armax-auto option occasionally generates this error
by Tim Nall
Thanks to all for the replies. Will try to find TRAMO. meanwhile, the
armax-auto option occasionally generates this error:
? armax(4, 4, BOTH, null, 1, 1, 0, 1, 0)
BFGS: initial value of objective function is not finite
*** error in function armax, line 82
> loop q = 0..maxq
On Sat, Apr 26, 2014 at 4:46 PM, Riccardo (Jack) Lucchetti
<r.lucchetti(a)univpm.it> wrote:
> On Sat, 26 Apr 2014, oleg_komashko(a)ukr.net wrote:
>
>> You can use armax_auto (see time series menu in Gretl GUI). The function
>> has a drawback: the cycle crushes on encountering a unit root in MA part of
>> the model Also you can use auto.arima{forecast} in R My experience tells it
>> would be better to determine the order of integration (use unit root tests)
>> beforehand and use, say "d=1" in auto.arima (type ?auto.arima in R console)
>
>
> That's a function package, you may need to install it first: go to
> Files>Function Files>On server.
>
> -------------------------------------------------------
> 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
> -------------------------------------------------------
> _______________________________________________
> Gretl-users mailing list
> Gretl-users(a)lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
--
Best regards,
Timothy M. Nall
Assistant Professor
National Quemoy University
Kinmen, Taiwan
11 years, 11 months
question about variance decomposition
by Leandro Zipitria
Dear all,
I want to made a variance decomposition analysis, that is to decompose the
variance into particular covariates. This models are hierarchical models.
Is any command in Gretl that does the same analysis as xtmixed in Stata, or
proc mixed in SAS?
Thanks
Leandro
11 years, 11 months
thanks
by oleg_komashko＠ukr.net
Thank everybody! Have tried on debian/jessie CVS and from Debian repos and on XP: the same
The problem is 100% with R 3.1 Have installed 3.03 works
11 years, 11 months
r session bug more simply
by oleg_komashko＠ukr.net
to easily see the possible bug: run #begin nulldata 100 setobs 1 1910 --time-series series norm = randgen(N,15000,200) # end start interactive R session and type in R console > gretldata What I obtained started as follows: index norm 1910 1 15 1911 2 1 1912 3 60
11 years, 11 months
possible bug with sending data to R session
by oleg_komashko＠ukr.net
It seems, there is a bug in exporting data on starting R session from Gretl If start a R session with the attached file opened in Gretl variables l_gdpr_usa and gdpr3 are read as they should be. gdpr_usa[1] is 99547.54
gdpr3=gdpr_usa/1000 gdpr_usa is read in R as [1] 142 1 2 5 4 6 7 8 9 15 19 21 26 27 29 31 34 37 36 40 41 43 48 [24] 46 44 50 49 52 54 58 60 64 67 70 68 72 79 81 74 82 83 85 89 91 86 88 [47] 95 94 102 103 101 99 106 112 116 118 121 122 124 131 120 115 107 104 110 113 126 130 127 [70] 132 137 3 12 17 23 20 11 10 13 14 16 18 22 25 24 28 30 33 32 35 38 39 [93] 42 45 47 51 53 55 56 57 59 61 62 66 65 63 69 71 73 76 75 78 77 80 84 [116] 87 90 92 93 96 98 97 100 105 108 109 111 114 117 119 123 125 128 129 133 134 136 140 [139] 139 135 138 141 143 The original source is http://www.eurmacro.eu/macrodata/datamtrx.html ; the data was copy-pasted to the empty text file. Original header gdpr_usa
"millions of U.S. Dollars; 1990 prices"
1870 99547.54 was edited to year gdpr_usa 1870 99547.54
and the text file was imported If recode the data as cross-section gdpr3 is read well but gdpr_usa is read as factor instead of numeric if type as.numeric(gdpr_usa) we again get [1] 142 1 2 5 , etc.
11 years, 11 months
Problems installing arima X13
by JOSE FRANCISCO PERLES RIBES
Dear list:
I have tried to install arima X13 on gretl 1.9.14 and Windows 7 (I have
tried both version x86 and 64 bytes).
After downloading and installing arima X13 I have modified the
configurations (preferences) of gretl to indicate it the new path as usual
C:\Program Files\x13...
However, when I run the arima X12 tab from menu GUI, the initial graph is
opened, but the ouptut window is completely white,...no output is printed...
So, arima X13 only runs from gretl console and not for GUI? and Somebody
has had the same problem???
Thanks in advance
José Perles
11 years, 11 months
Re: [Gretl-users] Questions about strings and string substitution
by Logan Kelly
Ok. Is there a way to use strsub() to add newline to a string?
Logan
-------- Original message --------
From: "Riccardo (Jack) Lucchetti"
Date:04/23/2014 2:24 AM (GMT-06:00)
To: Gretl list
Subject: Re: [Gretl-users] Questions about strings and string substitution
On Wed, 23 Apr 2014, Logan Kelly wrote:
> Hello,
>
> Question about strings and string substitution. Why does option 1 yield
> different output from option 2 (see below). I am using 1.9.14 on Win 7
> 64bit
>
> hansel:
>
> #option 1
> s = "1\n2\n3\n"
> printf "@s"
>
> #option 2
> printf "1\n2\n3\n"
>
> OUTPUT:
>
> gretl version 1.9.14
> Current session: 2014-04-22 23:49
> #option 1
> ? s = "1\n2\n3\n"
> Replaced string s
> ? printf "@s"
> 1\n2\n3\n
>
> #option 2
> ? printf "1\n2\n3\n"
> 1
> 2
> 3
That's by design. The two sister funtions/commands printf and sprintf
support ASCII control characters, simple assignment does not. If you need
to embed a newline or a tab into a string, use sprintf. For example:
<hansl>
sprintf a "%d\t%d", 3, 4
print a
</hansl>
That said, we are considering the idea to turn the sprintf command into a
function (this is already available in CVS and the snapshots), so perhaps
you may want to experiment with the new notation, which would be
scalar n = sprintf(a, "%d\t%d", 3, 4)
where n is the number of characters that "a" contains.
-------------------------------------------------------
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
-------------------------------------------------------
11 years, 11 months
Questions about strings and string substitution
by Logan Kelly
Hello,
Question about strings and string substitution. Why does option 1 yield different output from option 2 (see below). I am using 1.9.14 on Win 7 64bit
hansel:
#option 1
s = "1\n2\n3\n"
printf "@s"
#option 2
printf "1\n2\n3\n"
OUTPUT:
gretl version 1.9.14
Current session: 2014-04-22 23:49
#option 1
? s = "1\n2\n3\n"
Replaced string s
? printf "@s"
1\n2\n3\n
#option 2
? printf "1\n2\n3\n"
1
2
3
Thanks,
Logan
11 years, 11 months
Seasonal adjustment procedures not available
by Logan Kelly
Hello all,
I am having some difficulty getting the seasonal adjustment functions working. I have tried installing the packages from the gretl website but gretl does not recognize that they are installed.
I am running 1.19.14 on Windows 7 64 Bit
Thanks,
Logan
11 years, 11 months
Mahalanobis Distance - Execution Time
by GOO Creations
Hi,
I'm benchmarking the Mahalanobis distance to see how the accuracy and
execution time changes with an increasing sample size. As far as I
understand the algorithm the execution time should grow linearly as the
sample size increases. The weird thing is that the time grows linearly up
to (and including) 199 samples, but then suddenly has a drop at 200
samples. I've attached a graph to illustrate this.
I'm using it to do outlier detection. The time drops at 200 samples, but
the accuracy increases without a sudden drop.
Does anyone know why this happens?
Chris
11 years, 11 months
