生成具有污染对数正态分布的随机样本

发布于 2024-12-29 19:47:04 字数 255 浏览 1 评论 0原文

我想生成一个随机样本，其污染的对数正态分布在 Matlab 中。受污染的对数正态分布样本的一个示例可能是双峰对数正态分布，其中有 1 个大节点和 1 个小节点。

我用它来生成 5 个样本，每个样本包含 10 个数据点。

trueGM=1;
trueGSD=2;
n=10;
m=5;
o = lognrnd(log(trueGM), log(trueGSD),n,m);

我该如何修改它以获得污染的对数正态分布？

原文

I would like generate a random sample with a contaminated lognormal distributed in Matlab. An example of a contaminated lognormal distributed sample could be bimodal lognormal distribution where you would have 1 large node and 1 small node.

This is what I used to generate 5 samples each containing 10 data points.

trueGM=1;
trueGSD=2;
n=10;
m=5;
o = lognrnd(log(trueGM), log(trueGSD),n,m);

How can I modify this to get contaminated lognormal distribution?

分享到QQ

分享到微博

如果你对这篇内容有疑问，欢迎到本站社区发帖提问参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

发布评论

需要登录才能够评论，你可以免费注册一个本站的账号。

七月上 2025-01-05 19:47:04

这会导致一个对数正态样本被另一个对数正态样本的 25% 污染。

sampleSize = 10000
pureln = exp(rnorm(n=sampleSize, 3, 4))
contam = runif(n=sampleSize) < .25
other = exp(rnorm(n=sum(contam), 15, 0.01))
mixture = pureln
mixture[contam] = other
hist(log(mixture))

This contaminates a lognormal sample with 25% of another lognormal sample.

sampleSize = 10000
pureln = exp(rnorm(n=sampleSize, 3, 4))
contam = runif(n=sampleSize) < .25
other = exp(rnorm(n=sum(contam), 15, 0.01))
mixture = pureln
mixture[contam] = other
hist(log(mixture))

回复收藏 0 原文

~没有更多了~