Question when having few data points

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

Ynwe
Posts: 22
Joined: Tue Dec 08, 2015 4:39 am

Question when having few data points

Postby Ynwe » Tue Dec 08, 2015 8:04 am

So I need data from 1980-2012, but the data for what I am looking for (poverty in Austria and % of religious people in Austria) only seems to be available all 10 years before the late 2000. so I may only have 1981 91 01 and and than some late 2010 data points. Can Eviews fill the rest data points using an estimator or something? and how useful would this be?

startz
Non-normality and collinearity are NOT problems!
Posts: 3798
Joined: Wed Sep 17, 2008 2:25 pm

Re: Question when having few data points

Postby startz » Tue Dec 08, 2015 9:12 am

Proc/Interpolate may do what you want. It is useful if you want a good guess as to the missing data. It may not be so useful if you subsequently want to use the data to estimate an equation, since the interpolated data is in fact made up.

Ynwe
Posts: 22
Joined: Tue Dec 08, 2015 4:39 am

Re: Question when having few data points

Postby Ynwe » Tue Dec 08, 2015 10:13 am

Proc/Interpolate may do what you want. It is useful if you want a good guess as to the missing data. It may not be so useful if you subsequently want to use the data to estimate an equation, since the interpolated data is in fact made up.
yes, I want to use the data than in my equation. lets say I do this, any it is significant at the 5% level, what should I consider doing or looking for if I want to state that my results are good?

startz
Non-normality and collinearity are NOT problems!
Posts: 3798
Joined: Wed Sep 17, 2008 2:25 pm

Re: Question when having few data points

Postby startz » Tue Dec 08, 2015 11:05 am

Try running with your real data and see if you get the same result.


Return to “Econometric Discussions”

Who is online

Users browsing this forum: No registered users and 2 guests