• Minor adjustments in anticipation of dplyr 1.0.0

• Use patchwork for grouping multiple plots together
• Use polycor::hetcor to calculate correlations for a mix of numeric and categorical variables
• Updated correlation plot that accommodates a mix of numeric and categorical variables
• Fix for sd estimate in single_prop and compare_prop functions
• Add dimension labels to all tables in Basics > Cross-tabs

• Update action buttons that initiate calculations when one or more relevant inputs are changed. When, for example, a CLT simulation should be updated, a spinning “refresh” icon will be shown
• Allow fractions as input for the Goodness of fit and Probability calculator > Discrete tools

• Summary statistics provided for single_mean, single_prop, compare_means, and compare_props are now consistent
• n_missing were not show correctly for compare_means and compare_props

• Fix for code generation from the probability calculator when the distribution type is set to binomial
• Fix for input restoration from a state file for the probability calculator. For the value or probability inputs two sided values might be restored when only a one-sided input was previously specified

• Documentation updates (i.e., key functions for each tool)
• Improvements in goodness and prob_dics to allow fractions in generated code sent to Report > rmd or Report > R
• Improved checks for variables that show no variation
• Numerous small code changes to support enhanced auto-completion, tooltips, and annotations in shinyAce 0.4.1

• Flexible adjustment of level of jitter in plot.correlation
• Support for variables of type ts

• Various fixes to address (soft) deprecations in dplyr 0.8.0

• Option to pass additional arguments to shiny::runApp when starting radiant such as the port to use. For example, radiant.basics::radiant.basics(“https://github.com/radiant-rstats/docs/raw/gh-pages/examples/demo-dvd-rnd.state.rda”, port = 8080)
• Catch settings where the number of levels in a comparison of means or proportions is the same as the number of rows in the data (e.g., grouping by a unique identifier)
• Show significant stars for Compare means and Compare proportions even when Show additional output is not selected
• ci in summary table compare_means and compare_props should be margin of err (me)
• Option to use Z-test in single_prop

• Load a state file on startup by providing a (relative) file path or a url

## Major changes

• Various changes to the code to accommodate the use of shiny::makeReactiveBinding. The advantage is that the code generated for Report > Rmd and Report > R will no longer have to use r_data to store and access data. This means that code generated and used in the Radiant browser interface will be directly usable without the browser interface as well.

## Major changes

• Upload and download data using the Rstudio file browser. Allows using relative paths to files (e.g., data or images inside an Rstudio project)
• Variable selection in Summary tabs only to simplify Plot interface

## Bug fixes

• Fix for #43 where scatter plot was not shown for a dataset with less than 1,000 rows

## Minor changes

• Format tables with thousand separator
• Added print method for return from correlation

## Minor changes

• Enhanced keyboard shortcuts
• summary.single_prop will not print row numbers
• Added log.normal as an option in the probability calculator
• The correlation plot now has an option to select a sample of data for scatter plots (e.g., 1K, 5K, 10K, or All)

## Minor changes

• Upgraded broom dependency to 0.4.3
• Upgraded dplyr dependency to 0.7.4
• Upgraded tidyr dependency to 0.7.2
• Fixed CI printing error for compare_prop
• Applied styler to code
• Long lines of code generated for Report > Rmd and Report > R will be wrapped to enhance readability

## Minor changes

• correlation defaults to all variables if no value for var is provided
• Renamed methods summary.correlation_ and plot.correlation_ to summary.correlation and plot.correlation
• Added tab argument to goodness and cross_tabs so a table object can be passed directly
• Scatter plots in Correlation > Plot are now based on 1,000 data points by default. Use Report > Rmd or Report > R to adjust (e.g., plot(result, n = -1))

## Bug fixes

• Fix for level ordering in goodness-of-fit expected-values plot
• Code clean-up and various minor fixes and improvements

## Major changes

• Show dataset name in output if dataframe passed directly to analysis function
• Scatter plots in Basics > Correlation > Plot now based on 1,000 data points by default. Add n = -1 to use all data points
• As an alternative to using the Estimate button to run a model you can now also use CTRL-enter or CMD-enter
• Use ALT-enter to put code into Report > Rmd or Report > R
• Documentation added on how to customize plots

## Bug fixes

• Fixed correlation dropdown. Correlations did not change when method was changed (thanks @Fiordmaster)
• Improved formatting for small negative values in Basics > Correlation
• Convert numeric bounds to integer in Basics > Probability calculator > Binomial to avoid warnings

## Deprecated

• Use of *_each is deprecated