I have 7 variables: 1 dependent and 6 independent variable

3 of these independent variables affect 3 of the other independent variables (currency, interest rates, and revenues in respective currencies).

And these 6 variables again affect the dependent variable (total revenues).

Is there a way to use multivariate regression analysis to find how the 3 variables (currencies and interest rates) affect the 3 revenue streams?

  • 1
    $\begingroup$ I'm not sure I understand what you mean, but it sounds more like some sort of path analysis than multivariate regression $\endgroup$ – Peter Flom - Reinstate Monica Feb 27 '17 at 13:02
  • $\begingroup$ I am supposed to measure the exposures to a company's total revenues. They have three revenue streams with three different exposures. The task is to find their coefficients and then forecast into the short-term. $\endgroup$ – Mataunited17 Feb 27 '17 at 16:28
  • $\begingroup$ Your data seems to be time series. The most popular multivariate time series model is vector autoregression (VAR), also its special case -- the vector error correction (VEC) model. Check them out. $\endgroup$ – Richard Hardy Feb 27 '17 at 16:54
  • $\begingroup$ 1 dependent variable and 6 independent variables: the best approach is multiple regression and not multivariate regression- Kennedy Ekerikevwe $\endgroup$ – user158257 Apr 21 '17 at 11:46
  • $\begingroup$ @user158257 I understand why you would answer this way, due to how the first half of the question is formulated. However, you are off the mark: the second half of the question makes it clear it concerns three dependent variables and three independent variables. $\endgroup$ – whuber Apr 21 '17 at 13:34

Your Answer

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

Browse other questions tagged or ask your own question.