1.3.19 (December 2nd, 2013)

  • Improve compatibility with files exported from Numbers '13. (Note that the Numbers '13 file format is not yet supported.)

New in version 1.3.18 (December 2nd, 2013)

  • Fix uncommon freezing issues in the Summary view

New in version 1.3.17 (December 2nd, 2013)

  • Fix an issue importing CSV files that start with a byte-order mark (BOM)
  • Improve error reporting for CSV files that cannot be imported

New in version 1.3.16 (December 2nd, 2013)

  • Fix an issue when importing variable names in XLSX files containing rich-text formatting

New in version 1.3.15 (December 2nd, 2013)

  • Wrap very long chart titles when viewing pie charts
  • Fix an issue with CSV exporting of columns with quotation marks in their names

New in version 1.3.14 (December 2nd, 2013)

  • Fix an issue with importing columns with non-ASCII character names from Numbers documents

New in version 1.3.13 (December 2nd, 2013)

  • Fix a few issues with date columns
  • New rows sometimes appeared in the middle of a data set rather than at the end

New in version 1.3.12 (December 2nd, 2013)

  • Fix importing of true/false fields in XLSX files

New in version 1.3.11 (December 2nd, 2013)

  • Fix an off-by-4-years issue when importing certain XLSX files
  • Fix importing of TSV and CSV files with comment lines that start with the "#" character

New in version 1.3.10 (September 10th, 2013)

  • NEW Export Pivot tables as CSV or XLS
  • Fix a crash when importing certain XLS files
  • Import time-of-day fields from Excel as a number from 0 to 24
  • (Pro only) Fix issues with DTA export

New in version 1.3.9 (August 28th, 2013)

  • Fix interpretation of system-missing values in .sav files
  • Fix an intermittent crash in the Summary view
  • Fix inaccurate tooltips

New in version 1.3.8 (July 24th, 2013)

  • Improved support for importing non-ASCII characters in SPSS and SAS binary files. Bon appétit!

New in version 1.3.7 (July 9th, 2013)

  • Fix a bug when importing from .sas7bdat files
  • Fix a crash when using model weights with multiple outcome variables
  • Fix a crash when exporting models as XLS with multiple outcome variables

New in version 1.3.6 (June 28th, 2013)

  • Support for batch-importing multiple files of the same type
  • Pro only: Support for importing .dta files created with Stata 13
  • New: Count Unique Values function in the Pivot view
  • Fix minor issues with importing from XLS files

New in version 1.3.5 (May 30th, 2013)

  • New "Delete Column" menu item when control-clicking a column header in the Raw Data view
  • Fix various issues with Recode variables
  • Adjust standard errors for small sample sizes (unweighted linear models only)

New in version 1.3.4 (May 22nd, 2013)

  • Fix a display bug in the Summary view with values containing newlines
  • Fix a crash with models containing both date and non-date explanatory variables
  • Fix a crash when removing a variable from the Model view using the context menu
  • Fix a crash involving text columns joined from another table
  • Fix a crash when deleting a column that is being used to perform a table join

New in version 1.3.3 (May 17th, 2013)

  • New menu item: Covariate > Deselect will deselect the active covariate in the Summary view. (You can still deselect by Command-clicking.)
  • New behavior: Deleting a column from the Summary view will immediately select the next column in the table. Ideal for rapidly inspecting / deleting a large number of columns.

New in version 1.3.2 (May 10th, 2013)

  • Preserve filter selections when switching between tables
  • Correctly parse numbers surrounded by spaces in CSV files
  • Fix a bug where a blank header cell in an Excel spreadsheet caused subsequent columns not to be imported
  • Fix some issues with PDF export of model images
  • Fix a crash when stacking tables with indicator variables

New in version 1.3.1 (May 3rd, 2013)

  • Fix a bug where date columns were not always recognized when importing XLSX
  • Fix a crash in the Raw Data view

New in version 1.3.0 (April 22nd, 2013)

  • NEW! Features for working with SAS — the popular statistical package — are now available in Wizard Pro, alongside the existing features for working with SPSS and Stata. Import SAS binary data files (.sas7bdat) and optional catalog files (for value labels), or import plain-text data that is described by .sas command files. In the Model view, Wizard's command-generator now includes a "SAS" option — perfect for reproducing regressions in SAS!
  • Importing newer Excel files (the XLSX file format). Wizard can now read in XLSX with ease. So if you see any old reviews bemoaning the lack of XLSX support, please note that as of today they are 100% obsolete. Being able to import XLSX is ideal for people who work with large data sets, as the older XLS format cannot store more than 65,000 rows.
  • To make up for several months of missing XLSX support, I went the extra mile with Wizard 1.3 and implemented the ability to import Numbers spreadsheets, that is, files ending in ".numbers". If you choose File > Import Numbers Document, Wizard will scan your spreadsheet and suck in all the data tables that it can find. So if you're a Numbers fan like me, now you can import your data into Wizard without having to export it as XLS first.
  • Fix a crash when zero observations are included in the Model view
  • Fix a bug when importing multiple sheets in XLS documents
  • Fix a bug where Q-Q plots were not properly exported as PDF

New in version 1.2.4 (March 28th, 2013)

  • New feature: pretty ROC curves for evaluating the performance of binary-outcome models. Just click "ROC curve" in the Model view. More green = better model
  • Improved blank-cell detection when importing Excel spreadsheets
  • Fix crash when joining text columns to foreign tables
  • Fix crash after canceling the creation of a new indicator variable

New in version 1.2.3 (March 15th, 2013)

  • Set the numeric format directly from the Raw Data view (control-click the column header)
  • Use scientific formatting for very small statistics (e.g. confidence intervals)
  • Fix a bug when importing categories from RData files
  • Fix XLS export for binary-response models
  • Fix a bug relating to long text fields
  • Fix a bug preventing an existing document being "Saved As" itself
  • Fix a bug preventing a document from being saved after deleting a model
  • Minor fixes to the Model interface

New in version 1.2.2 (March 7th, 2013)

  • Excel import: Improve blank-cell detection.

New in version 1.2.1 (February 13th, 2013)

  • Support for scientific formatting style
  • Export the dispersion parameter of Negative Binomial models
  • Fix a crash when importing older XLS files
  • Fix grayed-out "Join to Table" menu item bug

New in version 1.2.0 (February 1st, 2013)

  • DATE SUPPORT - THE #1 FEATURE REQUEST:
  • Enter dates manually or import them from any supported file format
  • Compose dates from one or more date component columns (e.g. "year" and "month")
  • View number of records by year, quarter, month, week, or day
  • Pivot numeric data by year, quarter, month, week, or day
  • Compute day of week, day of year, ISO week-numbering year, and more
  • Compute durations: years, months, weeks, or days between two date columns
  • EXCEL EXPORT - THE FEATURE YOU DIDN'T KNOW YOU NEEDED:
  • Export raw data as XLS
  • Export summary, correlation, and coefficient tables as XLS
  • Export models as interactive predictive spreadsheets. This makes a version of the Predict interface available to anyone running Microsoft Excel. See it to believe it!
  • NEW TESTS AND MODELS:
  • Mann-Whitney and Kruskal-Wallis (median test)
  • 2-sample and N-sample Kolmogorov-Smirnov (distribution test)
  • Negative Binomial model (for overdispersed count data)
  • Cox Proportional Hazards model (for failure-time data) -- includes options for stratification, censoring, and multiple causes of failure
  • MISCELLANEOUS FEATURES AND BUG FIXES:
  • Numeric data is now stored in double-precision
  • Support for importing text files with a custom delimiter
  • Address a mysterious crash
  • Many minor tweaks

New in version 1.1.2 (December 10th, 2012)

  • NEW support for manual data entry
  • NEW full-screen mode-- ideal for presentations (Lion and Mountain Lion only)
  • New behavior: double-click a slice in the pie chart to edit its color
  • Fix a crash when opening a .tsv file
  • Fix a bug when exporting correlation tables with category variables as CSV
  • Fix a bug when exporting model coefficients as CSV
  • (Pro) Fix an error when importing certain .por files

New in version 1.1.1 (November 27th, 2012)

  • Fix critical bug where saved multivariate models would not open on Mountain Lion
  • Fix bug in tutorial

New in version 1.1.0 (November 8th, 2012)

  • NEW multi-way pivot tables with sums, averages, variances, and percentiles -- great for summarizing data and squashing large data sets down into a more manageable size
  • Many new formatting options: set the number decimal digits displayed, change the capitalization of text, and choose custom category colors to suit your preferences
  • Logistic and count models can optionally display results as odds ratios -- perfect for researchers in health sciences
  • Many performance improvements, bug fixes, and interface tweaks

New in version 1.0.1 (September 25th, 2012)

  • NEW interactive tutorial that shows you how to analyze a fictitious spreadsheet of fish caught by three fishermen (Wynken, Blynken, and Nod).