[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
RE: st: Outreg: sign of t-statistics
At 03:32 PM 6/7/2006, Alex Ogan wrote:
This post by Steve Stillman back on Sept. 14 2005 laid out the case
for outreg and for updating it to outreg2:
Can anyone comment on the relative merits of outreg2 and estout, for the
benefit of those who don't want to install and experiment with both?
As I understand it, it is basically ease of use versus power. My
typical table has columns for model 1, model 2, model 3, etc. I have
the coefficients, standard errors, and a few summary stats. With
outreg2, I can generate that table quickly and easily and save it in
Word format. Given that, to date, outreg2 has met my needs, I
haven't looked at estout very closely.
But, if your needs are more complicated than that, estout has
zillions of options. It also can be used with the companion packages
estadd and estadd_plus, which allow you to include additional
statistics. (But perhaps those routines could also be used with outreg2?)
I suppose if I were forced to use only one, I would go with estout
because of the power. But, it took me the better part of 5 or 10
minutes to figure out how to get outreg2 to generate the basic tables
I wanted, so it isn't like it requires a huge investment to check it out.
In any event, both are great programs! And I am grateful to the
authors for providing them. The fact that outreg continues to get
more downloads than either of them is mostly just due to inertia and
fame, I suspect. People see outreg mentioned somewhere so they
download it, without knowing better options are available.
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
* For searches and help try: