Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

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

st: suest for panel data?

From   Dimitrije Tišma <[email protected]>
To   [email protected]
Subject   st: suest for panel data?
Date   Tue, 24 Jul 2012 12:56:49 +0200

Dear all,

Using data from a household survey I am trying to figure out whether a
difference in a coefficient of a variable for two samples is
statistically significant (standard errors are adjusted by clustering
per indvidiual). I do estimation without clustering (and store the
estimation), but I do specify cluster option when performing the
-suest- command. However, something seems to go wrong as I get the
following error report after -suest- :

unable to generate scores for model X
suest requires that predict allow the score option

Can anyone help me with this? Is there an alternative to suest? Best,

*   For searches and help try:

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