BPTest (Breusch-Pagan LM test for random effects)
Moderators: EViews Gareth, EViews Moderator, EViews Esther
Re: BPTest (Breusch-Pagan LM test for random effects)
additional information, i used eviews 7, add in lm test already download, equation: group01
thanks
thanks
-
- EViews Developer
- Posts: 149
- Joined: Fri Sep 03, 2010 7:57 am
Re: BPTest (Breusch-Pagan LM test for random effects)
The BPTest addin will work from the equation object. Please specify your equation first and then run this addin.
Re: BPTest (Breusch-Pagan LM test for random effects)
Dear All,
Why does this test so long? It takes up my processor and memory but crashes in between without displaying results. I have test it with a very small data and it works but my panel data is 142 countries, 17 years, 6 variables. As I write this, Eviews is still processing and displaying not responding. My Eviews is 7.1, and computer is Core i5, 64bit Windows 7 and 8 GB Ram, how much more does it require?
Why does this test so long? It takes up my processor and memory but crashes in between without displaying results. I have test it with a very small data and it works but my panel data is 142 countries, 17 years, 6 variables. As I write this, Eviews is still processing and displaying not responding. My Eviews is 7.1, and computer is Core i5, 64bit Windows 7 and 8 GB Ram, how much more does it require?
-
- Non-normality and collinearity are NOT problems!
- Posts: 3775
- Joined: Wed Sep 17, 2008 2:25 pm
Re: BPTest (Breusch-Pagan LM test for random effects)
It couldn't hurt to apply the free updates to bring your version uptodate.
Re: BPTest (Breusch-Pagan LM test for random effects)
Great... It works perfectly after updating to Eviews 7.2. Thanks alot and keep improving this remarkable software.
-
- Posts: 1
- Joined: Tue Aug 21, 2012 1:31 am
Re: BPTest (Breusch-Pagan LM test for random effects)
Hello!
I have a fixed effects model using panel data. I want to test if the residuals are normally distributed and that they are not autocorrelated. I have not found a test for this when using a fixed effects model.
Any ideas? And if there is not a function to do this in the program, is there any way to do this manually?
Sincerely
Stephanie
I have a fixed effects model using panel data. I want to test if the residuals are normally distributed and that they are not autocorrelated. I have not found a test for this when using a fixed effects model.
Any ideas? And if there is not a function to do this in the program, is there any way to do this manually?
Sincerely
Stephanie
Breusch-Pagan LM test for random effects
Hi,
when I run the Breusch-Pagan add-in for the object "Equation: MQOAGRUPADO" in the attached file I receive the following message:
Matrix or vector given non positive dimension in “MATRIX(0,5) _D1T01”
Could you help me with this problem?
Thanks,
Moises
when I run the Breusch-Pagan add-in for the object "Equation: MQOAGRUPADO" in the attached file I receive the following message:
Matrix or vector given non positive dimension in “MATRIX(0,5) _D1T01”
Could you help me with this problem?
Thanks,
Moises
- Attachments
-
- tabela dados brics_forum.wf1
- (54.9 KiB) Downloaded 946 times
-
- EViews Developer
- Posts: 149
- Joined: Fri Sep 03, 2010 7:57 am
Re: BPTest (Breusch-Pagan LM test for random effects)
Please reinstall this addin and do the BP-test again.
Re: BPTest (Breusch-Pagan LM test for random effects)
Thank you. Now it works.
-
- Posts: 2
- Joined: Fri May 23, 2014 2:22 am
Re: BPTest (Breusch-Pagan LM test for random effects)
I have a question concerning the add-in BPTest. I specified my equation but then when I want click on: Add-ins--> Breusch Pagan Random Effect LM Test, it gives an error saying: Procedure can only be run from Equations estimated by list. What does it mean? Thanks in advance!
Edit: I use Eviews 8
Edit: I use Eviews 8
-
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13319
- Joined: Tue Sep 16, 2008 5:38 pm
Re: BPTest (Breusch-Pagan LM test for random effects)
You must specify your equation as a list of variables, not as an expression (e.g. Y X1 X2 C, rather than Y=C(1)*C(2)*X1)
Follow us on Twitter @IHSEViews
-
- Posts: 2
- Joined: Fri May 23, 2014 2:22 am
Re: BPTest (Breusch-Pagan LM test for random effects)
Ok thanks now it works. However when I do the test I get an error identical to what other forum members also have. It says: 'Out of memory in .....' Does it mean that the memory problem is also not fixed for eviews 8 and that I should use older versions? If so, which version do you suggest then?
-
- EViews Developer
- Posts: 149
- Joined: Fri Sep 03, 2010 7:57 am
Re: BPTest (Breusch-Pagan LM test for random effects)
This implies that your dataset is too large so that the SLM test cannot be performed. I would suggest to exclude the SLM test from the list for now.
I will figure out how to deal with the large dataset problem.
I will figure out how to deal with the large dataset problem.
Re: BPTest (Breusch-Pagan LM test for random effects)
EViews Gareth wrote:You must specify your equation as a list of variables, not as an expression (e.g. Y X1 X2 C, rather than Y=C(1)*C(2)*X1)
Could you tell me, please, where I should write such expression as Y=C(1)*C(2)*X1 for getting appropriate results of BPTest?
-
- Posts: 1
- Joined: Mon Aug 30, 2021 1:38 pm
Re: BPTest (Breusch-Pagan LM test for random effects)
Dear All,
I am running a panel data model with EViews 10. However, when I want to run a Breusch-Pagan LM test for random effects, the software tells me "not available with this estimation method". But I am using normal pooled OLS to test for it without any random effect already being defined. What is wrong?
Thanks for any hint.
I am running a panel data model with EViews 10. However, when I want to run a Breusch-Pagan LM test for random effects, the software tells me "not available with this estimation method". But I am using normal pooled OLS to test for it without any random effect already being defined. What is wrong?
Thanks for any hint.
Who is online
Users browsing this forum: No registered users and 35 guests