[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: saving a sample after a regression
At 02:47 PM 3/12/2007, william.miles wrote:
Consider using nestreg, e.g.
I am running regressions with several variables, and not all
data on all variables. I run a regression of Y on X, and use say 1,000
observations. Then I run a regression of Y on X and Z, and because not all
observations have Z, I only get a sample of 800 observations. Is there any
way to save the sample from the latter regression, so I can then run the
original regression of Y on only X, but using only the 800 observations that
include Z, without having to go throught the data by hand?
nestreg: reg y x z
This will first regress y on x and then y on x and z. It will use
listwise deletion, and for an added bonus it will give you
incremental f tests at the end testing the vars added at each stage.
Alternatively, consider something like
gen touse = !missing(y, x1, x2, x3, x4)
reg y x1 x2 x3 if touse
Or, yet another trick:
reg y x z
reg y x if e(sample)
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
* For searches and help try: