Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Brendan Churchill <Brendan.Churchill@utas.edu.au> |
| To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
| Subject | RE: st: Count variables and growth curves |
| Date | Thu, 28 Jun 2012 10:05:52 +0000 |
Hi Maarten Thank you very kindly for replying to my question! I have centred all my continuous/count variables and this has seemed to have improved the look of my constant! I do have one more issue... I am grouping year of birth into small five-year birth cohorts. I have year of birth from 1909 to 1986. When I recode this into 14 birth cohorts (for example 1981-1986 = 14). These have been coded from 0 to 14. I have also tried 1 to 15, but still the erroneous constant problem remains. Any suggestions? Again, I greatly appreciate your help! -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Maarten Buis Sent: Thursday, 28 June 2012 6:08 PM To: statalist@hsphsun2.harvard.edu Subject: Re: st: Count variables and growth curves On Thu, Jun 28, 2012 at 8:04 AM, Brendan Churchill wrote: > I'm working on a growth curve model to explain attitudinal changes over > time. I have noticed that when I include independent count variables like > income or hours that my intercept dramatically increases - beyond what would > seem normal. Can you help me out with what this might be? The constant is the expected outcome when all independent variables equal zero. If some independent variables are zero way outside the range of the data than the constant would become a rather extreme extrapolation. A typical example would be year of birth. If you do nothing than the constant will be the expected outcome for someone born in the year 0, which is typically some 1900 years before the range of the data. I typically center my variables at some meaningful value within or close to the range of the data. So in case of year of birth I will often just subtract 1950 from year of birth, so that the constant represents the cohort born in 1950. Hope this helps, Maarten -------------------------- Maarten L. Buis Institut fuer Soziologie Universitaet Tuebingen Wilhelmstrasse 36 72074 Tuebingen Germany http://www.maartenbuis.nl -------------------------- * * 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/ * * 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/