Time series data

[Steve Mikos]

Hi everyone, I am new to STATA so I am sorry if this is a silly question. I am researching oil price shocks and was hoping that oil price shocks are followed by a decrease in real GDP. My regression

var d.RealGDP Priceofoilbarrel, lags(1/4) exog(ConsumerConfidence RealWagesWeekly Interestratediscountrate InflationRate REERExchnageRate)

That is what my model looks like. I have data from 1965 until 2010 and I didn't get the results I wanted as I have an issue with simultaneity. Do I need to run separate regressions for all of the oil price shocks. So I would do one regression for the oil price shock in the 70s and use maybe five years before and after the shock and then run a separate one from the price shock in the 2000s? Thank you for your help!

[Phil Bromiley]

You didn't get a quick response. You'll increase your chances of a useful response by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output (fixed spacing fonts help), and sample data using dataex.

How would you know that your parameters reflect simultaneity rather than just being the right parameters (i.e., your priors might be wrong)? I also wonder if differencing the dv makes sense - you're explaining changes in the change. If you legitimately believe the effects changed over time, then running on part of the sample makes sense.

However, I don't do var, but it sure looks like you have a lot of parameters relative to your sample size.