EViews.com

Generally because when serial correlation is ignored the reported standard errors are wrong. Adding AR(1) gives the correct standard errors. In addition, sometimes serial correlation indicates misspecification. so this means, that in the original output, the standard errors were wrong due to a AR t...

startz wrote:The fact that a variable is "insignificant" does not mean you should throw it out.

but why does the adding of an AR term suddenly render a variable insignificant?

hi trubador sorry shoudl have done that. I noticed someting while going over a topic http://forums.eviews.com/viewtopic.php?f=4&t=3212 I used the method described here by vmillias which startz says is actually bad. Why is that so? So I should use a Coefficient Variance decomposition test right, ...

Hey, In my output I have an obvious issue with autocorrelation. Durbin-Waston has a value of 1.1 and a Q-Statistic under Residual Diagnostics shows me pretty much that I have autocorrellation. So I add an AR (1) term. Now durbin watson goes up to 1.6, the Q-Statistic overall seems to be fine too now...

GDP_PER_CAPITA EDUC_PER LAW LIFE_EXPEC REL_PER URB_PER GDP_PER_CAPITA 1.000000 0.895168 0.956279 0.952616 -0.973835 0.807385 EDUC_PER 0.895168 1.000000 0.975186 0.977476 -0.948947 0.824475 LAW 0.956279 0.975186 1.000000 0.997357 -0.991417 0.853135 LIFE_EXPEC 0.952616 0.977476 0.997357 1.000000 -0.98...

Thank you, I confused H0 and HA

hello I have the following outputs http://i.imgur.com/9XaeGX0.png I have a problem: My first result is on the left. To test the three insigfnificant variables I should use a redundant variable test right? It tells me though to remove all 3! But I know from just reducing the model by hand, that life ...

whoops, this is what you get whenn you always minimize the command window. thank you very much!

EViews Gareth wrote:If you want the pre-1988 years to be NA, then yes, enter them as NA.

To create such a series you can use:

Code: Select all

series yrssince88 = @recode(@year>1987, @year-1988, na)


wait, never coded in Eviews. I go to object create a new object and call it time, where do I enter that code than?

Hey! I have a time series going from 1980-2013. One of the variables should have a starting point in 1988. Its basically a law change. So the variable should be "X years since Law Y was passed" How would I put that into eviews? Just leave he 1980-87 years as NA, and than the rest just begi...

is this a new feature in eviews 9? can remember seeing it in eviews 8

So I want to check if my equation has autocorrelation. So I type in AR(1) into the equation. But it also gives me a SIQMASQ variable out. Why does it do this? I remember in the past it didn't do this also the method is changed to a Method: ARMA Maximum Likelihood (OPG - BHHH) Can't I just use my OLS...

Hey I did a very simple output and got this http://i.imgur.com/eTy8c35.png I have a few questions: 1: the values, educ religion and urban are values between 0 and 1, life expec between 70-80ish and the GDP between 10k and 50k. Divorce rate is between 1-3 Do I need to change my variables around a bit...

and once again Eviews crashes and I lose everything. I love it