st: gidecomposition...problems

[adiallo5@worldbank.org]

Vincenzo,

I used that command last year and usually, when this happens,
it means you are using the same dataset.

What you should do is something like:

u mydata // this is a "pooled data"

preserve
keep if (region==1 & some other rules)
sa usingI_1989, replace

restore, preserve
keep if (region~=1 & some other rules)

gidecomposition using  usingI_1989 , etc...

restore // back to original data

HTHs.

Amadou.





-------------------------------------------------------------------


                                                                                 
                                                                                 
                                                                                 
 dear  all,                                                                      
 i am using the gidecomposition program in stata 9 to decompose the              
 change                                                                          
 in poverty into the 3 effects. the outcome I get looks like this:               
                                                                                 
 Growth and Inequality Poverty Decomposition                                     
                                                                                 
 Base year 1        Base year         2           Average effect                 
                                                                                 
 Poverty rate (P0)           100.000        100.000                              
                                                                                 
 Change in P0                 0.000         0.000                         0.000  
                                                                                 
 Growth component             0.000         0.000                         0.000  
 Redistribution component     0.000         0.000                         0.000  
 Interaction component        0.000         0.000                         0.000  
                                                                                 
 that is, it is as stata does not recognize any changes in the                   
 Head-Count. I                                                                   
 canceled out from my original dataset all the variables not needed, and         
 I                                                                               
 kept only Head-Count for each region (I have 19 italian region, for             
 which                                                                           
 i will use "if"), year and gini coefficient..                                   
 could you tell me why stata does not reply as it was supposed? Am I             
 doing                                                                           
 something wrong? for instance should I set some description of the              
 distribution or of the data??                                                   
 the command I used to implement the decomposition is:                           
                                                                                 
 gidecomposition using "C:\Documents and                                         
 Settings\Vicius\Desktop\MAData\decomposition\usingI_1989.dta" if                
 region==1, var1(rHC) var2(rHC) pline1(povline) pline2(povline) hc               
                                                                                 
 thanks a lot                                                                    
 warm regards, vincenzo                                                          
                                                                                 
                                                                                 
                                                                                 
 --                                                                              
 Vincenzo Lombardo                                                               
 University of Sussex, Dept. of Economics                                        
 University of Napoli Parthenope, DSE                                            
 12 Canfield Road                                                                
 BN2 4DN Brighton - UK                                                           
 tel. (UK):++44(0)7765991711                                                     
 tel. (ITALY):++393284164302                                                     
                                                                                 
                                                                                 
 ------------------------------------------------------------------------------- 

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/