The typical JSS paper will have a section explaining the statistical technique, a section explaining the code, a section with the actual code, and a section with examples. All sections will be made browsable as well as downloadable. The papers and code should be accessible to a broad community of practitioners, teachers, and researchers in the field of statistics.
Each article/manual/paper will be an issue. Thus the appropriate bibliography entry will be Journal of Statistical Software, volume 1, 1995, issue 17, 1-15. There is no page limit.
The manuscript (article/paper/manual) will be peer reviewed in the usual way. The editor-in-chief selects an editor, the editor selects two reviewers (one of them can be the editor). The review has two parts: both the manuscript and the software are reviewed. The combination of the parts should work as indicated, be clearly documented, and serve a useful purpose. The statistical part of all submissions is reviewed for both correctness and usefulness. If the statistical technique has been published elsewhere, a short introduction with references is usually sufficient. To assess the software part, its source code must be submitted along with information on how to replicate the results from the manuscript.
The possible editorial decisions are:
Revisions, in any state of the review process, must always be submitted together with a point-to-point reply to the points made by reviewers and editors.
Accept decisions are always conditional on delivering a manuscript that satisfies the JSS style and reproducibility requirements. It is the responsibility of the author to make sure the manuscript conforms with the JSS requirements. Accepted manuscripts that do not satisfy these requirements cannot be published.
Manuscripts rejected by JSS cannot be resubmitted. We hope the review process gives the authors sufficient information to submit to another journal.
If a submission cannot be placed with an editor within three months the corresponding author will be notified the submission is unsuitable for the journal.
If a revision is not received back from the authors within a year, the paper will be considered to be withdrawn.
If a conditionally accepted paper is not brought into final form within a year, the paper will be considered to be withdrawn.
The Journal of Statistical Software has chosen to apply the Creative Commons Attribution License to all articles we publish in this journal. Under the CCAL, authors retain ownership of the copyright for their article, but authors allow anyone to download, reuse, reprint, modify, distribute, and/or copy articles in Journal of Statistical Software, so long as the original authors and source are credited. This broad license was developed to facilitate open access to, and free use of, original works of all types. Applying this standard license to your work will ensure your right to make your work freely and openly available. Code distributed with JSS articles uses the GNU General Public License (version 2 or version 3). Submitted software packages must use at least one of these as one of their license(s).
JSS will be free, in the sense that there is no charge for submission and no charge for subscription. Actually, there is no subscription. Everybody is free to download code and papers and to print or otherwise distribute them.
All submissions are electronic. Submissions should go to firstname.lastname@example.org and provide attachments or links to the following: (1) PDF manuscript in JSS style, (2) source code for the software, (3) replication materials for all results from the manuscript. Also the license(s) of the software should be clearly indicated (and need to include the GPL-2 for publication in JSS). Acknowledgments of receipt, and a JSS submission number, will be emailed to the corresponding author within two weeks. If you do not receive such an acknowledgment, contact email@example.com. Use the JSS submission number for all other correspondence with the editor.
Papers must be written in LaTeX using the JSS style files and must be submitted as pdfs. It is the responsibility of the authors to provide a submission in the appropriate format. JSS has no resources to help authors with conversions, so we strongly advise authors who need assistance to find a local LaTeX expert. The zip archive includes examples. Also, a manual with more detailed instructions is available in the download.
Source code for the software, replication materials, and potentially further supplements not in the paper must be submitted separately. The materials must enable reproducibility of all results from the manuscript (see also "Review Process" above).
Source code must be submitted in ASCII files - it should be readable and have comments. For software environments with package/library systems (e.g., R, S, Stata, etc.), the code should come with formatted help files and should be packaged for easy installation. If at all possible, submitted R packages should also be available from a standard repository (typically CRAN or Bioconductor). If feasible, we encourage to include JSS submissions as vignettes in the R packages.
Papers should preferably be in English. All non-English papers should have an English summary.
Code can be in any language. We prefer code that can be executed by interpreters, written in languages such as S, SPSS/Matrix, SAS/IML, Matlab, and Mathematica, provided the interpreter is not too esoteric. If it is, it should come with the submission.
Code in Fortran, C, C++, Common Lisp is also welcome, but it will generally take longer to review.
UCLA Statistics will maintain the interface to the journal (homepage, table of contents, links, interactive features), will provide disk space, and network access. The journal will have cross-referencing and search-on-keywords, allowing easy browsing. The journal indices are available as HTML, RSS, Bibtex, OAI-DC and RePEc. UCLA Statistics shall also maintain page counts, showing how many hits each paper gets.