Hi,
I've noticed that the sample seems to be adjusted when I try to solve a model using EViews from 2020 onwards.
I was wondering if you could provide me with more information on this adjustment procedure - why is it necessary, and how exactly does it work? I've also noticed that both endogenous variables and variables that are excluded and overridden with values from 2020 to 2021:4 get NA during this initial time period when the sample is adjusted.
Thomas
sample adjusted
Moderators: EViews Gareth, EViews Moderator
-
- EViews Developer
- Posts: 564
- Joined: Thu Apr 25, 2013 7:48 pm
Re: sample adjusted
Hello,
The model solution procedure adjusts the solution sample to ensure that all referenced variable lags/leads exist in the workfile. For example, imagine a quarterly workfile spanning 2000Q1 to 2020Q4. If the specified solution sample covered the full workfile, "2000Q1 2020Q4", but the smallest variable lag (most negative) in the model is -2, then the solution sample would be adjusted to "2000Q3 2020Q4" to account for the fact that lagged data in 1999Q3 and 1999Q4 isn't available. However, if the specified solution sample were instead "2010Q1 2020Q4" then no adjustment would be necessary since the lagged data is available.
You're correct to notice that the solution series are filled with NAs for observations that represent the difference between the specified solution sample and the adjusted solution sample.
The model solution procedure adjusts the solution sample to ensure that all referenced variable lags/leads exist in the workfile. For example, imagine a quarterly workfile spanning 2000Q1 to 2020Q4. If the specified solution sample covered the full workfile, "2000Q1 2020Q4", but the smallest variable lag (most negative) in the model is -2, then the solution sample would be adjusted to "2000Q3 2020Q4" to account for the fact that lagged data in 1999Q3 and 1999Q4 isn't available. However, if the specified solution sample were instead "2010Q1 2020Q4" then no adjustment would be necessary since the lagged data is available.
You're correct to notice that the solution series are filled with NAs for observations that represent the difference between the specified solution sample and the adjusted solution sample.
-
- Posts: 540
- Joined: Fri Apr 15, 2011 5:35 am
Re: sample adjusted
Thank you for the explanation, Matt.
t
t
Who is online
Users browsing this forum: No registered users and 3 guests