removing nan and inf from a matrix
by Logan Kelly
Hello,
I need to take the log difference of a matrix, i.e. log(M[2 rows(M):,]/M[1:rows(M)-1,]). Unfortunately, M has elements equal to zero. I need to replace the nan's and inf's with 0's. This almost works
M = isnan(M) ? 0 : M
but does not remove inf's. Any sugestions?
8 years, 4 months
logit and $error
by Artur Tarassow
Hi,
after estimating a LOGIT model I obtain the following message:
"Note: armeu == 0 predicts failure perfectly
714 observations not used
Not a Number in calculation"
I used the command "catch logit ..." to control for any error. I am
wondered why the $error flag is still zero despite the message. Should
this not result in a non-zero error value?
Best,
Artur
11 years, 1 month
logit: accessors for the no. of cases correctly predicted
by Artur Tarassow
Hi,
I am just wondering if there already exists a built-in accessors for the
number of cases correctly predicted after a logit/probit estimation? I
couldn't find any in the manual, but maybe I missed something.
Best,
Artur
11 years, 1 month
question
by Salvador Rodriguez
package there stretch / seats and x-12-arima for 64-bit architectures? is that
packets ... 32bit not work on my 64-bit computer .... my computer has debian
7 ... is there any way to make them work in the gretl that I have installed
on my 64bit debian?
11 years, 1 month
logit: accessor for the no. of cases correctly predicted
by Artur Tarassow
Hi,
I am just wondering if there already exists a built-in accessor for the
number of cases correctly predicted after a logit/probit estimation? I
couldn't find any in the manual, but maybe I missed something.
Best,
Artur
11 years, 1 month
modeltab bug
by Artur Tarassow
Hi all,
I've found an issue (using current cvs on linux) with the "modeltab"
command. As long as the 4th line in the following example is commented,
the print-out does not include any estimated coefficients.
<hansl>
open denmark
m1 <- ols LRM LRY --quiet
modeltab add
#modeltab show
modeltab --output="OLS_1.txt"
<\hansl>
Best,
Artur
11 years, 1 month
String and Scalar Error
by Henrique
Dear Gretl Developers,
I'm getting an error message when I try to run that script using the latest snapshot:
<hansl>
clear
nulldata 200
setobs 12 2000:01 --time-series
string data_1o_lim_sup = "2010:02"
string data_2o_lim_sup = "2013:7"
scalar n_exec = @data_2o_lim_sup - @data_1o_lim_sup + 1
</hansl>
The message is: "Data types not conformable for operation".
I'm a little bit confused because the same script works with Gretl 1.9.11cvs (build date: 2013-01-08).
Best regards,
Henrique Andrade
Enviado via iPhone
11 years, 1 month
Retrieving adjusted R-squared using the command line
by Beek Pang
Dear gretl community,
When using the gretl console, or a script, it is possible to use '$rsq' in order to retrieve the value of the (according to the gretl documentation) UNadjusted R-squared from the model output. This is convenient when using the --quiet option, for example.
My question now: Can the adjusted R-squared (which gretl usually also includes in model output, where appropriate) also be retrieved, in a similar (using the $-accessor) or another way?
Many thanks.
Kind regards
Beek
11 years, 1 month
Time series before 1700
by Cristián Arturo Ducoing Ruiz
Hello everyone.
I'm economic historian and I'm working with silver prices in the spanish
empire. When I tried to import the data from excel, the minimun starting
point is 1700. Do you know how to resolve this problem?
Kind regards
--
Atte.
Cristián Arturo Ducoing Ruiz
11 years, 1 month
Printing of Saved Models and a BUG of the .show command
by Pindar
Hi,
I would like to print in the icon window saved models with the help of a
UDF with an outfile --write command. The idea is that the model is
correctly specified and then the printing function takes the name of the
Model as argument and saves a txt file.
How could this be achieved?
Second, I noticed a small bug in the .show command as illustrated below:
Names starting with numbers are allowed but fail with .show.
<hansl>
open data4-1
Model1 <- ols 1 0 2 3 4 --quiet
Model1.show
"Model 1" <- ols 1 0 2 3 4 --quiet
"Model 1".show
"1 a" <- ols 1 0 2 3 4 --quiet
"1 a".show
<hansl>
Cheers
Leon
11 years, 2 months
