Insufficient number of observations

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

acemi
Posts: 46
Joined: Thu Jun 23, 2016 10:28 pm

Re: Insufficient number of observations

Postby acemi » Sat Nov 26, 2016 11:11 am

Dear Eviews Gareth,

all c's are coefficients to be estimated and independent variable "n" is a positive number for all data. How did you determine that this cannot be a positive log ? Doesnt eviews have to estimate itas such ? I am confused..
Sorry to be such a bother on this but would very much appreciate if you can elaborate some more.
Best regards,

log(c(5)+(1-c(2))*c(1)*n)

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 13305
Joined: Tue Sep 16, 2008 5:38 pm

Re: Insufficient number of observations

Postby EViews Gareth » Sat Nov 26, 2016 4:42 pm

Yes, it is estimating the C coefficients, but it requires starting values to do so. It uses whatever is currently in C as starting values. Currently you have zeros in C.
Follow us on Twitter @IHSEViews

acemi
Posts: 46
Joined: Thu Jun 23, 2016 10:28 pm

Re: Insufficient number of observations

Postby acemi » Thu Dec 01, 2016 5:12 am

Dear Gareth,
I want to confirm that since I have 5 coefficients in my model, it is enough to specify first 5 values in the C - coefficient vector.

Thnak you and regards

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 13305
Joined: Tue Sep 16, 2008 5:38 pm

Re: Insufficient number of observations

Postby EViews Gareth » Thu Dec 01, 2016 5:19 am

As long as you have used C(1) through C(5), yes.
Follow us on Twitter @IHSEViews

acemi
Posts: 46
Joined: Thu Jun 23, 2016 10:28 pm

Re: Insufficient number of observations

Postby acemi » Thu Dec 01, 2016 5:36 am

Dear Gareth,

I tried 0.1 (which has been mentioned as a safer value by Eviews Glenn at another post thread.) and 0.001 and 0.0001 for c(1) to c(5), but none of them worked I keep getting "Insufficient number of observations" upfront. I am very much stuck on this, should I be trying randomly and if so between which values can you give me a slightest clue ?
Many thanks in advance
regards

log(y) = (1/((1-c(2))*(1-c(3))-c(1)))*((1-exp(-c(1)*@trend))*c(2)*(1-c(3))*log(s)+(1-exp(-c(1)*@trend))*c(1)*log(l)+(1-exp(-c(1)*@trend))*c(4)*log(fi)+(1-exp(-c(1)*@trend))*log(c(5)+(1-c(2))*c(1)*n)+(1-exp(-c(1)*@trend))*c(2)*(1-c(3))*log((n+delta)+(c(1)*n))+(1-exp(-c(1)*@trend))*log(y(-1)))

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 13305
Joined: Tue Sep 16, 2008 5:38 pm

Re: Insufficient number of observations

Postby EViews Gareth » Thu Dec 01, 2016 5:38 am

Look at this term:

Code: Select all

log(c(5)+(1-c(2))*c(1)*n)


You need to find values of C(1), C(2) and C(5) that ensure this is positive for all the values of n.
Follow us on Twitter @IHSEViews

acemi
Posts: 46
Joined: Thu Jun 23, 2016 10:28 pm

Re: Insufficient number of observations

Postby acemi » Fri Dec 02, 2016 1:16 am

Dear Gareth,

I manually calculated expression within parenthesis with excel for c(1) to c(5) = 0,1 and all came out positive, thus ln() of expression can be calculated as well. Moreover I calculated all ln() expressions manually in excel as well.

Is there any other option which might be the cause of this error so that I can check it as well ? (I dont have any idea)
Thank you and Regards,

PS.I attached both excel and eviews files below. sheet "manual" has the calculation.
Attachments
Eviews deneme data.xlsx
(71.75 KiB) Downloaded 232 times
eviews deneme data.wf1
(25.9 KiB) Downloaded 185 times

acemi
Posts: 46
Joined: Thu Jun 23, 2016 10:28 pm

Re: Insufficient number of observations

Postby acemi » Mon Dec 19, 2016 1:02 am

Hello,

I was not able to make progress on this issue since. I am aware it became a nuisance to you but would appreciate any further guides, suggestions anything..

Best regards

EViews Gareth
Fe ddaethom, fe welon, fe amcangyfrifon
Posts: 13305
Joined: Tue Sep 16, 2008 5:38 pm

Re: Insufficient number of observations

Postby EViews Gareth » Mon Dec 19, 2016 9:04 am

The only suggestion I have is to provide different starting values until it works. Or re-formulate the expression into something less complicated.
Follow us on Twitter @IHSEViews


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 18 guests