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

# st: RE: new explanatory variable in a loop

 From Nick Cox To "'statalist@hsphsun2.harvard.edu'" Subject st: RE: new explanatory variable in a loop Date Tue, 7 Dec 2010 18:47:07 +0000

```Yes, you _can_ do that. The central line would become

quietly regress liq `X' d`i' if isin2==`i'

However, if each dummy is 1 if and only if the identifier is that named, then the dummy is identically 1 and no purpose is served thereby. Thus if -d3- is 1 if and only if -isin2- is 3, then your variable is just a constant.

Nick
n.j.cox@durham.ac.uk

Rodrigo Briceño

Hello again Stata listers. I am running several regressions (stata
9.2, windows XP) that contains a set of dummies (each dummy is defined
as a "d" plus the identification number of the bond considered. So for
id3, the dummy is d3, and so on. I made the following loop (this is a
shortened version; the original include tests and exporting
coefficients using estimates store and estout):

loc X = "sap liqmk m2-m12 mes pprom"
local isin "3 4 247 1 5 6"
foreach i of local isin	{
quietly regress liq `X' if isin2==`i'
}

My question to the list is: can I include something like d`i'  as a
new explanatory variable? What I need is that each regression include
its corresponding dummy, so I can do the process automatically instead
of typing individual commands:

regress liq sap liqmk m2-m12 mes pprom d3 if isin2==3
regress liq sap liqmk m2-m12 mes pprom d4 if isin2==4

THanks

--
Rodrigo Briceño
Economist
rjbriceno@gmail.com
MSN: jbric98@hotmail.com
SKYPE: rbriceno1087

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
```