Histogram of overlaid standard normal draws

Question

Snoopy 2021-10-24

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1570748-histogram-of-overlaid-standard-normal-draws

评论： Snoopy 2021-10-26

Picture.png

The code below overlays histograms of two sets of standard normal draws. I also attach the graph itself. These draws are based on two Halton sequences, but that is (probably) not relevant to my question. Both sets use the same number of draws (3573) from the Halton sequence. I am a bit puzzled with the overlaid histograms. It looks as if the frequency count of one set (dark blue) is almost everywhere larger than that for the other set (white). But this is impossible because both sets have the same number of draws. That is, I would either expect a very close overlay, or that if one set has more counts at some regions, the other should have more at other regions, so that the number of counts (of draws) are the same in total.

H = haltonset(2,'Skip',50+1);

H = net(H,3573*3);

H = reshape(H,3573,3,2);

S = norminv(H);

histogram(S(:,3,1),100,'FaceColor','blue','EdgeAlpha',0.5);

hold on

histogram(S(:,3,2),100,'FaceColor','white','EdgeAlpha',0.5);

legend('Standard normal draws for 1st dimension','Standard normal draws for 2nd dimension')

hold off

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

the cyclist 2021-10-25

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1570748-histogram-of-overlaid-standard-normal-draws#answer_815563

编辑：the cyclist 2021-10-25

在 MATLAB Online 中打开

If you look carefully, you will notice that your bins are not at precisely the same locations. If you instead choose the exact bin locations (instead of just using 100 bins), you'll get what you expect:

H = haltonset(2,'Skip',50+1);

H = net(H,3573*3);

H = reshape(H,3573,3,2);

S = norminv(H);

binEdges = -4:0.1:4;

histogram(S(:,3,1),binEdges,'FaceColor','blue','EdgeAlpha',0.5);

hold on

histogram(S(:,3,2),binEdges,'FaceColor','white','EdgeAlpha',0.5);

legend('Standard normal draws for 1st dimension','Standard normal draws for 2nd dimension')

hold off

Just illustrate it a bit more, here are the differences in bin counts for your method. You see that away from the peak, the values are negative, so the rear bins are fully hidden behind the front bins.

H = haltonset(2,'Skip',50+1);

H = net(H,3573*3);

H = reshape(H,3573,3,2);

S = norminv(H);

hc1 = histcounts(S(:,3,1),100);

hc2 = histcounts(S(:,3,2),100);

figure

plot(hc1-hc2)