Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Standard error of a ratio of two random variables


From   Steven Samuels <[email protected]>
To   [email protected]
Subject   Re: st: Standard error of a ratio of two random variables
Date   Thu, 15 Jan 2009 14:13:36 -0500


After reading the document that Sergiy referred to, I think that you are right. I misread Sergiy's post.

-Steve



On Jan 15, 2009, at 1:19 PM, Austin Nichols wrote:

Steven Samuels <[email protected]>:
Perhaps I misunderstood, but I thought Y did not condition on school.
As I understand it, the goal is to estimate the proportion of the
population that finishes some level of schooling by taking the ratio
of the number entering that year of school to the total population of
the "right" age for that year of school (including those who never
enrolled in school).  This is related to the "graduation rate" or
"dropout rate" calculations for states in the US discussed by e.g.
http://www.rand.org/pubs/working_papers/2006/RAND_WR372.pdf
http://www.urban.org/UploadedPDF/411050_realtruth.pdf
In 2004 or 2005, I recommended using Census data on population
age-eligible 5 years prior in a state (e.g. population aged 22 who
report living in the state of interest 5 years ago; see
http://usa.ipums.org/usa-action/codes.do?mnemonic=MIGPLAC5) for the
denominator and number graduating in the state 5 years ago (from state
admin data) for the numerator, which I think is conceptually similar
to Sergiy's measure, but I don't think anyone ever constructed those
estimates. Both the graduation rate and the dropout rate calculations
require some definition of "on-time" completion (or dropping out as
not having completed school within, say, 4 years of when your peers
did), which is also relevant to Sergiy's calculation.  I.e. should you
not count people who finish a year or two late as completing school?

On Thu, Jan 15, 2009 at 12:08 PM, Steven Samuels
<[email protected]> wrote:
Austin-
Sergiy defined the denominator population to be:
[Y] population at least 10 years old and less than 11 AND in the 5th grade
*
*   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/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index