--- Dirk Nachbar wrote:
> I have survey data for one year from which I want to estimate
> an equation for the age a person had his first child. I
> derive the independent variable from the adult's and oldest
> child's age. When I regress that equation I have significantly
> positive cohort effects for old cohorts which I find quite
> puzzling for my UK sample. My expectation was that the age
> someone had a child would increase over time. Do you have any
> views on what might have gone wrong.
Dirk Nachbar:
This is not a lot of information to go on, but three thoughts
jump to mind: The oldest cohort in a sample is usually quite
small, in which case this could be sampling variation. If the
oldest cohort is very old (say >80 years) than selection may
play a roll: you can only get answers from people who are still
alive and are sufficiently lucid to understand and answer a
questionnaire. Better educated people stay alive and healthy
longer and they get children at a later age. Another cause
could be if the oldest cohort includes people getting children
just after World War II. In the Netherlands people postponed
getting children during WWII, hence this cohort would get children
at an older age. I would imagine that something similar occurred
in the UK, even though you weren't occupied.
HTH,
Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting adress:
Buitenveldertselaan 3 (Metropolitan), room Z214
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting adress:
Buitenveldertselaan 3 (Metropolitan), room Z214
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
Send instant messages to your online friends http://uk.messenger.yahoo.com
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/