[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: RE: Instrumental variables regression for grouped panel data
It is not clear why you want to use a string
variable here. String variables are designed
to hold arbitrary text and are considered
as equivalent to numeric missings in this
If your string variable is in effect coding a categorical
variable, check out -encode-. If it is in effect
a string variable by mistake, check out -tostring-.
> 3) STATA doesn't allow me to use string variables in the
> random effects
> regression, and gives an error of r(2000): no observations.
> What is the
> cause of this problem?
* For searches and help try: