[PRE REVIEW]: defm: Estimation and Simulation of Multi-Binary Response Models in R

[editorialbot]

Submitting author: !--author-handle-->@gvegayon<!--end-author-handle-- (George Vega Yon) Repository: https://github.com/UofUEpiBio/defm Branch with paper.md (empty if default branch): Version: 0.1-1 Editor: Pending Reviewers: Pending Managing EiC: Arfon Smith

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/49919a5632258533a1f0bec73cc6d36f"><img src="https://joss.theoj.org/papers/49919a5632258533a1f0bec73cc6d36f/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/49919a5632258533a1f0bec73cc6d36f/status.svg)](https://joss.theoj.org/papers/49919a5632258533a1f0bec73cc6d36f)

Author instructions

Thanks for submitting your paper to JOSS @gvegayon. Currently, there isn't a JOSS editor assigned to your paper.

@gvegayon if you have any suggestions for potential reviewers then please mention them here in this thread (without tagging them with an @). You can search the list of people that have already agreed to review and may be suitable for this submission.

Editor instructions

The JOSS submission bot @editorialbot is here to help you find and assign reviewers and start the main review. To find out what @editorialbot can do for you type:

@editorialbot commands

[editorialbot]

Hello human, 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]

Software report:

github.com/AlDanial/cloc v 1.88  T=0.12 s (714.0 files/s, 232893.4 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
C/C++ Header                    63           4942           2554          11393
Bourne Shell                     2            458            472           3596
SVG                              1              0              0           2130
C++                              3            159            329            644
Markdown                         6            146              0            569
R                                6             95            452            237
TeX                              1             17              0            158
m4                               1             31              0            145
Rmd                              1             85            151             86
YAML                             2             20             11             74
make                             2             20              4             43
Dockerfile                       1              6              0              5
-------------------------------------------------------------------------------
SUM:                            89           5979           3973          19080
-------------------------------------------------------------------------------

gitinspector failed to run statistical information for the repository

[editorialbot]

Wordcount for paper.md is 620

[editorialbot]

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

[editorialbot]

Five most similar historical JOSS papers:

BayesMFSurv: An R Package to Estimate Bayesian Split-Population Survival Models With (and Without) Misclassified Failure Events Submitting author: @Nicolas-Schmidt Handling editor: @marcosvital (Active) Reviewers: @alletsee, @andybega Similarity score: 0.8257

Estimating statistics from multi-state models using simulation with multistateutils Submitting author: @stulacy Handling editor: @arfon (Active) Reviewers: @tgerke, @jenniferthompson, @rrrlw Similarity score: 0.8209

BGGM: Bayesian Gaussian Graphical Models in R Submitting author: @donaldRwilliams Handling editor: @akeshavan (Retired) Reviewers: @jayrobwilliams, @paulgovan Similarity score: 0.8176

rbmi: A R package for standard and reference-based multiple imputation methods Submitting author: @nociale Handling editor: @fboehm (Active) Reviewers: @DanielRivasMD, @JoranTiU Similarity score: 0.8161

fitODBOD: An R Package to Model Binomial Outcome Data using Binomial Mixture and Alternate Binomial Distributions. Submitting author: @Amalan-ConStat Handling editor: @csoneson (Active) Reviewers: @osorensen, @jjharden Similarity score: 0.8158

⚠️ Note to editors: If these papers look like they might be a good match, click through to the review issue for that paper and invite one or more of the authors before before considering asking the reviewers of these papers to review again for JOSS.

[arfon]

@gvegayon – thanks for your submission to JOSS. Could you describe which aspects of the codebase (https://github.com/UofUEpiBio/defm) are the defm package (i.e., what would need review here). There looks to possibly be some quite large dependencies included in the repo too?

[gvegayon]

Hi @arfon, sure. It would be all, with the exception of the C++ headers included under the inst/include folder. This R package is a wrapper of a portion of a larger project I have been working over the years (barry). Other than that, the package only depends on R core R packages and Rcpp.

[arfon]

Got it, thanks @gvegayon.

Re-running cloc excluding inst/include:

-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
Bourne Shell                     2            458            472           3596
SVG                              1              0              0           2130
CSV                              1              0              0           1731
C++                              3            159            329            644
Markdown                         6            146             17            553
R                                6             95            452            237
TeX                              1             17              0            158
m4                               1             31              0            145
Rmd                              1             85            151             86
YAML                             2             20             11             74
make                             2             20              4             43
C/C++ Header                     1              7              3             22
Dockerfile                       1              6              0              5
-------------------------------------------------------------------------------
SUM:                            28           1044           1439           9424
-------------------------------------------------------------------------------

[arfon]

@editorialbot query scope

@gvegayon – as this is on the smaller-side of what we'd typically allow in JOSS I'm going to ask the wider editorial team to give their opinion on whether this is in scope for us. This will likely take a couple of weeks to complete.

[editorialbot]

Submission flagged for editorial review.

[arfon]

Hi @arfon, sure. It would be all, with the exception of the C++ headers included under the inst/include folder. This R package is a wrapper of a portion of a larger project I have been working over the years (barry). Other than that, the package only depends on R core R packages and Rcpp.

Should https://github.com/USCbiostats/barry be counted as part of this submission then? The current consensus of the JOSS editorial team is that this submission doesn't meet our substantial scholarly effort criterion but perhaps we're missing something?

[gvegayon]

Thank you, @arfon. I understand the issue. From the scientific point of view, the package does implement the defm method, making it available for other users. The barry component of it provides the backbone for counting statistics, but the interface for model building and parameter estimation is all in the defm package. Regarding the amount of work, sure, I can see how this falls below the 1,000 lines of code, as what I see from cloc:

cloc src/ README.Rmd R/
      14 text files.
      14 unique files.                              
       4 files ignored.

github.com/AlDanial/cloc v 1.90  T=0.01 s (1001.6 files/s, 224959.6 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
C++                              3            159            329            644
R                                5             87            451            222
Rmd                              1             85            151             86
C/C++ Header                     1              7              3             22
-------------------------------------------------------------------------------
SUM:                            10            338            934            974
-------------------------------------------------------------------------------

Nevertheless, I would argue that comments on R and C++ files are doxygen comments, which are thoughtful work documenting the software.

barry is a massive library with lots of functionalities that are not used in defm. With such a blurry line separating the defm components, I would argue it would be better to avoid it. The only component of barry that can be distinguished as proper of defm is the module defm itself, so maybe that part could be included in the review:

cloc inst/include/barry/models/defm
       5 text files.
       5 unique files.                              
       0 files ignored.

github.com/AlDanial/cloc v 1.90  T=0.01 s (514.7 files/s, 174368.1 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
C/C++ Header                     5            396            234           1064
-------------------------------------------------------------------------------
SUM:                             5            396            234           1064
-------------------------------------------------------------------------------

That said, if it makes things easier, I could work on adding some more documentation and functionality to the package.

I appreciate all your work, thanks!

[arfon]

:wave: @gvegayon – apologies the scope review has taken a long time to complete here. Our decision is to reject at this stage, but we encourage you to resubmit.

Concerns of the editors at this point include:

• Small size and limited documentation.
• Lack of (unit) tests are a significant concern. This would be flagged by reviewers too.
• There was some concern that it wasn't easy to understand what the relationship was to the existing literature (your paper currently isn't compiling properly).

[arfon]

@editorialbot reject

[editorialbot]

Paper rejected.

[gvegayon]

Thank you, @arfon. Completely understand. I'll follow your advice. Thanks!