Nikos--
read -help macro- and -help matrix- and linked help files, then check
out -help foreach- and -help file-. -help program- can help you
automate your tables. Here is an example of what you might want:
clear
sysuse auto
reg pr mpg wei for
mat b1=e(b)
mat v1=e(V)
local df1=e(df_r)
sysuse cancer
reg died age
mat b2=e(b)
mat v2=e(V)
local df2=e(df_r)
local order "age mpg weight foreign _cons"
file close _all
file open t using /t.txt, write replace
file write t _tab "auto" _tab "cancer"
file write t _n _tab "(price)" _tab "(died)"
foreach v of local order {
file write t _n "`v'"
forv i=1/2 {
file write t _tab
local b=b`i'[1,colnumb(b`i',"`v'")]
local plus=cond(`b'>0,"+","-")
if `b'<. file write t "`plus'"
local s=sqrt(v`i'[colnumb(b`i',"`v'"),colnumb(b`i',"`v'")])
local t= b`i'[1,colnumb(b`i',"`v'")]/`s'
local p=ttail(`t',`df`i'')
if `b'<. &(`t'==. | `p'<.05) file write t "`plus'"
}
}
file close _all
type /t.txt
On 3/8/07, Sergiy Radyakin <[email protected]> wrote:
Method 1 involves headacke, and is not readily automated
Method 2 requires some more programming effort but simultaneously gives you
full control.
Method 3:
1) wait for other suggestions...
----- Original Message -----
From: "Nikolaos Kanellopoulos" <[email protected]>
> Dear all,
>
> I am estimating the same model in different datasets (the names of the
> variables used are the same in all datasets).
>
> I want to create a table with the sign of estimated coefficients and if
> possible have a double sign if the coefficient is significant.
*
* 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/
