dfbeta
The measure that measures how much impact each observation has on a particular predictor is DFBETAs The DFBETA for a predictor and for a particular observation is the difference between the regression coefficient calculated for all of the data and the regression coefficient calculated with the observation deleted, scaled by the standard error calculated with the observation deleted. (from here).
The dfbeta
command will calculate one, more than one, or all of the DFBETAs after running a regression.
predict
can do this as well but dfbeta
will calculate all the DFBETAs and generate
a new variable for each requested beta, named automatically. The new names begin with the letters DF.
The command itself is simple enough. Simply run a regression, then type dfbeta [indep var] [indepvar2] [indepvarN]
you can specify as many independent variables as desired.