February 2006 - Gretl-users - gretlml.univpm.it

Changing the limits of the ARMA estimation

by Ignacio Díaz-Emparanza

I have a multiplicative ARMA model that seems difficult to estimate as is actually not converging. I know that usually it means that the specification of the model is not good, but I think in this case if I augment the limit of iterations it will soon converge. Is there a way of doing that? and, Is there a way of changing the tolerance criterium for ARMA models? -- Ignacio Díaz-Emparanza Dpto. de Economía Aplicada III (Econometría y Estadística) UPV-EHU

20 years

7
60
0 / 0

translation question

by Sven Schreiber

Hi, in the German translation I have been adding a bunch of menu shortcuts, or more accurately, menu accelerators as I believe they're called. (type alt+letter to access the menu entry which has the corresponding underlined letter) I'm wondering: - Can I break anything if I add accelerators which in the original version don't exist? - Is there a rule for the choice of which items get accelerators? I couldn't infer the pattern from the status quo. Thanks, sven

20 years

3
3
0 / 0

Kalman filter

by Arnaud Bervas

By chance, would there be anyone having developed a Kalman filtering program with Gretl ? I imagine that such a program might be developed with Gretl and I would be interested in having a look at an example. Thanks

20 years

3
3
0 / 0

nonliinear least squares

by Arnaud Bervas

Thanks!

20 years, 1 month

1
0
0 / 0

new Windows snapshot

by Allin Cottrell

There's a new snapshot with fixes for some of the issues raised lately (I believe). There may also be new bugs, though: the transition from straight arma to arima is not well tested yet, particularly with regard to ARIMA forecasting. http://ricardo.ecn.wfu.edu/pub/gretl/gretl_install.exe -- Allin Cottrell Department of Economics Wake Forest University, NC

20 years, 1 month

1
0
0 / 0

nonliinear least squares

by Arnaud Bervas

I can't execute the following program: ols ld_SGD ld_USD ld_EUR ld_JPY ld_TWD ld_INR ld_KRW ld_IDR ld_AUD ld_THB genr b0 = coeff(ld_USD) genr b1 = coeff(ld_EUR) genr b2 = coeff(ld_JPY) genr b3 = coeff(ld_TWD) genr b4 = coeff(ld_INR) genr b5 = coeff(ld_KRW) genr b6 = coeff(ld_IDR) genr b7 = coeff(ld_AUD) nls ld_SGD= b0*ld_USD + b1*ld_EUR + b2*ld_JPY + b3*ld_TWD + b4*ld_INR + b5*ld_KRW+ b6*ld_IDR + b7*ld_AUD + (1-b0-b1-b2-b3-b4-b5-b6-b7)*ld_THB end nls I attach the corresponding dataset. Can you see what's wrong ? Thank you

20 years, 1 month

3
2
0 / 0

silly bug

by Ignacio Díaz-Emparanza

Sorry Allin, I know you are very busy know with the arima code, but I discovered something broken in the OLS graphing code that should be corrected. With for example data3-6.gdt, if I run an OLS regression of Ct vs Yt, and, in the model output window, I select "graphs/fitted, actual plot/against Yt", I obtain the incorrect plot you have in the attachment. This was with gretl for Windows in English (snapshot build 02/17/2006). I tried the same thing with Linux (official 1.5.0 version) and the result was the same with gretl in Spanish, but if I try it with "gretl --english" the graph plotted is correct. -- Ignacio Díaz-Emparanza Dpto. de Economía Aplicada III (Econometría y Estadística) UPV-EHU

20 years, 1 month

2
1
0 / 0

limitations of maximum likelihood estimations

by Arnaud Bervas

Thank you Allin and Riccardo. It works perfectly now. I guess I will have to be more careful on the syntax in the future. NB: the problem occured in the script mode (opening the window "new script") Arnaud

20 years, 1 month

2
1
0 / 0

limitations of maximum likelihood estimations

by Arnaud Bervas

I have also tried with artificial data, but still doesn't work. I was about to reinstall Gretl to try again, but you will maybe find out what is wrong using the data attached. Thank you for this

20 years, 1 month

3
3
0 / 0

limitations of maximum likelihood estimations

by Arnaud Bervas

Thank you. I have actually tried to run the program you suggest, but each time a window opens saying that a problem occured ant that Gretl must be closed. The dataset I use is however quite small (42 observations for each variable, integer nonnegative numbers). The parameters c1, c2 and c3 are real numbers comprised between 0 and 1.

20 years, 1 month

2
1
0 / 0

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Gretl-users February 2006