 |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: RE: Percentage as dependent variable, using -svy-
Let me ask a small question to clarify this
for those savvy about -svy-.
Your percent measure evidently varies between 0 and 1.
Do you mean that you are dealing with a
proportion or fraction, or do you mean what you
say?
Nick
[email protected]
Daw, Christina M
> I have a question prompted by Austin Nichols' earlier
> suggestion (thank you!) to look at -svy ratio- when
> considering variance extimates in variables that are
> percentages. My dependent variable is a percentage of total
> cost (and 0 and 1 are included values). How do I make that
> percentage into a variable to use as a dependent variable in
> regressions with svy commands and so obtain the appropriate
> variance/SE estimates? The -svy ratio-command allows the
> construction of a ratio, but not a variable with the ratio's
> value provided for each observation (at least I haven't been
> able to figure it out). Again, the svy commands do not
> support the fractional response variable glm regression
> method from Papke and Wooldridge that has been discussed in
> earlier posts.
*
* 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/