Dear Gretl users, I am trying to run a kernel approximation to a series of data (attached), using the command kdensity as show in the manual. Specifically, the inp is as follows: matrix d = kdensity(Water) gnuplot --matrix=d --with-lines --output=pruba.eps But, once run the output says that the second column has non finite values. Maybe is because values are integers, but I have checked on Stata (sorry, a friend of mine, I do not use it), and the kernel density flows without problems.

Is this a problem of the data, or I am doing something wrong?

Dear Gretl users, I am trying to run a kernel approximation to a series of data (attached), using the command kdensity as show in the manual. Specifically, the inp is as follows: matrix d = kdensity(Water) gnuplot --matrix=d --with-lines --output=pruba.eps But, once run the output says that the second column has non finite values. Maybe is because values are integers [...]

On Tue, 28 Jan 2014, Leandro Zipitria wrote: Dear Gretl users, > > I am trying to run a kernel approximation to a series of data (attached), > using the command kdensity as show in the manual. > > Specifically, the inp is as follows: > > matrix d = kdensity(Water) > gnuplot --matrix=d --with-lines --output=pruba.eps > > But, once run the output says that the second column has non finite > values. > Maybe is because values are integers, but I have checked on Stata (sorry, > a > friend of mine, I do not use it), and the kernel density flows without > problems. > > Is this a problem of the data, or I am doing something wrong? > Well, your data are in fact a bit weird: "Water" really is a discrete variable, with most cases equal to 0 and a few other values in the support. If you set Water as discete, this is what you get from the "freq" command: <output> Frequency distribution for Water, obs 1-2619 frequency rel. cum. 0 2190 83.62% 83.62% ****************************** 0.5 15 0.57% 84.19% 0.6 1 0.04% 84.23% 1 98 3.74% 87.97% * 1.1 27 1.03% 89.00% 1.5 148 5.65% 94.65% ** 2 122 4.66% 99.31% * 2.2 18 0.69% 100.00% </output> So this is decidedly not the kind of data you want to compute the kernel density of. Having said this, the fact that "kdensity" produces a string of NAs is in fact a bit perplexing, especially considering that if you add some random noise, as in <hansl> Water2 = Water + 0.01*normal() </hansl> then things work like you'd expect them to. I'll have a look as soon as possible. ------------------------------------------------------- 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

On Tue, 28 Jan 2014, Leandro Zipitria wrote: Dear all, > > First, I have checked the CSV and confirm that now the kernel works as > expected. > Thanks all for the help. > Just to add that the information is plotted reversed (the data generated > for the kernel approximation is reversed in the matrix), I attach the file > generated. > Whoops, youre right. Use this: <hansl> gnuplot 2 1 --matrix=d --with-lines --output=pruba.eps --suppress-fitted </hansl> ------------------------------------------------------- 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 -------------------------------------------------------

On Tue, 28 Jan 2014, Leandro Zipitria wrote: > Thanks Ricardo, > > I have reversed the axes: > > <hansl> > matrix d_1 = kdensity(Water) > matrix d[,1] = d_1[,2] > matrix d[,2] = d_1[,1] > <hansl> > > Now its ok. I think that the orders in the commmand kdensity are reversed, > or the gnuplot command use the information in the matrix that Gretl create > in reverse form (column 1 in the x axes and column 2 y axes, when it should > be otherwise). The matrix itself is fine, the columns being x, f(x). The thing is that gnuplot expects the y-axis variable(s) to be given first, then x (this is in the help for the "gnuplot" command). Maybe if you use "gnuplot" on a two-column matrix without giving a list for the column order we should assume the matrix is in x, y order and therefore reverse the columns for gnuplot's benefit? I'm not sure if that would break any build-in uses of gnuplot in gretl. Allin Cottrell _______________________________________________ Gretl-users mailing list Gretl-users(a)lists.wfu.edu http://lists.wfu.edu/mailman/listinfo/gretl-users

Am 28.01.2014 16:01, schrieb Leandro Zipitria: > Dear Allin, > > my fault, my command was > gnuplot --matrix=d --with-lines > > instead of: > gnuplot 2 1 --matrix=d --with-lines > > Now I realize that with the 2 1 Gretl rearrange the plot in the right wat. > > Just one final question, is there any option to add a title to a plot > using the gnuplot command? > Yes, but you have to embed literal gnuplot commands the way it's described in the help, with curly braces. Here's something I have used, as an example: gnuplot --matrix=temp --with-lp --output=display \ { set title 'blabla' font 'Verdana,11'; \ set key bottom right font 'Verdana,9'; \ set xlabel 'Jahr' font 'Verdana,9'; \ set xtics font 'Verdana,8'; \ set ytics font 'Verdana,8'; \ set ylabel 'blublu' font 'Verdana,10'; \ set style line 1 lw 2; \ set style line 2 lw 2; \ } hth, sven _______________________________________________ Gretl-users mailing list Gretl-users(a)lists.wfu.edu http://lists.wfu.edu/mailman/listinfo/gretl-users