Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Potential improvements for v2 #366

Open
13 of 26 tasks
rudeboybert opened this issue Jun 18, 2020 · 1 comment · Fixed by #418
Open
13 of 26 tasks

Potential improvements for v2 #366

rudeboybert opened this issue Jun 18, 2020 · 1 comment · Fixed by #418
Assignees
Labels
v2 Second edition

Comments

@rudeboybert
Copy link
Member

rudeboybert commented Jun 18, 2020

@avaldivi6

  • Erase Bowl from sections
  • Footnote for almonds
  • Make sure activity can be replicated by instructors (e.g. went to chemistry department to borrow scales). Be clear this refers to instructors (e.g, "If you are an instructor...")

General

  • Add Arturo's bio and photo to Preface.
  • Think about moving regression chapters all to the end Keeping where they are to ensure some exploratory regression is done before inferential.
  • Currently in v1 CLT is a subsection of Section 7.5. For v2, consider moving it to its own section to make CLT more prominent. Can do this by rebasing Switched section ordering and added to CLT #326 to eventual v2 branch that will get created.
  • Refactor Section 7.3 to break down reading into more bite-sized pieces. Rebase Refactoring Ch7 sampling #324
  • Per Katie’s suggestion, add discussion on R^2 and R^2-adjusted in Subsection 6.3.1 on Model selection. In particular somewhere after "visual model selection" we do. Can use moderndive::get_regression_summaries() wrapper to broom::augment() to get at these values easily. Can reuse fc4621d. Also per Will’s suggestion, add visualizations illustrating the breakdown of variances that go into R^2.
  • Add recap/key concepts to each chapter AND/OR define as learning goals at the outset of each chapter
  • In Ch7 Conclusion, consider adding a section on random sampling vs assignment?
  • Add exercises at the end of each chapter
  • Extend {infer} to more advanced use cases using fit() function
  • Use base-pipe |> instead of %>%
  • Remove any outstanding HTML comments. <!-- --> (They can be really dangerous if not closed!)
  • Address the warning message explicitly for group_by() in text and fix index.Rmd to remove options(dplyr.summarise.inform = FALSE)
  • Add relocate() to end of Chapter 3
  • Update preface with updates to 2nd edition
  • Add almonds data to moderndive package
  • Ask Kelly for an updated foreword
  • Create branch and link to first edition. 2nd edition stays at moderndive.com
  • Change font size of PDF to one point smaller
  • Add diagrams for sampling and bootstrapping

nycflights23

  • Use the anyflights package to create an nycflights23 package to replace nycflights13 data.
  • Update the early_january_weather and alaska_flights data frames in moderndive package to use '23 data
  • Update Learning Check solutions in Chapters 1-4 for '23 data
  • Explain that nycflights23 is an updated version of nycflights13 using the anyflights package
@rudeboybert rudeboybert added the v2 Second edition label Jun 18, 2020
@rudeboybert rudeboybert self-assigned this Jun 18, 2020
@rudeboybert rudeboybert changed the title Add subsection on random sampling vs assignment Potential improvements for v2 Jul 1, 2020
@rudeboybert rudeboybert linked a pull request Jan 30, 2021 that will close this issue
@wmorgan485
Copy link

In Section 9.6.1, the discussion about the warning message to check that conditions have been met for the theoretical method {infer} might be rewritten for clarity. The warning message is generated by a visualize() command with method = "both". However, the discussion about the warning message follows a get_p_value() command using a simulation-based null distribution (null_distribution_movies_t), where this warning doesn't apply (right?). It might be clearer to discuss the warning message before getting the p-value. Or get_p_value might be run instead with a null distribution generated using assume(distribution = "t"), where the warning message would then apply.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
v2 Second edition
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants