wyantjs Wrote: ------------------------------------------------------- > maratikus Wrote: > -------------------------------------------------- > ----- > > wyantjs Wrote: > > > -------------------------------------------------- > > > ----- > > > C has the correct numbers, it is just that > they > > > are reversed. You should be regressing > (1.885, > > > .3025…) on (.3025, .64…) instead of > > the > > > way they have it in the question. > > > > that’s wrong. you should use 1.885 to predict > > .3025, .3025 to predict .64 -> you always use > past > > values to predict future values. > > I love how you disagree with me, and are typically > incorrect. The goal is to test if the variance of > the residuals is conditional upon the observed > values. Therefore, you should regress the SQUARED > RESIDUALS ON THE INDEPENDENT VARIABLES. I was incorrect in choosing A because i didn’t realize that they were actually talking about this particular data series. A provides a data series of squared residuals that can be used in another AR model. As Joey said: for ARCH you are regressing squared residuals on the lagged squared residuals. by previous values I meant lagged squared residual, present value - current squared residual. wyantjs, you have a problem and unfortunately I can’t help you.
That might be the worst excuse I have ever heard. I don’t need your help son. I have a MFE, and am very well aware of the mathematics behind this.
C’mon guys. We support each other here. This is about both of you passing the exam and doing well.
You guys are really math geniuses. I think we should add some elements of chemistry and physics besides math into finance so it will become science.
I reckon we should get some history in there. Then when we make the same mistakes they did 30 years ago, at least we’ll be able to do them better.
Tell me about it. Baghdad feels like the days before Tet to me.
MA did not see that in the LOS. either way, i am going to need to do some real work on this!!
JoeyDVivre Wrote: ------------------------------------------------------- > As dinesh pointed out above, you can imagine other > kinds of more plain vanilla heteroscedasticity > where the variance of the error depends on one or > more independent variables or the predicted values > and then you’re back in Breusch-Pagan land. That > would be wyantjs comment "The CFAI book clearly > states on page 296 “Regress the squared residuals > from the estimated regression equation on the > independent variables in the regression.” That’s > a test for a different kind of heteroscedasticity > (that word just means “different variances” and > the differences can come from anything including > stuff not modelled). Also, the order given in C > seems to be right. > So once we have the model prepared and tested for significance using individual t-tests for coefficients or using F-test for the overall model and we get a neat R-squared/ Adjusted-R-squared, we are not yet done!! We need to check if the residuals error terms are having constant variance (i.e. test for homoskedasticity). So we use Breusch-Pagan-test to check for conditional heteroskedasticity by taking the [(no-of-observation)*( coefficient of determination)] as the t(stat-calculated) and check it against the Chi-Squared table value where DoF = no of independent variable. It’s only when we reject the null (of Conditional heteroskedasticity) we are safe to assume the model is good for use. It we fail to reject the null, then we conclude all our inferences were inappropriate due to the standard errors/ test statistcs being wrongly estimated and probably of Type-I error increases. Then on, we try to compute the Robust standard errors or go for the Generalized leased squares and assume that the derived regression equation, no longer has the heteroskedasticity issue. I tried a couple of problems for this and knocked them all down, so feel confident now. Thnx Joey for your help!!
Later. I’ve been drinking beer and not catching any fish. Not freaking one.