Hi Dimitri,
Thanks for help,
i knew that way that you have suggested but in fact my case is a little bit
complicated than this,
therefore, i am writing a better explanation now,
my model is trying to see the effect of eco-innovative industries on total
output, thats why i am trying to estimate by-industry regression:
the model is
lnQ~lnC+lnM+lnL+lnE+eco_inno+inno+(sum)ind_3d
capital,material expendtrs, #labor, energy expendtrs, eco-innovation
expenditures and innovation expenditures
and i have in my disposal the 3-digit industry codes where total number of them
are 99 ( not all of them belong to the same industry)
so in order to be able to do by-industry regression i need to create 3-digit
dummies for every different industry group
for example for the 1st group, from 111 to 119 this will be the 1st model to
estimate
then from 131 to 139#another model
then from 141 to 149#another model
so on so forth...
so at the end my aim is to compare the effect of eco-innovations on for these
industry groups.
so if i apply the way you have suggested it will take into account all the
3-digit industries which is not i want.
in fact i know that people create this kind of dummies by using loop since there
are many dummies to create, but i dont know how to do it.
i hope i could be more explicit now, and you could help me more at this time.
Thank you for your help in advance
--------------------------
Serdal,
I think what David is saying: just take those 2 variables you have and
specify them as factors. Assuming your data frame is called "MyData":
MyData$Ind_1<-as.factor(MyData$Ind_1)
MyData$Ind_2<-as.factor(MyData$Ind_2)
This way R will know they are not numeric variables but categorical
variables. Then, when you do analyses using those variables, R will
treat them as such and will build dummies "automatically" (e.g., if
you use regression, etc.).
Actually - it'd be nice to know what you are building your dummies for.
Dimitri
On Fri, Apr 23, 2010 at 11:34 AM, David Winsemius
<dwinsemius@comcast.net> wrote:>
> On Apr 23, 2010, at 11:26 AM, serdal ozusaglam wrote:
>
>>
>> Dear R users,
>>
>> I have a simple question (probably) but i couldnt how to find a
solution
>> for that.
>>
>> i am using 2 digit industry codes and 3 digit industry codes for my
model,
>> and i need to create dummies for the industries. The case is simple for
the
>> 2-digit industries since there are not that mcuh of them, so i am
creating
>> my dummies as following
>> ind_2da<-(ind_2d==11)#for the 11th industry
>> ind_2dc<-(ind_2d==12)#for the 12th industry and so on so forth ...
then i
>> directly put the dummy into the regression which works well.
>>
>> but creating dummies for the 3-digit is rather complicated since there
are
>> alot of sub-industries, for example:111,112,113...119 and this is just
for
>> the 11th industry
>> so when i consider the codes continues till 40, it would be exhausting
to
>> do it by hand.
>>
>> so i was looking for the loop commands to do it faster but since i am a
>> newbie i got lost in it.
>>
>> so is there some one who can help me for this problem?
>
> Don't use dummies.
>
> ?factor
>
>>
> --
>
> David Winsemius, MD
> West Hartford, CT
_________________________________________________________________
Yeni Windows 7: Size en uygun bilgisayarı bulun. Daha fazla bilgi edinin.
http://windows.microsoft.com/shop
[[alternative HTML version deleted]]