August 2020 - Gretl-users - gretlml.univpm.it

Using = instead of == for a boolean check not tolerated anymore

by Sven Schreiber

Hi everybody, here's a little service announcement: After years of being oficially deprecated, you cannot use the single equality sign "=" anymore to do a boolean check (in git and future released versions). You must use the double equality operator "==". Gretl has printed out deprecation warnings for a long time, so you should have noticed if you are affected. The assignment operator "=" is of course NOT affected by this, it will stay in this natural form, for example as in: series x = normal() cheers sven

5 years

2
1
0 / 0

The new ParMA package

by Riccardo (Jack) Lucchetti

Folks, Luca Pedini and myself have just released version 0.9 of the new ParMA package. "ParMA" stands for Parallelised Model Averaging. Basically, you can do Bayesian Model Averaging on Generalised Linear Models (which includes Poisson regression, Probit and more) using parallelisation if available. To install <hansl> pkg install ParMA.zip </hansl> Comments welcome! ------------------------------------------------------- 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 -------------------------------------------------------

5 years

3
3
0 / 0

Cointegration

by Mike ＠me.com

Hi All, I am trying to determine if two time series (closing prices of two securities)are cointegrated. The two pass the eyeball test. I have conducted both the Johansen and Engle-Granger tests. The results are attached. I don't know how to interpret the results. I was hoping for a big "YES", "NO" or at least a "LIKELY" at the end of the tests. If anyone would tell me which statistics I should be looking at and how to interpret them, I would sure appreciate it. If you are kind enough to do that, please speak slowly because I am not a data scientist! Best regards, MikeC

5 years

3
4
0 / 0

time-series plot weekly/ hourly data frequency

by Artur Tarassow

Hi all, I spotted a possible "bug" when trying to plot weekly or hourly data over time. Take a time-series, set some frequency and check the plot. Even though the <print invest -o> command shows a correct date index, the x-axis of the plot does _not_ show any date format for weekly or hourly data. For other frequencies, things are fine. This is with latest git on Ubuntu 20.04. <hansl> clear open grunfeld.gdt -q smpl firm == 1 --restrict # Set some frequency #--------------------- setobs 52 2020:40 --time-series # dates are NOT shown on x-axis # setobs 24 1:6 --time-series # dates are NOT shown on x-axis # setobs 1 2020 --time-series # dates are shown on x-axis # setobs 4 2020:1 --time-series # dates are shown on x-axis # setobs 12 2020:1 --time-series # dates are shown on x-axis # setobs 7 2020-01-01 --time-series # dates are shown on x-axis print invest -o gnuplot invest --with-lines --time-series --output=display </hansl> Artur

5 years

3
2
0 / 0

Wald test

by f.marchini＠studenti.unibg.it

Hi all, I'm a student at University of Bergamo and i'm writing my dissertation on the asymmetric eur/usd exchange rate effects on trade relations. I need some help to figure out how to perform the Wald test on Gretl in order to test the asymmetry hypotesis. Thanks in advance F.Marchini

5 years

5
7
2 / 0

New package available: LocalProjection.gfn

by Sebastián Díaz

Hello everyone, I'm introducing you to this new package which estimates the impulse response function for a multivariate linear local projection model, as described in Jordá (2005), and a multivariate regime-switching local projection model, following Auerbach and Gorodnichenko (2012). This package returns the graph or graphs, depending on the type of model, and a bundle which includes the values of the IRF that results from the estimation and some other features that you may find useful. For any further details, feel free to contact me. Any doubts, comments or suggestions are welcome. Best, Gerardo Sebastián Díaz Muro

5 years

1
0
1 / 0

New package: season_plot

by Artur Tarassow

Hi all, This package computes and depicts a time-series across sub-periods, also called a Buys-Ballot plot. For instance, if one has a quarterly time-series one can plot the dynamics of each quarter across years. Vice versa, you may also be interested in plotting the dynamics of each year's quarter. It's a kind of alternative to the existing package "|buys_ballot|" written by Ignacio Diaz-Emparanza and Riccardo (Jack) Lucchetti. However, "season_plot" allows you to plot _all_ frequency combinations. The main features are: * Simple API. * GUI access through the gretl menu. * Source code is tested by means of unit-tests to minimize bugs. It requires that version 0.2 of the "multiplot" package is installed on your system. It's already available on the gretl package server: <hansl> pkg install season_plot include season_plot.gfn help season_plot </hansl> For a brief introduction see also here: https://github.com/atecon/seasonality_plot Best, Artur

5 years

1
0
1 / 0

Re: Negative numbers to fractional powers

by Alecos Papadopoulos

Let X be a series of negative numbers. Then the command series Y = X^(1/3) (or any other "1/oddnumber" fractional power) returns a "Warning: pow: Domain error" message, overwrites series "Y" and returns a "no valid values" if one attempts to view the series. Why is this happening, considering that X^(1/3) is a real number even if X is a negative number? Now, consider series "Z" which has both positive /and/ negative values. We want to compute W = Z^(1/3) Given a recent new feature in gretl, the sign function sgn(), I guess we can avoid the obvious conditional if-else statement, and compute W by writing W = sgn(Z) * (abs(Z)^(1/3)) that covers also the case of Z taking an exact zero value. Is this the proper/efficient way? -- Alecos Papadopoulos PhD Athens University of Economics and Business web: alecospapadopoulos.wordpress.com/ skype:alecos.papadopoulos

5 years

4
8
0 / 0

Henrique's FOSS Twitter-campaign

by Artur Tarassow

Dear all, Henrique runs for a couple of days a nice campaign supporting FOSS (free open-source software). And Gretl is just the centre point of his thoughts on FOSS. You should check it out and support him: https://twitter.com/imakefoss Thanks for the initiative, Henrique! Artur

5 years

1
0
0 / 0

gretl 2020d released

by Allin Cottrell

This is an "emergency" release to fix a nasty bug in 2020c, but it has a little added functionality too. 2020-08-06 version 2020d - Fix GUI bug: crash on copying data series to clipboard in formats other than plain text - "poisson" command: switch to using Newton-Raphson with analytical hessian; also use analytical hessian for "negbin", and add Wald chi-square tests for both - "cusum" command: add a --plot option - GUI console: protect from deletion when a command is being executed -- Allin Cottrell Department of Economics Wake Forest University

5 years

3
2
0 / 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Gretl-users August 2020