Bookmark and Share

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]

Re: st: confa with R2>1


From   Stas Kolenikov <[email protected]>
To   [email protected]
Subject   Re: st: confa with R2>1
Date   Tue, 30 Aug 2011 16:14:01 -0500

-sem- will produce the same result, although it does work faster.
Sorado would want to specify -robust- option, and if the negative
variance of BORED variable retains significance, modify the model.

BTW, Stata convention is to have variables in lower case. I guess it
follows the Internet (and earlier email) formatting convention that
one uses capital letters when they need to SHOUT SOMETHING OUT LOUD.
The data set in question was probably exported from another source
such as SPSS.

On Tue, Aug 30, 2011 at 10:07 AM, Anders Alexandersson
<[email protected]> wrote:
> It's a "Heywood case", so maybe you specified the wrong model.
> Heywood cases are discussed, for example, on pages 362-363 in the SJ
> 9(3) article for confa:
> http://www.stata-journal.com/article.html?article=st0169
>
> An alternative to the user-written -confa- is the new -sem- command in Stata 12.
>
> Anders Alexandersson
> [email protected]
>
> Sorado  <[email protected]> wrote:
>> I ran a confa model and found that one of my variables has an R2>1 (see variable called BORED). Did I specify something wrong?
>>
>> If anyone can help that would be greatly appreciated.
>>
>> Regards
>>
>> ****OUTPUT BELOW*******
>>
>> . confa (neg:  ANG ASH GUILT FEAR) (pos:  JOYFUL EXCITED HOPE) (amb:  IRRITATED BORED) (dep:  POWERL CONF DESPAIR), from(ones)
>>
> [...]
>> ------------------------------------------------------------------------------
>>             |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
>> -------------+----------------------------------------------------------------
> [...]
>> Var[error]   |
>>       BORED |  -.7293374   .1959337    -3.72   0.000     -1.11336   -.3453144
> [...]
>> -------------+----------------------------------------------------------------
>> R2           |
> [...]
>>       BORED |     1.5988
> [...]
>
> *
> *   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/
>



-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.

*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index