My economic analysis uses OLS with cross-sectional annual data.

The dependent variables are defined as x/y where x is a variable (such as trade, debt etc.) and y is real GDP.

What if, instead of using real GDP to use nominal? Is it going to dramtically affect my results? Are there any way to overcome this problem without changing the variables?


Going from real to nominal will cause you to lose out on a lot of the legitimacy of your (probably intended) theory, because many of the changes in nominal gdp are not production-related, they are inflation-related.

Note that GDP and other macro variables are likely cointegrated. This is going to represent a problem if you are trying to publish or draw seriously meaningful results. However, for .... messing around or student work, I encourage you both continue what you are doing and investigate the obstacles that you are ignoring away for now. Good luck!


  • $\begingroup$ Thank you very much about your answer. It is about my dissertation and i am thinking seriously if i have to change the data and start again. $\endgroup$ – Ant Apr 4 '15 at 13:39
  • 2
    $\begingroup$ @Antonis Normally, you'd begin with theory and collect the data that corresponds closely to the theoretical variables, so in terms of methodology, you, arguably, have one foot ahead of the other. For example, there are contexts when you do want nominal data - e.g. money wages for original Philips Curve - and others when you want real data - e.g. to control for the effects of inflation. It depends on the question you're trying to answer or the theory that you're trying to test. Use economic theory as your guide. $\endgroup$ – Graeme Walsh Apr 4 '15 at 19:16

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.