Dear all,
I am using Manski's Bounds package to obtain non-parametric bounds on a
causal parameter of interest. I have successfully used -treat- to estimate
"worst case" (or "no assumption") bounds over a grid defined by some
discrete groupings of some covariates. However, when I estimate bounds given
monotone treatment response (MTR), -monotone- simply reports an error saying
"Unknown function ()". This report is rather curious, because I have copied
the command directly from the manual on Bounds (see:
http://faculty.wcas.northwestern.edu/~cfm754/bounds_stata.pdf). I have
stated the kernel function with "gau", implying the use of the Gaussian
distribution. This is exactly also what I have done in the estimation of the
"worst case" bounds with -treat-. -treat-, however, does not report any
errors.
Does anyone have experience with this error and, if so, can anyone tell me
what is wrong?
All the best,
Kristian
*
* 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/
