2

I am trying to reprogram the data generating process from Haug (1996) which follows this equation:

enter image description here

Parameter a1 can take values (0,1); a2 is fixed at value 1 and their purpose is to set exogeneity or endegeneity. How can I implement the second equation into my program code?

Source: Haug, A. A. (1996): Tests for cointegration a Monte Carlo comparison. Journal of econometrics, 71(1-2), 89-115.

totnan
  • 29
  • 3
  • Hi. It's not clear to me what you mean by the second equation ? maybe it's not clear to others either. – mlofton Aug 18 '21 at 23:07
  • Under the second equation I mean "a1*yt + a2*xyt = et" – totnan Aug 20 '21 at 08:57
  • Hi: I don't know the answer but here's my understanding. You generate the $\epsilon_t$ and the $\phi_t$ using the equations in the middle. Then, assuming you know $\beta$, $a_1$ and $a_{2}$, you then have to generate $x_{1}$ or $y_{t}$. Then, given one of them, it's sraightforward to generate the other. But I'm not clear on how to generate $x_{1t}$ or $y_{t}$. But, once you have one of them, the other can be backed out using the first or second equation. – mlofton Aug 21 '21 at 00:05

0 Answers0