Thank you for agreeing to serve as a referee for the Statistical Science. We expect our referees to provide a careful and prompt assessment of the paper. Submitting a report within two months of receiving the paper will be especially appreciated by the editorial board and the authors. In any case, if you now find that you will not be able to submit a report within four months, please communicate with the Associate Editor immediately. In this latter case, any comments you can make, particularly regarding other possible referees, will be appreciated.

If you do provide a report, your findings should be presented in two parts:

    • An anonymous report to be sent to the author. This report should contain detailed comments, concrete criticisms, and constructive suggestions about the content and exposition of the paper. Some questions to keep in mind are: Is the presentation clear and well organized? Are the results new and interesting? Are the proofs correct and given in adequate detail, or can they be substantially simplified? Do the introduction and abstract give an adequate summary? Can paper be streamlined?
    • A letter stating your opinion regarding the disposition of the paper. This letter will only be seen by the editors involved. It should set forth your frank opinions about the paper and recommend:

(a) rejection,

(b) acceptance after some minor corrections, or

(c) acceptance after a substantial revision. Option (c) should only be used if you are convinced that the paper will be acceptable to you once the revisions are made. (In the case of a substantial revision, the revised manuscript will be sent to you for your review.) In the case of a poorly written paper with interesting ideas, we would prefer to reject the paper and give the author the option of resubmitting a new version.

Electronic submission of reports

Electronic submission of reports is strongly encouraged. Postscript and pdf files are also preferable unless the Associate Editor handling the manuscript has indicated otherwise. Tex and Latex files are also acceptable if they do not depend on non-standard style files or fonts. (For example, please avoid using Scientific Word.).

Handling the Manuscript

You should not return the manuscript to the associate editor, unless you have written corrections for the author on it. All manuscripts should be regarded as privileged and confidential, and their contents not disclosed without the author’s permission.


The success of the Statistical Science depends on the willingness of referees to take the time to ensure the quality and importance of the papers published. We are grateful for your assistance.