BlueSky Statistics is easy-to-use software for data science. Behind the scenes it does its work using the powerful R language. You can read a full review here, and download the software free from the BlueSky Statistics website.
The BlueSky Statistics User Guide, Third Edition covers all the topics of the previous edition (online below) and the following new features:
- Using the Table of Contents to skip around the Output window.
- Freezing table labels as contents scroll beneath them.
- Adding variable labels to all tabular results.
- Renaming output tabs.
- Using the Datagrid’s audit trail.
- Rerunning an entire workflow with a single click.
- Automating the replacement of datasets when rerunning a workflow.
- Using project files to save or load many files simultaneously.
- Cleaning Excel files to remove rows or columns and create multi-row variable names.
- Automating the extraction of repeating patterns of variables.
- Creating cumulative statistics variables.
- Separating delimited values stored in a character variable.
- Converting characters to dates using expanded and simplified formats.
- Reading date/time variables; adding times to dates.
- Filling missing values upward or downward (e.g., last observation carried forward).
- Creating scatterplot matrix displays.
- Creating dual-axis plots.
- Plotting dose-response curves.
- Using new main effects and interaction plots.
The BlueSky Statistics User Guide, Third Edition, is available only in printed form here. However, the previous edition is online below. Both versions explain how to use the software and assume a minimal background in statistics, artificial intelligence, or machine learning.
When using the previous edition online, the search icon is the magnifying glass in the upper left corner. Click it again to make it disappear. The table of contents and the 1,300-entry index are all live links directly to each topic. The first 19 pages of the book are the preface, table of contents, etc., use Roman numerals and are not included in the page count. So, if you tell it to go to page 100, you will end up on page 81. The other navigation methods are preferred.
The PDF is not downloadable, as the advertising on this page helps support the considerable effort required to maintain this rapidly expanding software.
Errata to the Online Version (all corrected in the third edition)
- While the back cover of the book says BlueSky version 10 is open-source, that is no longer the case.
- A previous version had all data wrangling on a “Data” menu. More recent versions have them split between “Datasets” and “Variables” menus. I missed changing that in a few places.
- Several step-by-step examples end with “then click OK to run it.” That has been replaced with clicking a triangular “play” button in version 10.
- The item “Variables> Concatenate” is covered in the book’s “Variables> Compute” section.
- The triple-bar (“hamburger”) menu is being reverted to the classic name of “File.”