I know that the physics and math communities are very into ArXiv, but what about the stats community? Is it customary to post there before submission?
$\begingroup$
$\endgroup$
4
-
$\begingroup$ I have never posted there and can't remember having looked for papers there, either. $\endgroup$– Christoph HanckCommented Aug 6, 2015 at 6:16
-
$\begingroup$ @DeepNorth yes, that would be interesting. I am asking both out of curiosity and because I recently posted an "as submitted" draft on ArXiv. Was wondering if it would really reach any extra eyeballs.... $\endgroup$– user75138Commented Aug 6, 2015 at 6:26
-
1$\begingroup$ Yes; some of us look at arXiv at least some of the time. I do when I can or when someone points me there, and I often link people to papers there. $\endgroup$– Glen_bCommented Aug 6, 2015 at 7:42
-
3$\begingroup$ Define "statistics". In the area where I work, survey methodology, my arguably naive searchers for "complex survey" and "finite population" brought up 2 and 42 results on arXiv, respectively. Every year, the Survey Research Methods Section of the American Statistical Association has about 40 sessions at the Joint Statistical Meetings, between 1 and 3 in every time slot throughout 4 days of the conference, and correspondingly produces at least a hundred of Proceedings papers. As far as I can tell, none of that makes it to arXiv. $\endgroup$– StasKCommented Aug 7, 2015 at 11:52
Add a comment
|
4 Answers
$\begingroup$
$\endgroup$
3
Yes, Arxiv is popular in the statistics and the data science community.
As the world of stats and data science evolves everyday, it is important for statisticians and data scientists to keep themselves adept with the latest happenings, techniques and algorithms.
It might not be as popular as it is in the physics community, but it does have its share of importance in the data-rich world.
You might be interested in Gitxiv, which puts together state-of-the-art research with the corresponding open source code/libraries.
-
3$\begingroup$ +1 for the link to Gitxiv...ill take a look. Do you regularly check ArXiv or subscribe to one of its email lists? $\endgroup$– user75138Commented Aug 6, 2015 at 6:35
-
2$\begingroup$ My pleasure. Gitxiv have brought the world of research a bit closer to the world of stats and computer science. Kudos to those guys. No, I don't subscribe to the mailing lists, but as most of the Machine Learning and analytics papers dwell there, I do check it out every week. $\endgroup$– Dawny33Commented Aug 6, 2015 at 6:38
-
3$\begingroup$ It would be better if you included some supporting evidence. Now it is just one word "Yes", and the rest is not informative (but Gitxiv is interesting, thanks for mentioning). $\endgroup$ Commented Aug 6, 2015 at 10:40
$\begingroup$
$\endgroup$
4
I shall give a definitive, evidence based answer. The answer is YES.
Look at Google Scholar metrics for probability and statistics, top 10 sources by h5-index:
Publication h5-index h5-median
1. Journal of Econometrics 62 93
2. The Annals of Statistics 58 81
3. arXiv Statistics Theory (math.ST) 57 80
4. Journal of Statistical Software 53 113
5. arXiv Probability (math.PR) 53 65
6. arXiv Methodology (stat.ME) 48 69
7. Journal of the American Statistical Association 48 66
8. Statistics in Medicine 42 62
9. Computational Statistics & Data Analysis 40 51
10. Journal of Business & Economic Statistics 39 67
Note, this list is not based on the number of publications, it's based on the the citation index.
Google's citation index is becoming as popular as Scopus and Reuters (ok, I don't have proof of this statement), so my answer is as objective as it gets.
Compare this to the list from Scimagojr.com on Statistics and Probability:
Title Type SJR H index Total Docs. (2014) Total Docs. (3years) Total Refs. Total Cites (3years) Citable Docs. (3years) Cites / Doc. (2years) Ref. / Doc. Country
1 Annals of Mathematics j Q1 8,551 72 46 209 1.572 647 207 3,05 34,17 US
2 Vital and health statistics. Series 10, Data from the National Health Survey k Q1 7,801 30 4 7 55 125 7 16,33 13,75 US
3 Journal of the Royal Statistical Society. Series B: Statistical Methodology j Q1 6,148 90 45 99 1.507 547 94 3,09 33,49 GB
4 Annals of Statistics j Q1 5,602 103 64 296 2.099 809 287 2,25 32,80 US
5 Journal of Statistical Software j Q1 5,003 64 67 220 2.540 1.364 220 3,91 37,91 US
6 Journal of the American Statistical Association j Q1 4,162 123 106 408 3.501 907 373 1,85 33,03 US
7 Probability Surveys j Q1 3,645 22 1 20 84 46 19 2,73 84,00 US
8 Bioinformatics j Q1 3,576 248 809 2.145 18.801 11.329 2.089 4,69 23,24 GB
9 Journal of Business and Economic Statistics j Q1 3,496 66 58 146 1.464 384 139 2,21 25,24 US
10 Biometrika j Q1 3,342 83 58 233 1.485 369 229 1,28 25,60 GB
There's good overlap with Google Scholar's top 10 list, as you can see. The latter list is also based on h-index, but it's not Google's citation. This only validates the former table, and conclusions from it: arXiv is popular among statisticians in academia.
SSRN is another place to dump the preprints. It's popular among econometricians.
-
$\begingroup$ +1 - Great job using Google metrics! The h-index definitely puts it up there. $\endgroup$– user75138Commented Aug 6, 2015 at 14:55
-
$\begingroup$ @Bey, one thing to be aware of: open access movement. arXiv is the place where people dump their preprints, that's how it started in physics. So, you're going to see the same paper in arXiv then later in Phys Rev, for example. Thus arXiv initially was created as means to disseminate research faster. Good papers don't usually appear on arXiv exclusively. $\endgroup$– AksakalCommented Aug 6, 2015 at 15:10
-
$\begingroup$ Yep. I usually only cite a paper I find on ArXiv if I can find it in a peer reviewed journal as well. My paper is there while it undergoes review and Ill update with the accepted preprint after the embargo period (assuming its not rejected). $\endgroup$– user75138Commented Aug 6, 2015 at 15:12
-
$\begingroup$ @Bey, while we're on it, there are two other places where you can dump your preprints: RePec and SSRN. The econometricians might be using these more often than arXiv $\endgroup$– AksakalCommented Aug 6, 2015 at 15:31
$\begingroup$
$\endgroup$
5
It is not a matter of personal opinion so let's look at some figures on terms appearing on arXiv pages (some random Google queries with few domain-specific terms):
cross validation site:arxiv.org returns
About 17,800 results
monte carlo site:arxiv.org returns
About 187,000 results
sampling site:arxiv.org returns
About 141,000 results
forecasting site:arxiv.org returns
About 11,300 results
regression site:arxiv.org returns
About 51,100 results
EDIT
As @Scortchi noticed, arXiv posts its own statistics. stat category appears in reports for the last three years as below:
year submissions % submissions
2014 2025 2.2%
2013 1602 1.7%
2012 1284 1.5%
This however may not fully represent the content of published papers since some of them may be highly related to statistics but be tagged as different domain (e.g. as math or cs).
Also, Xi'an's blog could pose as a case study. He writes much about Bayesian statistics and often mentions arXived papers (having their own tag).
It also seems that we mentioned "arXiv" on CrossValidated in 689 posts and comments until now (including here).
Does this make it popular or not? Still, hard to say, but for sure thousands of statistics-related papers were posted on arXiv and its popularity is growing.
-
3$\begingroup$ Or at least, thousands of papers using/mentioning statistical methodology $\endgroup$– Glen_bCommented Aug 6, 2015 at 7:43
-
$\begingroup$ @Glen_b yes, it is a matter of keywords to check, but I see no any better way to check if it is "popular". $\endgroup$– TimCommented Aug 6, 2015 at 7:48
-
4$\begingroup$ 'Statistics' is a subject area on arXiv - with 7,711 submissions to the end of 2014, 0.9% of the total. arxiv.org/help/stats/2014_by_area/index $\endgroup$– Scortchi ♦Commented Aug 6, 2015 at 11:36
-
$\begingroup$ @Scortchi I never digged so deep in this site, thanks! $\endgroup$– TimCommented Aug 6, 2015 at 11:37
-
$\begingroup$ +1 :) I didn't imagine this question as an analysis exercise...but you found a way to get at it...this is very cool :) Wouldn't expect anything less from folks on this site! I'd say based @Aksakal and your analysis, ArXiv is reasonably well subscribed to for statistics :-) $\endgroup$– user75138Commented Aug 6, 2015 at 14:55
$\begingroup$
$\endgroup$
All journals published by the Institute of Mathematical Statistics (IMS) -- and that includes The Annals of Statistics (one of the very top statistics journals), The Annals of Applied Statistics, etc. -- explicitly encourage authors to put preprints on arXiv and, moreover, take care of putting postprints on arXiv too. I am actually not aware of any math or physics journal that uploads papers to arXiv if the authors did not do it themselves!
The IMS encourages all members to post their articles on arXiv.
(http://www.imstat.org/publications/arxiv.html)
All IMS articles 2004 and forward are freely available in a postprint format on arXiv, as well as those articles posted by authors.
ArXiv is an open access, fully automated electronic archive and distribution server for research articles, now owned and operated by Cornell University, and partially funded by NSF. The main fields it covers are physics, mathematics, non-linear science, computer science, and quantitative biology. Recently, arXiv has cooperated with IMS and the Bernoulli Society to open up a new statistics category within mathematics. We expect this category to eventually grow into a top level archive comparable to e.g. mathematics and physics.
