Re: st: first differences and growth rates

[Merijn Groenenboom <m.groenenboom@students.uu.nl>]

Thanks for your replay.
However, since I will put all the results of the variables in the same
table, I would like to know how I can compare the growth rates with
the first differences of the other variables. Are the results
comparable? Otherwise I have to remove the variable with the growth
rates out of the regression

MerijnG

2011/8/5 Billy Schwartz <wkschwartz@gmail.com>:
> You transform to first differences when you think there's serial
> correlation. If the growth rate could be serially correlated then
> you'd have to transform it too.
>
>
> On Fri, Aug 5, 2011 at 8:37 AM, Merijn Groenenboom
> <m.groenenboom@students.uu.nl> wrote:
>>
>> Dear statalisters,
>>
>> In my regression I use a lot of economic variables. These variables
>> are absolute numbers. In my regression I use first differences.
>> However one variables includes growth rates instead of absolute
>> numbers, therefore I think i do not need to transform these variable
>> to first differences.
>> So in that case I all variables are transformed into first
>> differences, except the variable with the growth rate. Is this
>> correct?
>>
>> Actually I doubt whether this is correct, since the results in Stata
>> looks a little bit strange.
>> Does anybody knows, what I can do with this variable? Or can't I use it?
>>
>> I hope somebody can help me!
>>
>> Thanks in advance,
>>
>> MerijnG
>> *
>> *   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/
>

*
*   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/