[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: Why does one command "lose" observations compared to another command?
At 03:02 PM 1/22/2006, Richard Williams wrote:
Does mecwt4 include weights of zero? I am guessing that may be
why. svy still counts cases with 0 weights, but mean with the
weight parameter does not.
To follow up on my own post - the Stata 9 Data Manual says on p. 10,
pt. #6 "svy commands handle zero sampling weights properly. Standard
commands ignore any observations with a weight of zero." It then
explains how postsampling adjustment procedures can legitimately lead
to weights of zero and how estimates of standard errors can sometimes
be affected if zero weights are not handled properly.
Assuming you do have zero weights, you may want to verify that they
are legit and shouldn't really be missing instead.
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
* For searches and help try: