When I weight my data using WTSUPP, the number of obervations listed in the regression output is less than the number of actual observations in my data.
Any ideas for what could be causing this? Thanks!
As an addendum to this: I am using the ASEC March sample and manipulating the data in STATA
Housing units that were vacant or individuals who could not be interviewed (due to refusals to participate or absence of the individual from the household) are included in the IPUMS-CPS data beginning in 1988. Such vacant households and non-interview records have a weight of zero in WTSUPP.