Official Publication of the International Institute of Forecasters

Guide for Authors
International Journal of Forecasting
Submissions to the International Journal of Forecasting can be made online at http://mc.manuscriptcentral.com/ijf

1. Papers must be in English. Write in a concise manner. Referees will be asked to consider the value of the paper relative to its length. Papers with poor English may be sent back to the author for correction.

2. Authors requiring information about language editing and copyediting services should visit http://www.elsevier.com/wps/find/authorshome.authors/languagepolishing or contact authorsupport@elsevier.com for more information.

3. Submission of a paper implies that it contains original work that has not previously been published and that has not being submitted for publication elsewhere. Publication in a limited distribution "Proceedings", or in a working paper series, does not disqualify a paper.

4. Authors are required to disclose papers published or under review in other journals that are based on similar methods or data. Please cite and explain how the current paper differs from these similar papers.

5. An abstract of 100-150 words is required. The abstract is one of the most important elements of your paper; many people will read only the abstract. Summarize the principal findings and how they were obtained. Explain why the findings are important for researchers and for practitioners. Be specific. Do not include references, jargon and mathematical notation.

6. Keywords (at least five) are also required. A list of recommended keywords is available at http://www.forecasters.org/ijf/keywords. There is no point repeating words that are in the title.

7. Provide a biographical sketch of not more than 100 words for each author. These should be in a separate file.

8. The main paper should not contain the names of authors, or anything else that might identify them.

9. Use major and minor headings to aid readability. Headings should be short. Double space everything. Use wide margins. Footnotes should be kept to a minimum. If used, they should be numbered consecutively and placed after the references.

10. References should include only relevant sources; for example, those papers that proposed and developed the methods used, papers that clarify the methodology, and papers that add further evidence. Do not include references simply to increase the length of your bibliography or to increase citation rates.

11. In the text, references should appear for papers as "Klein (1984)", or for books as "Box & Jenkins (1970, p.245)". At the end of the manuscript, the references should be listed alphabetically by surname of the first author. Use the following format:
• For articles: Armstrong, J. S. & Collopy, F. (1992). Error measures for generalizing about forecasting methods: Empirical comparisons. International Journal of Forecasting, 8, 69-80.
• For books: Cook, T. D. & Campbell, D. T. (1979). Quasi-Experimentation, Boston: Houghton Mifflin.
• For collective works: Kahneman, D. & Tversky, A. (1982). Intuitive prediction: Biases and corrective procedures. In: D. Kahneman et al. (Eds.), Judgment under uncertainty: Heuristics and biases. Cambridge: Cambridge University Press, pp.414-421.
• For web sites: Hyndman, R. J. (2006) Time series data library,http://www.robhyndman.info/TSDL/. Accessed on 4 December 2006.

Authors should ensure that there is a strict one-to-one correspondence between the authors' names (years) in the text and those in the reference list.

In general, only published references should be cited. If unpublished, indicate how copies may be obtained.

Please check all references against their original sources.

12. Use simple notation. Our readership crosses many disciplines. Avoid unusual symbols if possible.

13. If mathematical derivations are needed, put them in an Appendix.

14. Quotations should be kept to a minimum. Authors must obtain written permission from the publisher to use a quotation that exceeds 250 words.

15. Figures should be high resolution with descriptive headings. Provide explanatory labels for the rows and columns of a table. Figures of poor quality will not be published. Illustrations that have to be redrawn by the publisher will be charged to the author. The on-line version of a paper may include colour figures, but the print version will be in black and white.

16. Simplify the presentation of data. Round data to no more than three digits where possible. Organize tables and charts to aid understanding.

17. Authors using LaTeX should follow the guidelines at http://www.forecasters.org/ijf/authors

18. Authors should fully disclose their methods and data. The disclosure of data will be considered in the decision of whether to publish the paper. Upon acceptance the data sets of published papers will be posted on the IIF website: http://www.forecasters.org/ijf/. Authors should tell readers how to obtain additional details.

19. Supplementary material (e.g., extra tables, computer code, extended proofs, movie files) may be published at the above website and referenced in the article.

20. Evidence of prior peer review is helpful, such as a listing of the occasions on which this paper has been presented, and a list of colleagues who have reviewed the paper.

21. Authors are invited to provide names, addresses, and fields of interest of 4 to 6 persons outside their own institution who are qualified to act as referees. We will try to use at least one of these as a referee.

22. Further information for authors is available at www.elsevier.com/authors. This site provides facilities to track accepted articles and set up e-mail alerts to inform you of when an article's status has changed, as well as detailed artwork guidelines, copyright information, frequently asked questions and more. Contact details for questions arising after acceptance of an article, especially those relating to proofs, are provided after registration of an article for publication.

23. Page proofs will be sent to the (first) author. Please proof read-carefully. Corrections other than printer's errors may be charged to the author. The corresponding author will be provided, at no cost, either a PDF file of the article via e-mail or 25 paper offprints. Additional reprints (minimum of 50) are available at a cost and may be ordered prior to publication. Please consult the price list accompanying proofs.