z*******h
发帖数: 346 | 1 把佛山小女孩事件作为一个random sample from binomial distribution B(19, p),
where drawing a 道德败坏 person means success, and drawing a 好人 means
failure. Since 18 out of 19 people are 道德败坏, maximum likelihood
estimation of p is then 18/19, which is far greater than 1/10000 as claimed
by some 50c ID here. |
d****o
发帖数: 32610 | 2 技术角度来说，这19个人又不是iid
claimed
【在 z*******h 的大作中提到】
: 把佛山小女孩事件作为一个random sample from binomial distribution B(19, p),
: where drawing a 道德败坏 person means success, and drawing a 好人 means
: failure. Since 18 out of 19 people are 道德败坏, maximum likelihood
: estimation of p is then 18/19, which is far greater than 1/10000 as claimed
: by some 50c ID here.
|
l******t
发帖数: 55733 | |
z*******h
发帖数: 346 | 4 why?
【在 d****o 的大作中提到】
: 技术角度来说，这19个人又不是iid
:
: claimed
|
d****o
发帖数: 32610 | 5 不独立啊
前面的人的行为肯定是对后面的人有影响的
【在 z*******h 的大作中提到】
: why?
|
z*******h
发帖数: 346 | 6 Not sure about the confidence interval. Can you calculate it?
【在 l******t 的大作中提到】
: 19能构成针对14亿的统计学意义吗？
|
l******t
发帖数: 55733 | 7
it will kill some of my brain cells and doesnt deserve it at all. Let it be.
【在 z*******h 的大作中提到】
: Not sure about the confidence interval. Can you calculate it?
|
z*******h
发帖数: 346 | 8 In fact, you can't calculate it unless you make some assumptions about the
geographical distribution of good people in China. But since this is not an
isolated event, my hunch is that the CI will by no means include 1/10000.
that is all I want to say.
be.
【在 l******t 的大作中提到】
:
: it will kill some of my brain cells and doesnt deserve it at all. Let it be.
|
I********l
发帖数: 8702 | 9 First of all, this accident is NOT a random sample as you presume. Secondly,
the sample size of 19 people is simply way too low to predict a population
as large as 1.4 billion.
You may randomly select a reasonable number of cases from a pool of total
accidents in mainland in a given year and see if immoral behavior is
significantly present in these cases.
However, Even if the result is significant, we can only cautiously conclude
that the vehicle drivers in the situation of accident are more likely to
engage in immoral behavior. We cannot make any inference that Chinese people
are immoral, since the population of drivers could be distinctly different
from the whole population of Chinese people.
claimed
【在 z*******h 的大作中提到】
: 把佛山小女孩事件作为一个random sample from binomial distribution B(19, p),
: where drawing a 道德败坏 person means success, and drawing a 好人 means
: failure. Since 18 out of 19 people are 道德败坏, maximum likelihood
: estimation of p is then 18/19, which is far greater than 1/10000 as claimed
: by some 50c ID here.
|
I********e
发帖数: 1843 | 10 1肯定是高估了，具体百分比可以参考这个版上小将和五毛的并集占全部注册用户的比
例。
claimed
【在 z*******h 的大作中提到】
: 把佛山小女孩事件作为一个random sample from binomial distribution B(19, p),
: where drawing a 道德败坏 person means success, and drawing a 好人 means
: failure. Since 18 out of 19 people are 道德败坏, maximum likelihood
: estimation of p is then 18/19, which is far greater than 1/10000 as claimed
: by some 50c ID here.
|
h*****s
发帖数: 228 | 11 小右的观点是不救人是普世有道理，小左认为是30年该开造成道德败坏 |
w********l
发帖数: 11447 | 12 晕死，先不说别的，你这也不是binomial啊，至少也是个negative binomial. |
