22 Oct
2011
22 Oct
'11
3:40 p.m.
for the first, you can use the square root transformation. for the second,
rounding i'm sure will be fine.
Gary
--
*Gary King* - Albert J. Weatherhead III University Professor - Director,
IQSS - Harvard University
GKing.Harvard.edu <http://gking.harvard.edu/> - King(a)Harvard.edu -
@kinggary<http://twitter.com/kinggary>- 617-500-7570 - Asst 495-9271 -
Fax 812-8581
On Sat, Oct 22, 2011 at 2:19 PM, Sera Choma <sera.onalan(a)gmail.com> wrote:
Hi,
I would like to set bounds for some of my variables. For example I have a
variable that measures the number of health personnel in a given province.
The min should be 0, but I do not require a max bound. What would be the
best approach for this type of bound? Should I be setting the max to
infinity?
Also, I have set a bound for one of my dependent variables that is a
percentage of votes in a given province. The min is 0 and the max is 1.
However, when I impute my data the min for this variable is -1.388e-17,
which is nearly 0. I am not sure why this happens and if it is ok for me to
keep a negative number (even though it is so small) as my dependent
variable
(that is a proportion). Any suggestions?
Thank you for your help.
Sera