Confidence intervals in Plots (Normal distribution)

2 visualizaciones (últimos 30 días)
David Canales
David Canales el 7 de Jun. de 2017
Editada: David Canales el 8 de Jun. de 2017
I would like to know how to plot the 68% confidence interval of a Gaussian in such a way the resulting image looks similar to this one:
I am trying to do that with R, but I want to resort to Matlab again for my research and I want to see its abilities for statistics. I would compute the histogram as follows. The input comes from the CODAchain1.txt attached.
ic_table_file1 = 'CODAchain1.txt';
%%Read tables
codachain = load(ic_table_file1);
%%Length params
snum=1000;
media=mean(codachain(1:snum,2));
sdev=std(codachain(1:snum,2));
vector1=codachain(1:snum,2);
vector1=sort(vector1);
%Histogram
figure(2);
hold on;
min_bin=min(vector1);
max_bin=max(vector1);
inc_bin=(max_bin-min_bin)/40;
binranges = min_bin:inc_bin:max_bin;
[bincounts,ind] = histc(vector1(:),binranges);
sumatot=sum(bincounts(:));
bar(binranges,bincounts/sumatot,'m');
mu=media;
sigma=sdev;
analytic = min_bin:inc_bin:max_bin;
Y = normpdf(analytic,mu,sigma);
sumatotY=sum(Y(:));
plot(analytic,Y/sumatotY);
xlim([min_bin max_bin])
I don't know how would I be able to make the confidence interval that appears in the first image.
Thank you very much.

Respuestas (0)

Categorías

Más información sobre Histograms en Help Center y File Exchange.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by