Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# st: ICE with intervall

 From "Renger van Nieuwkoop" <[email protected]> To <[email protected]> Subject st: ICE with intervall Date Wed, 27 Oct 2010 11:02:00 +0200

```Hi
I am trying to use ICE with interval imputation (the values are censored
and are not allowed to be below 0).
I have generated two variables co2_lb (lower bound) = 0 and co2_ub
(upper bound) = . and then tried
ice c01  c02  c02_lb c02_ub inc_earned, m(5) saving(imputed)
interval(c02:c02_lb  c02_ub) replace
Without interval I have no problems with ICE, with interval I get the
following output (see below).
Any idea what I am doing wrongly?
Thanks
Renger

. ice c01  c02  c02_lb c02_ub inc_earned, m(5) saving(imputed)
interval(c02:c02_lb  c02_ub) replace

#missing |
values |      Freq.     Percent        Cum.
------------+-----------------------------------
0 |     25,181       85.37       85.37
1 |      3,579       12.13       97.50
2 |        735        2.49      100.00
3 |          1        0.00      100.00
------------+-----------------------------------
Total |     29,496      100.00

Variable | Command | Prediction equation
------------+---------+-------------------------------------------------
------
c02_lb |         | [Lower bound for c02]
c02_ub |         | [Upper bound for c02]
c01 | regress | c02 inc_earned
inc_earned | regress | c01 c02
c02 | intreg  | c01 inc_earned
------------------------------------------------------------------------
------

Imputing [Note: in regression for c01, permanently removing c02 due to
collinearity]
[Note: in regression for inc_earned, permanently removing c02 due to
collinearity]

Error #459 encountered while running -uvis-
I detected a problem with running uvis with command intreg on response
c02
and covariates c01 inc_earned.

The offending command resembled:
uvis intreg c02 c01 inc_earned , gen([imputed])

you may wish to try the -persist- option to persist beyond this error.
dumping current data to ./_ice_dump.dta
something that should be true of your data is not
r(459);

*
*   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/
```