January 2013 - Gretl-users - gretlml.univpm.it

by Leandro Zipitria

Dear all, I have two quick problems: 1) I have a database which have monthly data. I want to compact the data restricting the original database. In doing so, I have made the following loop: loop i=2002..2012 --progressive loop j=1..12 --progressive smpl Destino=1 && Familia=2 && Anio=i && Mes=j --restrict M[132+(i-2002)*12+j,2]=nobs(Anio) smpl full endloop endloop which store each sample in a matrix. The problem is that sometimes the result from the restriction is null. In that case, the loop breaks and stop running. I know that I have to use the if command, but I do not how. What I want to do is that if the result of the restriction is null, then to store a N/A, and continue the loop. 2) The second point I want to know is if there is a chance to put "labels", strings should be the right word, in the first row of the matrix. Thanks, Leandro

11 years, 11 months

2
2
0 / 0

optional and variable function arguments

by Logan Kelly

Hello, I would like to write a function that accepts as an argument a variable that could be a series, a matrix or a scalar. The function should behave differently depending on the variable type passed. Is there a good way to do this, i.e. what should the function declaration look like? Thanks, Logan

11 years, 11 months

2
1
0 / 0

URGENT

by Kofi Kamasa

I want to know if you can estimate an ARDL model with dependent variable integrated of order zero.

11 years, 11 months

3
2
0 / 0

gnuplot: How to format an eps file

by Logan Kelly

Hello, I am having trouble getting gnuplot to work. I am trying to produce eps graphics files, but I (i) cannot get the line colors right (the second line is neon green. I need line one to be black, line two to be red and line three to be blue) and (ii) the graphic file has no buckhound, i.e. the background is transparent (this is not a huge deal). Here is the code I am using gnuplot R1_@cc R2_@cc \ --time-series \ --single-yaxis \ --with-lines \ { set terminal postscript eps enhanced "Helvetica, 10" dashed color size 2.5,1.75;\ set key left top;\ set linestyle 1 lt 1 lc 7;\ set linestyle 2 lc 1 lt 2;\ set linestyle 3 lc 3 lt 5; }\ --output="Bench_(a)cc.eps" I am using gretl 1.9.9, Gnuplot 4.2 on a Win 7 64 bit OS Any ideas on what I am doing wrong? Thanks, Logan

11 years, 11 months

2
2
0 / 0

[gretl-users] bootstrapping standard errors

by JOSE FRANCISCO PERLES RIBES

Dear all: I'm trying to replicate a table similar to that of Angrist and Pischke(2009) Mostly Harmless Econometrics chapter 8 p,306 where in a Monte Carlo experiment comparing different bootstrap standard errors(conventional versus White, ...HAC) for a regression coefficient of interest, to show that the robust errors tend to be biased if the problem that are trying to solve (heteroskedasticity or autocorrelation) is not very serious. I have seen that Gretl GUI has a bootstrap option when estimates a model, but it is for the confidence interval and p-value. This option allows you save the values, which is very interesting to get the mean and standard deviation of the beta coefficient. But my question is, there is no option to save the estimated standard errors directly, and via descriptive statistics to obtain the mean and standard deviation of these errors? Thanks in advance and sorry for any inconvenience. José F. Perles Ribes Honorary Collaborator Applied Economic Analysis Department University of Alicante (Spain)

11 years, 11 months

2
1
0 / 0

Problems running Gretl on Mac OSX Lion

by Mirko Weber

Hello Community, i have some problems running Gretl on Mac OSX Lion. I have Intel i5 Macbook Pro from 2011 and I followed all the steps on http://gretl.sourceforge.net/mac-intel.html including the installation of GTK+ Framework and the the steps given in the README.pdf. When i wanted to open Gretl in the normal Applications Folder it gives me the Message: "You can´t open the Program "Gretl", because it is not supported by your type of Mac" (Because I´m from Germany i had to translate the error message, so it might look slightly different on english) I definitely downloaded the gretl version for intel macs and the right GTK+ Framework (I did it several times to be sure as it did not work) and as my Os is Lion, X11 was already installed. So i followed the Trouble-Shooting section in the README.pdf an executed Gretl manually via X11 xterm. Then this error-message appears: dyld: Library not loaded: @executable_path/../lib/libgmp.3.dylib Referenced from: /Applications/Gretl.app/Contents/Resources/bin/gretl_x11 Reason: no suitable image found. Did find: /Applications/Gretl.app/Contents/Resources/bin/../lib/libgmp.3.dylib: file too short /Applications/Gretl.app/Contents/Resources/bin/../lib/libgmp.3.dylib: file too short Trace/BPT trap: 5 I tried to find answers in the previously discussed problems on running Gretl on mac, but i did´t find anything that worked for me! Thanks for your answers and greetings Mirko

11 years, 11 months

5
14
0 / 0

R-programing vs Gretl

by Nabil Brandl

I installed R-programing and I found that R-programing is very useful in case Gretl has some problems in programing such as date and strings treatment. But R-programing is not easy to find syntax, therefore I collect all available syntax in one text file from the following websites. I think R-programing is a very good supply to Gretl programing. I found also through Gretl can run R-programing. R-programing is useful to treat image analysis. My question is how to start R-programing through Gretl. I tried to start gnu r but I failed to started it. The following website have R-programing syntax: http://cran.r-project.org/doc/contrib/Seefeld_StatsRBio.pdf http://en.wikipedia.org/wiki/R_programming_language Best regards and keep in touch Nabil Brandl <http://nabilnabil.homestead.com/> http://nabilnabil.homestead.com

11 years, 11 months

3
2
0 / 0

Assign NA to first observation of a series

by Logan Kelly

Hello, I have a matrix that I need to store as a series, but while the sample is t observation the matrix has only t-1 rows, i.e. the first observation is missing. The following works, but I am not sure this is the correct thing to do: Series MySeries = NA|MyMatrix While this works, it triggers the following warning: Warning: generated non-finite values What is the correct way to deal with a missing observation? I would rather not insert a zero. Thanks, Logan

11 years, 11 months

3
2
0 / 0

Enter date to gretl system

by Nabil Brandl

It is not easy to enter or import date to Gretl system. The only way to enter date is through time series function. It is a weak side in Gretl. It should be a function of enter any date to the system. Any statistic software has function to create date variables as well as create character variables. Collecting data is depends on measuring observations time. It is not difficult to add creating date function as well as creating character variables. Thanks Nabil Brandl http://nabilnabil.homestead.com <http://nabilnabil.homestead.com/>

11 years, 11 months

5
6
0 / 0

Script editor features

by Pindar

Hi there, I have two questions concerning working with the script editor and output window: 1) when using variable names with underscores "series test_2_2" it's hard to reuse them by copying. Double click on e.g. 'test' marks 'test' a third click marks the whole line (at least on windows). What I would expect is marking only 'test_2_2'. 2) If the output window is already open and new lines are executed in the script editor these are silently added to the output. In order to see the result one has to find the output window and scroll down. Sometimes it would be useful to change this behavior, bringing the output window to the front (without changing it's position and format) with the focus already on the last line. I don't now in how far such properties are open to specification in the framework (is this 'gtk'?), but perhaps that's something to enhance future releases, or? Cheers Leon

11 years, 11 months

1
0
0 / 0

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Gretl-users January 2013