Re: st: query on right-censored predictors/covariates

[Richard Goldstein <richgold@ix.netcom.com>]

Phil,

thank you for the clarification

Rich

On 6/24/10 1:55 PM, Phil Schumm wrote:
> On Jun 24, 2010, at 12:33 PM, Richard Goldstein wrote:
>> thank you for the info about the -ice- options -- the variables are
>> *not* interval censored -- only the top is censored (e.g., I have the
>> actual counts if they are less than 10, but have a value of 10 for any
>> observation that has a count of at least 10; another example is that I
>> have actual age if less than 90, but anyone who is at least 90 years
>> of age has the value 90;
> 
> -ice- can handle intervals of the form [a,infinity), and you can also
> impose an upper bound so that you don't generate implausibly high values.
> 
>> the count variable is definitely not normally distributed
> 
> As I said, as long as you can transform to approximate normality for the
> imputation step, I think you'd be fine.  You could then just transform
> back to the original scale to fit your model.
> 
> -- Phil
*
*   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/