st: adjusted mean by group

[Rachele Capocchi <rachele.capocchi@arsanita.toscana.it>]

>     I have some problems with the adjusted means.
>     I did the adjusted means on quantitative variable (_8pgf2a) by a group var adjusting for uri_enz_creat_mg24h.
>
>     xi: regress _8pgf2a i.gruppi_ord uri_enz_creat_mg24h
>     adjust uri_enz_creat_mg24h , by( gruppi_ord)
>
>     RECODE of |
>     gruppi | xb
>     ----------+----
>     * 0 | 1309,4*
>      1 |1027,86
>      2 | 1068,04
>
>
>     Then I need to do the same, considering the sex.
>     
     anova _8pgf2a gruppi_ord uri_enz_creat_mg24h if sesso==1,continuous( uri_enz_creat_mg24h)
>     adjust uri_enz_creat_mg24h , by( gruppi_ord)
>
>     RECODE of |
>     gruppi | xb
>     ----------+-----------
>   *  * 0 | 1359,01**
>       1 | 994,102
>     * 2 | 1127,67*
>     anova _8pgf2a gruppi_ord uri_enz_creat_mg24h if sesso==2, continuous( uri_enz_creat_mg24h)
>     adjust uri_enz_creat_mg24h , by( gruppi_ord)
>
>     RECODE of |
>     gruppi | xb
>     ----------+-----------
>   *  * 0 | 1424,16**
>       1 | 1261,85
>     * 2 | 1237,97
>     *
>
>     *How is it possible ? The overall means are not between the two value of sex ! Do you think is it possible ?*
>
>  
>     Best Regards,
>     Rachele
>    
--
Rachele Capocchi
Agenzia Regionale Sanità Toscana
"U.O. Centro Statistico Elaborazione Dati"
Sede Operativa - viale Milton,7
50134 Firenze
Tel. 055-4624354
Fax. 055-4624345 
*
*   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/