Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
r-class and e-class programs [was: Re: st: Amelia object as data.frame]
From
Nick Cox <[email protected]>
To
[email protected]
Subject
r-class and e-class programs [was: Re: st: Amelia object as data.frame]
Date
Wed, 27 Feb 2013 10:43:06 +0000
I've changed the name of this thread so that no-one is distracted by a
previous digression to an R question.
If you have done no programming this detail can't be covered by a few
suggestions. You have to read the appropriate sections of [U].
There is a more fundamental question which should be easier to answer.
-mi- refused to play because it found no e(b) and no e(V). So, the
issue is not how to convert an r-class program to an e-class program,
but whether that even makes sense here. That is, can you recast this
procedure as producing a vector of coefficient estimates and a
variance-covariance matrix? My very wild guess is that you can't; if
so the road ahead is well and truly blocked. I'd be happy to be wrong
here, but that's what you need to answer.
Nick
On Wed, Feb 27, 2013 at 10:33 AM, Laura Maria Schwirz <[email protected]> wrote:
> Thanks, Billy. I haven't written my own programmes and am fairly new
> to this. Any suggestions on how to change the programme so it supports
> rclass programmes? I also tried the cmdok option which does not work
> for the same reason.
> I'd rather work within the same package and ideally work with Stata.
>
> Thanks,
> Laura
>
> On 26 February 2013 15:27, William Buchanan <[email protected]> wrote:
>> Hi Laura,
>>
>> The issue that Daniel pointed out wasn't that MI doesn't support -msp-, but that -msp- does not support MI data. For more information, see -help program_properties##mi- which explains some of the information that programmers use to make their packages support MI data. One reason that the program is likely incompatible with the -mi estimate- command is that -msp- is an rclass program (a point that Nick Cox made yesterday in response to your previous thread).
>>
>> That being said, you could always use -msp- as a framework to develop your own procedure (say -msp2-) that would be an eclass program and would support MI commands.
>>
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/