[REVIEW]: sleev: An R Package for Semiparametric Likelihood Estimation with Errors in Variables

editorialbot commented 1 month ago

Submitting author: !--author-handle-->@JiangmeiRubyXiong@jbytecode<!--end-editor-- Reviewers: @alemermartinez, @aalfons Archive: Pending

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/2dc012ed16ca93ac2f265dc6725f1466"><img src="https://joss.theoj.org/papers/2dc012ed16ca93ac2f265dc6725f1466/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/2dc012ed16ca93ac2f265dc6725f1466/status.svg)](https://joss.theoj.org/papers/2dc012ed16ca93ac2f265dc6725f1466)

Reviewers and authors:

Please avoid lengthy details of difficulties in the review thread. Instead, please create a new issue in the target repository and link to those issues (especially acceptance-blockers) by leaving comments in the review thread below. (For completists: if the target issue tracker is also on GitHub, linking the review thread in the issue or vice versa will create corresponding breadcrumb trails in the link target.)

Reviewer instructions & questions

@alemermartinez & @aalfons, your review will be checklist based. Each of you will have a separate checklist that you should update when carrying out your review. First of all you need to run this command in a separate comment to create the checklist:

@editorialbot generate my checklist

The reviewer guidelines are available here: https://joss.readthedocs.io/en/latest/reviewer_guidelines.html. Any questions/concerns please let @jbytecode know.

✨ Please start on your review when you are able, and be sure to complete your review in the next six weeks, at the very latest ✨

Checklists

📝 Checklist for @aalfons

📝 Checklist for @alemermartinez

editorialbot commented 1 month ago

Hello humans, I'm @editorialbot, a robot that can help you with some common editorial tasks.

For a list of things I can do to help you, just type:

@editorialbot commands

For example, to regenerate the paper pdf after making changes in the paper's md or bib files, type:

@editorialbot generate pdf

editorialbot commented 1 month ago

Reference check summary (note 'MISSING' DOIs are suggestions that need verification):

✅ OK DOIs

- 10.1002/sim.8799 is OK
- 10.1111/biom.13512 is OK
- 10.1017/CBO9780511618994 is OK
- 10.1080/01621459.2017.1295864 is OK
- 10.2307/2669386 is OK
- 10.1214/20-aoas1343 is OK

🟡 SKIP DOIs

- No DOI given, and none found for title: An empirical study for impacts of measurement erro...

❌ MISSING DOIs

- None

❌ INVALID DOIs

- None

editorialbot commented 1 month ago

Software report:

github.com/AlDanial/cloc v 1.90  T=0.03 s (1498.9 files/s, 242374.7 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
R                               30            524           1164           2131
C++                              5            252            360           1379
Markdown                         2             80              0            375
TeX                              1              0              0             71
C/C++ Header                     1             19             67             22
YAML                             1              1              4             19
-------------------------------------------------------------------------------
SUM:                            40            876           1595           3997
-------------------------------------------------------------------------------

Commit count by author:

   112  Joey Sherrill
    26  Sarah Lotspeich
     9  JiangmeiRubyXiong
     5  Sarah
     3  Ran Tao
     3  Sarah Lotspeich (She/Her)
     2  Ruby XIONG
     2  dragontaoran
     1  Shawn Garbett

editorialbot commented 1 month ago

Paper file info:

📄 Wordcount for paper.md is 2168

✅ The paper includes a Statement of need section

editorialbot commented 1 month ago

License info:

🟡 License found: GNU General Public License v3.0 (Check here for OSI approval)

editorialbot commented 1 month ago

:point_right::page_facing_up: Download article proof :page_facing_up: View article proof on GitHub :page_facing_up: :point_left:

jbytecode commented 1 month ago

@editorialbot remind @aalfons in four weeks

@aalfons - You will get reminded by our bot automatically. As you emphasized in pre-review issue, we expect your report in 8-10 weeks. Thank you in advance

editorialbot commented 1 month ago

Reminder set for @aalfons in four weeks

jbytecode commented 1 month ago

Dear @alemermartinez & @aalfons, you can start your review by generating your tasklist, please just type

@editorialbot generate my checklist

Thank you in advance

jbytecode commented 1 month ago

@editorialbot remind @alemermartinez in 15 days

editorialbot commented 1 month ago

Reminder set for @alemermartinez in 15 days

aalfons commented 1 month ago

Review checklist for @aalfons

Conflict of interest

[ ] I confirm that I have read the JOSS conflict of interest (COI) policy and that: I have no COIs with reviewing this work or that any perceived COIs have been waived by JOSS for the purpose of this review.

Code of Conduct

[ ] I confirm that I read and will adhere to the JOSS code of conduct.

General checks

[ ] Repository: Is the source code for this software available at the https://github.com/dragontaoran/sleev?
[ ] License: Does the repository contain a plain-text LICENSE or COPYING file with the contents of an OSI approved software license?
[ ] Contribution and authorship: Has the submitting author (@JiangmeiRubyXiong) made major contributions to the software? Does the full list of paper authors seem appropriate and complete?
[ ] Substantial scholarly effort: Does this submission meet the scope eligibility described in the JOSS guidelines
[ ] Data sharing: If the paper contains original data, data are accessible to the reviewers. If the paper contains no original data, please check this item.
[ ] Reproducibility: If the paper contains original results, results are entirely reproducible by reviewers. If the paper contains no original results, please check this item.
[ ] Human and animal research: If the paper contains original data research on humans subjects or animals, does it comply with JOSS's human participants research policy and/or animal research policy? If the paper contains no such data, please check this item.

Functionality

[ ] Installation: Does installation proceed as outlined in the documentation?
[ ] Functionality: Have the functional claims of the software been confirmed?
[ ] Performance: If there are any performance claims of the software, have they been confirmed? (If there are no claims, please check off this item.)

Documentation

[ ] A statement of need: Do the authors clearly state what problems the software is designed to solve and who the target audience is?
[ ] Installation instructions: Is there a clearly-stated list of dependencies? Ideally these should be handled with an automated package management solution.
[ ] Example usage: Do the authors include examples of how to use the software (ideally to solve real-world analysis problems).
[ ] Functionality documentation: Is the core functionality of the software documented to a satisfactory level (e.g., API method documentation)?
[ ] Automated tests: Are there automated tests or manual steps described so that the functionality of the software can be verified?
[ ] Community guidelines: Are there clear guidelines for third parties wishing to 1) Contribute to the software 2) Report issues or problems with the software 3) Seek support

Software paper

[ ] Summary: Has a clear description of the high-level functionality and purpose of the software for a diverse, non-specialist audience been provided?
[ ] A statement of need: Does the paper have a section titled 'Statement of need' that clearly states what problems the software is designed to solve, who the target audience is, and its relation to other work?
[ ] State of the field: Do the authors describe how this software compares to other commonly-used packages?
[ ] Quality of writing: Is the paper well written (i.e., it does not require editing for structure, language, or writing quality)?
[ ] References: Is the list of references complete, and is everything cited appropriately that should be cited (e.g., papers, datasets, software)? Do references in the text use the proper citation syntax?

editorialbot commented 3 weeks ago

:wave: @alemermartinez, please update us on how your review is going (this is an automated reminder).

alemermartinez commented 3 weeks ago

Review checklist for @alemermartinez

Conflict of interest

[x] I confirm that I have read the JOSS conflict of interest (COI) policy and that: I have no COIs with reviewing this work or that any perceived COIs have been waived by JOSS for the purpose of this review.

Code of Conduct

[x] I confirm that I read and will adhere to the JOSS code of conduct.

General checks

[x] Repository: Is the source code for this software available at the https://github.com/dragontaoran/sleev?
[x] License: Does the repository contain a plain-text LICENSE or COPYING file with the contents of an OSI approved software license?
[x] Contribution and authorship: Has the submitting author (@JiangmeiRubyXiong) made major contributions to the software? Does the full list of paper authors seem appropriate and complete?
[ ] Substantial scholarly effort: Does this submission meet the scope eligibility described in the JOSS guidelines
[x] Data sharing: If the paper contains original data, data are accessible to the reviewers. If the paper contains no original data, please check this item.
[x] Reproducibility: If the paper contains original results, results are entirely reproducible by reviewers. If the paper contains no original results, please check this item.
[x] Human and animal research: If the paper contains original data research on humans subjects or animals, does it comply with JOSS's human participants research policy and/or animal research policy? If the paper contains no such data, please check this item.

Functionality

[x] Installation: Does installation proceed as outlined in the documentation?
[x] Functionality: Have the functional claims of the software been confirmed?
[x] Performance: If there are any performance claims of the software, have they been confirmed? (If there are no claims, please check off this item.)

Documentation

[x] A statement of need: Do the authors clearly state what problems the software is designed to solve and who the target audience is?
[ ] Installation instructions: Is there a clearly-stated list of dependencies? Ideally these should be handled with an automated package management solution.
[x] Example usage: Do the authors include examples of how to use the software (ideally to solve real-world analysis problems).
[x] Functionality documentation: Is the core functionality of the software documented to a satisfactory level (e.g., API method documentation)?
[ ] Automated tests: Are there automated tests or manual steps described so that the functionality of the software can be verified?
[ ] Community guidelines: Are there clear guidelines for third parties wishing to 1. Contribute to the software 2. Report issues or problems with the software 3. Seek support

Software paper

[x] Summary: Has a clear description of the high-level functionality and purpose of the software for a diverse, non-specialist audience been provided?
[x] A statement of need: Does the paper have a section titled 'Statement of need' that clearly states what problems the software is designed to solve, who the target audience is, and its relation to other work?
[ ] State of the field: Do the authors describe how this software compares to other commonly-used packages?
[x] Quality of writing: Is the paper well written (i.e., it does not require editing for structure, language, or writing quality)?
[ ] References: Is the list of references complete, and is everything cited appropriately that should be cited (e.g., papers, datasets, software)? Do references in the text use the proper citation syntax?

alemermartinez commented 3 weeks ago

@editorialbot commands

editorialbot commented 3 weeks ago

Hello @alemermartinez, here are the things you can ask me to do:


# List all available commands
@editorialbot commands

# Get a list of all editors's GitHub handles
@editorialbot list editors

# Adds a checklist for the reviewer using this command
@editorialbot generate my checklist

# Set a value for branch
@editorialbot set joss-paper as branch

# Run checks and provide information on the repository and the paper file
@editorialbot check repository

# Check the references of the paper for missing DOIs
@editorialbot check references

# Generates the pdf paper
@editorialbot generate pdf

# Generates a LaTeX preprint file
@editorialbot generate preprint

# Get a link to the complete list of reviewers
@editorialbot list reviewers

alemermartinez commented 3 weeks ago

Hi @jbytecode I would like to ask for your guidance on how to communicate some issues I observed while reviewing the paper.

For instance, I believe that requiring users to manually select the B-splines basis, without providing a default option for the Bspline argument, makes the package less "user-friendly" than it could be. Including a default option for the univariate case (and for the bivariate setting, if possible) would be beneficial. In situations where computing k-fold cross-validation is computationally expensive, using a fixed number of B-splines as a starting point could be an effective approach. Additionally, it would be important to include some relevant methods to enhance usability.

The term “robust” has been used in the paper. I would appreciate some clarification on what “robust” refers to in this context.

Regarding related packages, are there any other commonly-used packages that estimate under these models, aside from the two developed by the author’s colleagues?

Additionally, I would suggest including system times in order to compare the different B-spline methods presented in the vignette.

I also found some typos, particularly in the mathematical equations. Some of these equations also extend beyond the right margin of the PDF file, affecting readability.

jbytecode commented 3 weeks ago

@alemermartinez - Thank you for your review and suggestions. I think they're very clear and I hope @JiangmeiRubyXiong can handle most of them. You can also open pull requests that include your corrections on the manuscript and/or open issues that address your suggestions. Writing down your suggestions here is also a convenient way of reviewing. Thank you!

@JiangmeiRubyXiong - Could you please consider the suggestions above and update your status? Thank you in advance.

alemermartinez commented 3 weeks ago

Thanks @jbytecode Below are the additional issues I found while reviewing the paper and vignette.

From the paper:

Line 26: The word “and” is missing.
Lines: 45 and 54. The letter “beta” is missing in the PDF compilation.
Line 49: The symbol for independence might not be clear to the reader. I suggest replacing it with the word “independent”.
After equation (1): There is no mention in the main paper of the probability term that was left out.
Line 62: The equation exceeds the page margins and is unreadable.
Equation (2). The variable “s_n” is lowercase but in the sum it appears in uppercase. Additionally, an “i” appears instead of a “k” and some “k”’s are missing.
Lines 115 and 117: The formulas exceed the right margin and can be broken before “degree=3”.
Lines 138 and 139: The formulas exceed the right margin as well.
Lines 143: The output is missing.
Table 2: This table is not referenced in the text.

From the vignette:

The reference to Schumaker should be 2007, as this is the third edition (as mentioned in the paper), but it is cited as 1981 here.
Before Equation (1), the regression model is stated as Y=alpha + X beta + epsilon. However, in the first paragraph, it states alpha + beta^T X + epsilon. Is X the same in both cases? If so, a transpose might be missing.
Equation (3): There are two logarithms in the second sum.

JiangmeiRubyXiong commented 3 weeks ago

Thanks @alemermartinez for catching all the typos and reviews! I will fix all typos, and I will discuss with co-authors regarding the major comments.

editorialbot commented 1 week ago

:wave: @aalfons, please update us on how your review is going (this is an automated reminder).

openjournals / joss-reviews