Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: re: SSC Activity, November 2009


From   Kit Baum <baum@bc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: re: SSC Activity, November 2009
Date   Fri, 4 Dec 2009 14:44:16 -0500

<>
Some doubt was voiced in an earlier posting regarding the legitimacy of the download statistics. As it happens, we have been analysing these statistics for suspicious activity for several months. It is perfectly legitimate for a single IP address to download a package multiple times, as in some networks the IP address visible to my webserver is a common address for, e.g., all machines in a lab. Last month we found that the highest frequency of downloads of one package was from a domain named lab.wesleyan.edu, which sounded quite proper. 

I have looked at the Nov 2009 downloads of outreg2 and estout, tabuiating multiple downloads from the same IP as iota, and found:

  +------------------------------------------------+
  |                        ip         fname   iota |
  |------------------------------------------------|
  |             124.42.78.194   outreg2.ado     57 |
  | ssclab17.ads.ssc.wisc.edu   outreg2.ado     39 |
  |              193.227.8.65   outreg2.ado     38 |
  |             arc.lse.ac.uk   outreg2.ado     35 |
  |              137.53.241.9   outreg2.ado     34 |
  |------------------------------------------------|
  |       REDUCEDFORM.MIT.EDU    estout.ado    124 |
  |        newcell.crc.nd.edu    estout.ado     49 |
  |        194172.ntpu.edu.tw    estout.ado     41 |
  |    dhcp199.green.ox.ac.uk    estout.ado     36 |
  |              137.53.241.9    estout.ado     32 |
  +------------------------------------------------+

These are all multiple downloads exceeding 25 per site in that month for each package. Given the total number of downloads recorded (4,181 for outreg2.ado, 2,683 for estout.ado) these multiple downloads cannot represent a large fraction of the total. 
I do not see any evidence of systematic manipulation of the statistics.

If you peruse my prior months' postings of SSC activity, you will consistently find these two packages (and the original outreg) near the top of the list every month. Many users find these tools indispensable, and doubtless recommend them widely, as I do myself. 

Kit

Research Papers in Economics (RePEc)
http://repec.org




*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index