Forecast graphic treatment of panel data
by Brian Revell
There is an irritation in using the Forecast Function in Analysis in that
it treats Panel data as a continuum between adjacent panel units in
plotting by observation number sequence. So as illustrated below, there are
21 annual observations in Panel 1 ending in 2021. However the forecast
funtion treats this as as a observation continuum from 1:21 to 2:01(year
2001) and plots an irritaing line between1:21 and 2:01......and similarly
between all the adjacent 10 Panel Units. Is there anyway to suppress this
joining line, as the forecast graph plots beautiful CI shaded areas.
The workaround is to transfer the data to Excel -but that does not provided
a shaded 95% CI -which is clearly more elegan -only the ability to plot the
Upper and lower CI bounds as lines..
The Graph function on the other hand will show model fitted and actual
values by Panel Unit number, but no confidence intervals!
Brian
1:20 6.963190 6.860621 0.283066 6.301620 - 7.419622
1*:21 6.729824 6.452257 0.284134 5.891148 - 7.013367*
2:01 6.952729
2:02 5.905362
Perhaps an option in the graphics GUI to plot the forecasts for each panel
by Panel numbered units might remove the problem.?
[image: Capture.JPG]
Brian J Revell
Professor Emeritus (Agricultural Economics)
Harper Adams University UK
Current Chair of Defra Economic ADvisory Panel
Former President Agricultural Economics Society
Tel: home 01952 728153 Mobile 07976 538712
Address: Orchard Croft, Vineyard Rd, Homer, Much Wenlock TF!3 6NG
Alt. Email bjrevell(a)harper-adams.ac.uk
1 month, 3 weeks
some panel work we may want to do
by Riccardo (Jack) Lucchetti
OK, this message is meant to summarise a few things we discussed in
today's meeting for the benefit of Artur and Sven and also, so that we
don't forget.
The starting point was B. Revell's message on out-of-sample forecasting
in panel datasets, which spurred a discussion on several different
points (all panel-related):
* out-of sample forecasting for panel estimators _in the time dimension_
may be tricky for FE and/or dynamic models, so maybe we could start from
providing this facility for static models estimated with random effects,
and proceed from there.
* forecasting _a unit_ may pose different problems. Again, this should
not be a problem if the estimator is RE (and the model is static); what
we should do if the estimator is FE is less clear and we may want to put
this aside for the moment.
* related to out-of-sample forecasting is the issue of extending the
"dataset addobs" command to panel datasets. At present, this works by
appending empty units, provided the parameter is an integer multiple of
$pd, but it may be interesting to provide a way to add time periods. It
could be nice to make this the object of a collective coding session
next week. This would also have the benefit of illustrating some
characteristics of the DATASET struct, that appears pretty much
everywhere in libgretl.
* we may provide a new option to the panel command to have CRE
estimator, which is basically RE with cross-sectional means added and
returns the FE estimator for time-varying regressors. I find it of some
pedagogical value (J. Wooldridge is quite a fan), and besides, it
implies very little extra computational effort from what we do already.
In fact, I'm providing an example in my book that the attached script
illustrates.
-------------------------------------------------------
Riccardo (Jack) Lucchetti
Dipartimento di Scienze Economiche e Sociali (DiSES)
Università Politecnica delle Marche
(formerly known as Università di Ancona)
r.lucchetti(a)univpm.it
http://www2.econ.univpm.it/servizi/hpp/lucchetti
-------------------------------------------------------
1 month, 3 weeks
side-by-side time series to panel conversion greyed out
by Sven Schreiber
Hi all,
I'm having problems with the attached dataset, which holds annual
regional GDP values for the German federal states (plus the German
total). This is in time series format but I'd like to convert it to a
panel structure with the relatively recent GUI feature of using several
"side-by-side" time series. I have used this feature successfully in the
past, but with this dataset the relevant option in the dialog following
the choice of Data - Dataset structure - interpret as panel is not
accessible, greyed out.
When I don't have the time trend variable in the dataset, gretl even
complains that the dataset cannot be turned into a panel at all.
What's happening here? I guess I can work around this problem by using
the script commands from section 4.5 of the guide (haven't tried yet),
but that's suboptimal.
thanks
sven
2 months
function package for weighted instrumental-variable (IV) estimation
by Sven Schreiber
Hello everybody,
quite a while ago there was a question here on this list on how to run a
IV/TSLS regression with weighted observations. As a response to that
question, some hansl scripting code was posted.
Recently I turned that code into a contributed function package named
"weightedIV", which is now available on the package server as usual, so
installable from within the gretl program. As with every function
package, documentation and a sample script are included. The package
should also be usable in a GUI-dialog-oriented way.
If you have any comments, feedback, or bug reports about the package,
you're welcome to post them here.
thanks
sven
2 months
Panel data
by Brian Revell
Hi Sven
Many thanks. You have understood my need. I'll try your solution. If it
works it saves me butchering the original xls panel datafile and then
uploading it with 10 panel units.
Wrt the LSDV fixed effects panel model test result for intercepts. It is
helpful up to a point. However, if equal intercepts are rejected, does one
resort to OLS pooled data with DVs to see which differ as this is normally
a matter of interest. I can see no way from the LSDV option itself to
uncover the panel unit dummies relative to the estimated value of the
constant.
On Tue, 6 Feb 2024, 15:45 Sven S., <svetosch(a)users.sourceforge.net> wrote:
> Brian, you're replying to a ticket that has been closed for over two
> years, and the topic is unrelated. If the problem persists after my reply,
> please re-post your question (or follow-ups) on the mailing list.
> Having said that, you would have to choose Sample/Restrict by condition,
> and then enter an expression like "unit != 6 && unit != 8" (without the
> quotes). If the series "unit" doesn't exist yet, create it with "Add/Panel
> group index" first (or similar wording).
> Whether that qualifies as a "simple way", I don't know.
> ------------------------------
>
> Sent from sourceforge.net because you indicated interest in
> https://sourceforge.net/p/gretl/feature-requests/147/
>
> To unsubscribe from further messages, please visit
> https://sourceforge.net/auth/subscriptions/
>
2 months, 2 weeks
Midas make high frequency series stationnary
by d.lalountas＠minfin.gr
HI all,
I am working with non stationary HF data . The source of stationnarity appers to by a seasonal patern.
The ordinary gretl functions to deal with non stationary patterns are diff sdiff , while the corresponding diff function is hfdiff/hfldiff.
In the midas case what are the corresponding function to deal with seasonality?
Thanks in advance
Denis
2 months, 3 weeks
Gretl is shutting down
by Dionysio Lalountas
Hi all,
When running some script files, the gretl is shutting down . I am runing the 2023b version.
This happens when connected to the dbnomics database
A sample of the script file is shown below.
Thanks
Dionisio
clear --dataset
open dbnomics
data Eurostat/ei_bsin_m_r2/M.BAL.BS-ICI.SA.EL --name="esi_indu" # esi industry
data Eurostat/ei_bsrt_m_r2/M.BAL.BS-RCI.SA.EL --name="esi_retail" # esi retail
data Eurostat/ei_bsco_m/M.BAL.BS-CSMCI.SA.EL --name="esi_cons" # Consumer confidence indicator
data Eurostat/ei_bssi_m_r2/M.BS-ESI-I.SA.EL --name="esi" # SENTIMENT INDICATORS
data Eurostat/ei_bsbu_m_r2/M.BS-CCI-BAL.SA.EL --name="esi_constr" #Construction confidence indicator – Seasonally adjusted data, not calendar adjusted data
data Eurostat/ei_bsci_m_r2/M.BS-BCI.SA.EA20 --name="esi_eurozone" #Business climate indicator – Seasonally adjusted data, not calendar adjusted data – Euro area – 20 countries
data Eurostat/ei_bssi_m_r2/M.BS-SCI-BAL.SA.EL --name="esi_service" # Services confidence indicator – Seasonally adjusted data, not calendar adjusted data
2 months, 3 weeks
chow test
by Alison Loddick
Hi all,
I’m hoping the econometricians can help me. I’m working with a colleague at another university and he recommends using the Chow test to test whether we should use an OLS model vs Fixed effects. My question is what test does Gretl use within Fixed effects to compare the model with OLS as the manual doesn’t say?
The manual recommends that we use the fixed effect model results to see whether there should be a fixed effects model or OLS. I assumed this was the Chow test. My output is below:
Test for differing group intercepts -
Null hypothesis: The groups have a common intercept
Test statistic: F(98, 1230) = 11.49
with p-value = P(F(98, 1230) > 11.49) = 4.27683e-116
There is a Chow test on the OLS model but when I run it has different degrees of freedom and different F-statistic.
Thank you for any knowledge you can give me.
You all have been great in increasing my knowledge.
Alison
University of Northampton: Transforming Lives and Inspiring Change www.northampton.ac.uk This e-mail is private and may be confidential and is for the intended recipient only. If you are not the intended recipient you are strictly prohibited from using, printing, copying, distributing or disseminating this e-mail or any information contained in it. We virus scan all E-mails leaving The University of Northampton but no warranty is given that this E-mail and any attachments are virus free. You should undertake your own virus checking. The right to monitor E-mail communications through our networks is reserved by us.
Disclaimer
The information contained in this communication from the sender is confidential. It is intended solely for use by the recipient and others authorized to receive it. If you are not the recipient, you are hereby notified that any disclosure, copying, distribution or taking action in relation of the contents of this information is strictly prohibited and may be unlawful.
This email has been scanned for viruses and malware, and may have been automatically archived by Mimecast, a leader in email security and cyber resilience. Mimecast integrates email defenses with brand protection, security awareness training, web security, compliance and other essential capabilities. Mimecast helps protect large and small organizations from malicious activity, human error and technology failure; and to lead the movement toward building a more resilient world. To find out more, visit our website.
2 months, 3 weeks
