Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Nick Cox <njcoxstata@gmail.com> |
| To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
| Subject | Re: st: growth rates |
| Date | Fri, 7 Mar 2014 14:10:43 +0000 |
Maarten's [sic] advice is probably the most relevant here. I'd expect positive numbers and exponential growth as a zeroth approximation, so fractional growth rate is good not only for tracking individual countries but also for comparing different countries. Nick njcoxstata@gmail.com On 7 March 2014 14:02, Bornmann, Lutz <lutz.bornmann@gv.mpg.de> wrote: > Thanks, Marten for this first solution. > > Nick, I am looking for advice on how to measure growth. Martens solution standardizes the annual changes in publication numbers. Are there other options and how can I get an overall growth value with which I can compare several countries? > > Lutz > >>-----Original Message----- >>From: owner-statalist@hsphsun2.harvard.edu [mailto:owner- >>statalist@hsphsun2.harvard.edu] On Behalf Of Nick Cox >>Sent: Friday, March 07, 2014 2:24 PM >>To: statalist@hsphsun2.harvard.edu >>Subject: Re: st: growth rates >> >>I don't get this. Do you have a definition of growth rate and want >>Stata code for this or do you want advice on how to measure it? >> >>For example, if something can ever be zero or negative, then even >> >>change in value / previous value >> >>can not be a good idea, because growing from -1 to 0 gives growth rate >>of -1 and growing from 0 to 1 gives an indeterminate value. >> >>so even that is not a universal. >>Nick >>njcoxstata@gmail.com >> >> >>On 7 March 2014 13:12, Bornmann, Lutz <lutz.bornmann@gv.mpg.de> wrote: >>> Hi, >>> >>> I do have annual publication numbers for several countries: >>> >>> ITEM_PY us' ch' >>> 1990 3759 119 >>> 1991 3738 149 >>> 1992 3757 149 >>> 1993 3810 169 >>> 1994 3920 199 >>> 1995 4134 171 >>> 1996 4404 211 >>> 1997 4436 236 >>> 1998 4513 246 >>> 1999 4542 238 >>> 2000 4456 275 >>> 2001 4519 263 >>> 2002 4602 259 >>> 2003 4705 276 >>> 2004 4836 310 >>> 2005 4834 337 >>> 2006 5150 344 >>> 2007 5253 433 >>> 2008 5568 466 >>> 2009 5520 475 >>> 2010 5690 534 >>> >>> I would like to calculate growth rates. What is the best (and simplest) >>statistical procedure to do that? >>> >>> Thank you, >>> >>> Lutz >>> >>> * >>> * For searches and help try: >>> * http://www.stata.com/help.cgi?search >>> * http://www.stata.com/support/faqs/resources/statalist-faq/ >>> * http://www.ats.ucla.edu/stat/stata/ >>* >>* For searches and help try: >>* http://www.stata.com/help.cgi?search >>* http://www.stata.com/support/faqs/resources/statalist-faq/ >>* http://www.ats.ucla.edu/stat/stata/ > > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/faqs/resources/statalist-faq/ > * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/