[Gretl-users] Re: Allocation of instrumental variables

> From an econometric point of view, there is an ambiguity in the > original post that must be resolved before explaining how to do things > in gretl, as Alecos rightly pointed out. > > A common misconception in IV estimation is that a given instrument is > related to a given endogenous variable. This is by no means true in > general. Generally speaking, ALL instruments are used for ALL > endogenous variables. > > Having said this, it is perfectly possible to impose constraints in > the "first-stage" regression, for example by stipulating that some of > the instruments don't enter some of the equations. But in order to do > so, you can't rely on the plain IV estimator and you have to use a > different estimator (maximum likelihood, or possibly GMM). Jack is of course perfectly right, but I believe that for the actual estimation no other estimator than standard IV is wanted here. It seems to me that the real-world question is: "Hm, I believe Z1 and Z2 will be good instruments for X1, can I convince my audience that this is true?" And so one could present the pseudo-1st-stage just for X1, to check the fit and so on. But once this auxiliary regression shows satisfactory results (and maybe do the same thing for X2 as well), you just want run the full standard IV regression.