t*******s
发帖数: 3031 | 1 什么看到了higgs boson 是几个GeV，然后有三个西格玛。这里的西格玛是什么意思？
前三个回答送包子，谢谢。 | s*******i
发帖数: 12823 | 2 放狗便知的东西...
http://www.lhc-closer.es/php/index.php?i=1&s=4&p=21&e=0
Sigma is the decisive parameter of the Gaussian curve, a mathematical
function that describes the distribution of data from many experiments.
Citing a certain number of sigma directly translates into a probability.
1.5 sigma means just noise (backgroud), but three sigma is equivalent to a
99.75 percent chance that a future experiment will yield a compatible result
. So something interesting has been observed, Well, technically it抯 not a
99.7% chance that the result is correct, but a 99.7% chance that if they
were to run the same experiment again (with the same instruments), they
would get the same result.
Physicists think that only a 5-sigma result, indicating a 99.99995 percent
chance that the result can be reproduced, is trustworthy and can survive the
test of time. A "5s significance" describes effects where the chance of
random occurrence is smaller than a few parts in tens of millions, and is
agreed to be enough to claim the discovery of a new particle or phenomenon.
【在 t*******s 的大作中提到】
: 什么看到了higgs boson 是几个GeV，然后有三个西格玛。这里的西格玛是什么意思？
: 前三个回答送包子，谢谢。
| t*******s
发帖数: 3031 | 3 我就是类似的这几段话没读懂。你能用统计公式解释下吗？谢谢你。先收包子把。
result
【在 s*******i 的大作中提到】
: 放狗便知的东西...
: http://www.lhc-closer.es/php/index.php?i=1&s=4&p=21&e=0
: Sigma is the decisive parameter of the Gaussian curve, a mathematical
: function that describes the distribution of data from many experiments.
: Citing a certain number of sigma directly translates into a probability.
: 1.5 sigma means just noise (backgroud), but three sigma is equivalent to a
: 99.75 percent chance that a future experiment will yield a compatible result
: . So something interesting has been observed, Well, technically it抯 not a
: 99.7% chance that the result is correct, but a 99.7% chance that if they
: were to run the same experiment again (with the same instruments), they
| t*******s
发帖数: 3031 | 4 主要疑问就是统计里给出概率的同时，都会给估计区间。但涉及西格玛的都是一个数值
，不带区间。
result
【在 s*******i 的大作中提到】
: 放狗便知的东西...
: http://www.lhc-closer.es/php/index.php?i=1&s=4&p=21&e=0
: Sigma is the decisive parameter of the Gaussian curve, a mathematical
: function that describes the distribution of data from many experiments.
: Citing a certain number of sigma directly translates into a probability.
: 1.5 sigma means just noise (backgroud), but three sigma is equivalent to a
: 99.75 percent chance that a future experiment will yield a compatible result
: . So something interesting has been observed, Well, technically it抯 not a
: 99.7% chance that the result is correct, but a 99.7% chance that if they
: were to run the same experiment again (with the same instruments), they
| s*******i
发帖数: 12823 | 5 你往那个网页的最下面看，有个例子
就是关于已知theory的standard deviation
【在 t*******s 的大作中提到】
: 我就是类似的这几段话没读懂。你能用统计公式解释下吗？谢谢你。先收包子把。
:
: result
| t*******s
发帖数: 3031 | 6 那个例子没提哪能算西格玛，直接来五个，还是描述性的。
【在 s*******i 的大作中提到】
: 你往那个网页的最下面看，有个例子
: 就是关于已知theory的standard deviation
| s*******i
发帖数: 12823 | 7 算法不就是按standard deviation算么
就是这么个东西嘛：sqrt(\sum_i (x_i - \bar{x})^2)
再要细说我也说不清了，俺就是个搞凝聚态的而已
【在 t*******s 的大作中提到】
: 那个例子没提哪能算西格玛，直接来五个，还是描述性的。
| t*******s
发帖数: 3031 | 8 这个公式算的是样本标准差用来做区间估计。用标准差来理解西格玛的话，好歹也需要
给个估计区间。大佬，您多说两句吧。
【在 s*******i 的大作中提到】
: 算法不就是按standard deviation算么
: 就是这么个东西嘛：sqrt(\sum_i (x_i - \bar{x})^2)
: 再要细说我也说不清了，俺就是个搞凝聚态的而已
|
|
