EViews.com

Is there any reason why you can't use the information criteria to pick lag length? I would think the AIC or BIC would work fine.

Alpha and beta have to sum to less than one for the GARCH model to be stationary. You can't really report results with alpha+beta>1, they don't mean much except that your model seems misspecified. An integrated GARCH is such alpha+beta sum to exactly one (not greater than one). Two suggestions: try ...

This looks similar to a GARCH in mean (GARCHM) but I suppose you have to write out the likelihood to estimate this in eviews.

The idea behind a VAR is that the lags of the endogenous variables affect each other (lags of x, y and z affect each other, dpending on the identifying assumptions you use). You can certainly do what the VAR that you're describing. It would not be a VAR per se but a near VAR (where some coefficients...

You would do ARMA modelling similarly to the way you'd do it with data at other frequencies. Box-Jenkins identification (using autocorrelation and partial autocorrelations) to select the optimal ARMA model and then you estimate the chosen model.There's no specific code for that in eviews. You have t...

The lag length of the VAR/VECM has nothing to do with the number of cointegrating relationships. If think you're confusing optimal lag length with the number of cointegrating relationships. Variables can't be differenced and have a cointegrating relatiohsip. You would wipe out the cointegrating rela...

I've never heard on non-stationary asset returns. You must be interpreting/performing the ADF in the wrong way. Returns are just like first differincing. They would make the price series stationary. Log differencing the price series is another option (you get continuously compounded returns). It is ...

You should preferably run a regression with both inflation and the regressor being I(0) (stationary). Is there a problem with first differencing inflation to get it to be I(0)?

Worst case scenario is to have both inflation and your regressor as I(1). You'd be running "spurious" regressions.

Not necessarily. It just means that the population errors are quite far from being normally distributed.

I don't think you really understand what a unit root test is. The unit root test is not about the intercept being stationary or not. It is about the series itself (in levels) being stationary or not. The Dickey and Fuller regressions (I assume this is what you use) used to obtain the test may or may...

First, estimate the regerssion without the coefficient restriction imposed (not the way you show in your screen shot). That is, include beds and baths seperately as regressors. Then, after estimating the regression, go to coefficient restrictions, Wald test, and input your restiction as C(3)+C(4)=-2...

GARCH and ARCH models are designed to capture certain features of asset price volatility. So, if I understand your question correctly, you may use a multivariate GARCH model to examine whether copper price volatility and the volatility of stock price you're interested affect each other (this is call...

Thanks rpn4 for clarifying this. I had a similar question regarding the warning message of singularity in SSpace estimation. I'm also only interested in obtaining state series. Can you please calirify how did you set (or change) the initial condition values ?

Hi, I am trying to obtain the impulse response functions (graph) of the endogenous variables of a vector autoregression to a shock in an exogenous variable. I can't seem to figure out a way to do it. Suppose I have a VAR x(t) = c + a1*x(t-1)+b1*y(t-1)+c1*z(t-1)+e1(t) y(t) = d + a2*x(t-1)+ b2*y(t-1) ...