Disturbance term

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

rickyyml
Posts: 16
Joined: Tue Nov 05, 2013 1:58 am

Disturbance term

Postby rickyyml » Sat Nov 23, 2013 6:10 am

Dear All,

I am very green with EViews, and hope that you would offer me a helping hand.

Now I am practicing how to evaluate Calendar Effect by reproduce some calculation in literature.

I found one literature as attached and tried to calculate descriptive statistics for day of the week (Table 1) and month of the year (Table 4), it is done, no problem.

When I tried to do Linear Regression Aanalysis for day of the week effect, I make a equation "day_of_the_week" as below:

equation ls return mon tue wed thu fri

But the result is totally difference with the literature, then I go though the literature again, I found a equation on the beginning of page 3 with a "Vit", it is said that "Vit is the disturbance term", but I cannot find this term in EViews manual, and really don't know what is it, and I believe that it is the main cause of the difference.

Would you please advise how can I modify my equation so that I can get the same result as the literature?

If it is convenience, please kindly explain what is "Disturbance term".

Thank you in advance.
Attachments
bse sensex.wf1
(251.29 KiB) Downloaded 256 times
Literature.pdf
(136.8 KiB) Downloaded 362 times

startz
Non-normality and collinearity are NOT problems!
Posts: 3797
Joined: Wed Sep 17, 2008 2:25 pm

Re: Disturbance term

Postby startz » Sat Nov 23, 2013 8:07 am

The disturbance term, or error, is the part of the equation left over after your explanatory variables. It's not something you include in your equation. In EViews, the estimated disturbance term--called the residuals--is put into the series RESID after you estimate an equation.

rickyyml
Posts: 16
Joined: Tue Nov 05, 2013 1:58 am

Re: Disturbance term

Postby rickyyml » Sat Nov 23, 2013 11:42 pm

Hello, Startz

Thank you for your explanation regarding disturbance term.

Would you please advise how should I form the equation as well? I really have no idea why my result is totally difference with that of the literature.

It is extremely important for me, as I need to confirm the equation and use it on our group project. We are in hurry.

Thank you in advance.

ALL EXPERTS, PLEASE KINDLY HELP ME IF YOU COULD

startz
Non-normality and collinearity are NOT problems!
Posts: 3797
Joined: Wed Sep 17, 2008 2:25 pm

Re: Disturbance term

Postby startz » Sun Nov 24, 2013 8:48 am

Your results match the results in the paper exactly.

rickyyml
Posts: 16
Joined: Tue Nov 05, 2013 1:58 am

Re: Disturbance term

Postby rickyyml » Sun Nov 24, 2013 6:20 pm

Dear Startz

Really? Would you please explain to me how to generate the result for Table 2 & 3, I need it urgently.

As I don't know at all how to do it.

Thank you in advance.

startz
Non-normality and collinearity are NOT problems!
Posts: 3797
Joined: Wed Sep 17, 2008 2:25 pm

Re: Disturbance term

Postby startz » Sun Nov 24, 2013 6:47 pm

I suspect your instructor is hoping you will do the project, that way you'll learn more about EViews and about econometrics.

rickyyml
Posts: 16
Joined: Tue Nov 05, 2013 1:58 am

Re: Disturbance term

Postby rickyyml » Sun Nov 24, 2013 7:29 pm

My difficulty is that, our instructor didn't teach us how to use EViews any, but ask us to do the project with EViews.

I have prepared the workfile by reference to manual and some help from this forums up to now. I am willing the learn but the deadline of the project don't wait for me familiar with EViews.


Return to “Econometric Discussions”

Who is online

Users browsing this forum: No registered users and 2 guests