Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: check_eq: limited capacity of locals


From   "Gresch,Cornelia" <[email protected]>
To   <[email protected]>
Subject   st: check_eq: limited capacity of locals
Date   Mon, 20 Oct 2008 09:37:29 +0200

Dear all,

I have a problem with the ado "check_eq" (- a package which can be used to check a selection of predictors for a multiple imputation model with (ado: ICE)):

I want to check the equations for several dependent variables by using 20 predictors. Since several of the predictors are categorial variables integrated as "dummies" into the model the different equations can become very large.

E.g. one of the equations looks as follows (while all *_1/*_2/*_3 ... variables are dummy-sets of categorial variables):

#delimit;
check_eq, eq(
e22106: e22107 e22104 e22105 e22103 e309m_1 e309m_2 e309m_3 e309m_4 e309m_5 e309m_6 e309m_8 e309v_1 e309v_2 e309v_3 e309v_4 e309v_5 e309v_6 e309v_8 e310m_1 e310m_2 e310m_3 e310m_4 e310m_5 e310m_7 e310m_8 e339_1 e339_2 e339_4 e339_5 e339_6 e339_7 e310v_1 e310v_2 e310v_3 e310v_4 e310v_5 e310v_7 e310v_8 e22102 tr12empr_1 tr12empr_2 tr12empr_3 tr12empr_5 e226iv e209a_1 e209a_2 e209a_4 e209a_5 e209a_6 e209a_7 e209a_8 tr10empr_1 tr10empr_2 tr10empr_3 tr10empr_5 e340_1 e340_2 e340_4 e340_5 e340_6 t_sci s304_1 s304_2 s304_4 s304_5 e219a_1 e219a_2 e219a_4 e219a_5 e219a_6 e219a_7 slsprachr_2 slsprachr_3 slsprachr_4 slsprachr_5 slsprachr_6 slsprachr_7 slsprachr_8 e3his,
...-

If I use the command I get error messages like 

- e2 ambiguous abbreviation - 

I checked it with -set trace on- and the equation seems to be too long for one local used in the ado, at least the long list of predictors is cut off in the middle ending with "e2" which causes the error message.

 
So my question: is there any way to either extend the capacity of locals and how could I do it within the ado or is there any other way to integrate categorical variables in a shorter way into the equation? It is not possible to use "stars" (like e310m_* instead of e310m_1 e310m_2 e310m_3...).

I hope you have any comments on this,
Thanks!
Cornelia


**********************************************
Cornelia Gresch (geb. Hausen)
Max-Planck-Institut für Bildungsforschung
Lentzeallee 94
14195 Berlin - Germany
Raum: 296
Telefon: 030-82406-675
Email: [email protected]


*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index