Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.

# RE: st: How to Convert Nominal GDP to Real GDP

 From "Lovisa Persson" To Subject RE: st: How to Convert Nominal GDP to Real GDP Date Fri, 21 Sep 2012 11:24:52 +0200

```What I mean by cpi2001 etc is that you replace this with the actual values
from your variable CPI from the year in question.

If your variable CPI is in rate of change and the value for 2001 is 0.021
and the value for 2002 is 0.025
Then you will have

Generate index=1
replace index=1.021 if year==2001
replace index=(1.021)*(1.025) if year==2002

The index variable will then be:
1                        (at base year 2000)
1.021               (2001)
1.046525        (2002)

Etc...

This is what I would do, but there is maybe a more flashy way to do it.

But if your CPI variable is already in index form, related to year 2000,
there is no need....

Lovisa

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Nick Cox
Sent: den 21 september 2012 11:10
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: How to Convert Nominal GDP to Real GDP

I think you need to explain where the variables -cpi2001-, -cpi2002-, etc.

I guess that you are thinking in terms of subscripts, but writing otherwise.

Perhaps you mean something more like

gen index = 1
replace index = index[_n-1] * (1 + cpi) if _n > 1

Nick

wrote:

> Is your variable CPI an index with value 100 or 1 at base year 2000?
>
> In that case you do what Lukas recommended.
>
> If the CPI is in rate of change from year to year,  you first need to
> generate a price index variable with base year 2000 , and THEN you do
> what the previous responder told you.
>
> generate index=1
> replace index=1+cpi if year==2001
>
> and then you impute the rest of the values...
>
> replace index=(cpi2001+1)*(cpi2002+1) if year==2002 replace index=
> (cpi2001+1)*(cpi2002+1)* (cpi2003+1) if year==2003
>
> You impute the actual values of the CPI in rate of change...
>
> Now you have an index which you can use to generate your Real GDP
variable.
> Using your nominal GDP variable and divide it by the index just as
> described below.

Lukas Borkowski

> the answer would be -gen realgdp = gdp/cpi-

Shawn Meyer:

>> I am new user to Stata. I am requesting if you could teach me
>> something
> which sounds very simple. I have a panel data on GDP of over 100
> countries for 10 years; from 2000 to 2010 with four variables id, year,
GDP and CPI.
> Now I want to generate a new variable REALGDP so that I get real GDP
> for each country (id), with 2000 as the base year. Could you please
> help me how to do it?
*
*   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/
```