l****z
发帖数: 29846 | 1 Al-Qaida memo to Bin Laden warns of 'cunning methods' of US news networks
Al-Qaida spokesman Adam Gadahn a fan of 60 Minutes but said Fox News 'lacks
neutrality' and CBS is 'close to being unbiased'
Osama bin Laden pondered the merits of US television news channels as he
considered how to extract the best propaganda benefit from the tenth
anniversary of 9/11 last year, and concluded that CBS was "close to being
unbiased".
But an American-born media adviser for al-Qaeda warned Bin Laden to beware... 阅读全帖 |
|
c*********7
发帖数: 7607 | 2 【 以下文字转载自 shopping 讨论区 】
发信人: capricorn87 (老猫咪), 信区: shopping
标 题: W8测评：W8 Revealed - An Unbiased Dissection (转载)
发信站: BBS 未名空间站 (Sat Mar 5 17:54:53 2011, 美东)
全部内容
http://www.mitbbs.com/article_t/ebiz/33151493.html
希望对想要买而没有买，或者已经买了准备+硬件的版友有用
网上关于这个机子已经有很多hype，一直想买她但是对小本无爱，连SONY Z也一直属于
睡着的状态。
我对自用笔记本只注重质量，基本不注重价格，高端机有过 Thinkpad T41, T60, T60p
, T61p,
W500, W510, W700,X61s, x200s, X201s, X300.
Dell Alienware M11x, M15x, Precision 4400m
HP Elitebook w8540w
SONY Z 1190X, 1390X
W8总体感觉，是在同重量等级里面，算好... 阅读全帖 |
|
c********r
发帖数: 73 | 3 Consider a sequence X1,X2,......,Xn of Bernoulli trials, Here the Xi are iid
as X with Prob(X=1)=p,0
show that there exists no unbiased estimator for the odds ratio p/(1-p)
due next Thesday.
thank jiay |
|
J**Y
发帖数: 34 | 4 We can have more compact way to think about this. Suppose f(X) is an
unbiased estimator of odds ratio, where X=(x1,....,xn). Then
E[f(X)]=Sum_k[f(k)*C_nk*p^k*(1-p)^n-k], where C_nk is the combination
symbol. Because f(k)*C_nk is constant, let a_k denote it. Then
E[f(X)]=Sum_k[a_k*p^k*(1-p)^n-k]=p/1-p =>
Sum_k[a_k*p^k*(1-p)^n-k+1]=p, you then can show the equation
doesn't exist. |
|
g********n
发帖数: 2314 | 5 原来是'Performance profiling' could help to catch cheater 现在是 '
Performance profiling' could help to dispel doubts.
Why great Olympic feats raise suspicions
'Performance profiling' could help to dispel doubts.
Ewen Callaway
01 August 2012 Corrected: 03 August 2012
Chinese swimmer Ye Shiwen broke the world record for the women's 400-metre
individual medley event at the Olympic Games on 28 July.
L. NEAL /AFP / GETTY IMAGES
Article tools
print
email
rights & permissions
share/bookmark
At the Olympics,... 阅读全帖 |
|
p******x
发帖数: 441 | 6 得到一个strong at math but lack of clarity and knowledge on statistics的评语
，憋半天实在忍不住上来再吐槽一下。
Multicolinearity问题:
首先，最简单的模型 Y=Xb+e 的LS解是b_hat=(X’X)^(-1)X’Y， var (b_hat)=(X’X
)^(-1) sigma^2.
问题：什么是Multicolinearity，
答：如果承认X是rv，才能用”correlated “，否则只能用比较数学的linear
dependent，not of full column rank这种术语。
Multicolinearity又分2种，multicolinearity 和perfect multicolinearity，分别对
应的是X的column vectors 是 nearly linear dependent和 linear dependent(not
full ranked)，分别对应的结果就是 (X’X) 是ill-conditioned 和singular. ，前者
是(X’X)^(... 阅读全帖 |
|
s*********s
发帖数: 70 | 7 看来有人跟我问过同样的问题啊：
http://answers.yahoo.com/question/index?qid=20111130141546AAZHa
Resolved Question
Are vaccines tested in double blind placebo controlled studies?
I mean truly unbiased studies? Do you have any links to give proof so it's
not just someone's word or statement about it? I want something completely
unbiased to help settle a debate
1 year ago Report Abuse
grindl
Best Answer - Chosen by Asker
In order to do a double blind placebo controlled study with vaccines, one
group should be give... 阅读全帖 |
|
g****g
发帖数: 1828 | 8 In probability theory, the normal (or Gaussian) distribution, is a
continuous probability distribution that is often used as a first
approximation to describe real-valued random variables that tend to cluster
around a single mean value. The graph of the associated probability density
function is “bell”-shaped, and is known as the Gaussian function or bell
curve:[nb 1]
f(x) = \tfrac{1}{\sqrt{2\pi\sigma^2}}\; e^{ -\frac{(x-\mu)^2}{2\sigma^2}
},
where parameter μ is the mean (location of the pe... 阅读全帖 |
|
q*a
发帖数: 2330 | 9 ☆─────────────────────────────────────☆
jianglai (Veni, Vidi, Vici.) 于 (Thu Aug 2 02:54:30 2012, 美东) 提到:
http://www.nature.com/news/why-great-olympic-feats-raise-suspic
英帝堕落到什么地步了。。。
★ 发自iPhone App: ChineseWeb 7.3.1
☆─────────────────────────────────────☆
daye520 (哈哈) 于 (Thu Aug 2 02:56:00 2012, 美东) 提到:
罗切特每次都被拿出来做背景。
☆─────────────────────────────────────☆
michaelxiaga (南京中山陵) 于 (Thu Aug 2 02:58:53 2012, 美东) 提到:
回复里面有一个哥们写的不错
其实咱们在这里说有啥用, 就得用英文反驳white trash
☆─────────────────... 阅读全帖 |
|
i*******e
发帖数: 349 | 10 my $0.02。
BLUE里面的U=unbiased，unbiasedness是个finite sample的概念，consistency是个
asymptotic的概念，两者没有必然关系。
计量教材里面有很多estimator在finite sample里面是biased但是consistent。另外一
方面，有的estimator是unbiased但是不consistent，例如我用样本里面的第一个观测
值X1作为sample mean的estimator，是unbiased，但通常不是consistent的，因为在样
本趋向无穷大时，lim( |X1-mean(x)|>epsilon )=常数，该常数一般不为0。
另外，WLS是不是BLUE或者consistent当然要看DGP的假设。 |
|
a***r
发帖数: 420 | 11 正在复习Casella那本书上的data reduction和point estimation，相当的有点纠结啊
尤其关于Lehmann-Scheffe Theorem:
Unbiased estimators based on complete sufficient statistics are unique.
书上主要做了如下讨论：
Theorem 7.3.23: Let T be a complete sufficient statistic for a parameter
theta, and phi(T)be any estimator based only on T. Then phi(T) is the unique
best unbiased estimator of its expected value q(theta).
这个phi(T)，我的理解是, Rao-Blackwell里的,比如W(X) unbiased for q(theta), 那么
phi(T)=E(W(X)|T(X))就是一个UMVUE.
那么这个是不是可以理解为，对于一个分布p(x;theta)... 阅读全帖 |
|
s*********0
发帖数: 2045 | 12 记者自己不是没有责任。美国人的看法:
"throwaway account here. So my friend here in Beijing is a journalist for a
similar organization, and says that they actually did find a regulation they
ran foul of to kick them out. Their cameraman was unregistered and filmed
some footage in Tiananmen without a permit. In any case, pretty much
everyone here is probably breaking dozens of vague or obscure laws, so they
just need to pick one or the other and toss you out."
"Not to take away from the video, these jails are awful... 阅读全帖 |
|
m**e
发帖数: 857 | 13 【 以下文字转载自 Biology 讨论区 】
发信人: muce (muce), 信区: Biology
标 题: Re: 要求撤稿的
发信站: BBS 未名空间站 (Tue Aug 7 13:23:01 2012, 美东)
华人生物学家协会出面要求撤稿
http://www.cbisociety.org/
Nature should adhere to fact-based and unbiased reporting
Philip Campbell, Ph.D.
Editor-in-Chief, Nature
Dear Dr. Campbell:
We write on behalf of the Chinese Biological Investigators Society (CBIS) to
express our deep concern regarding a recent news article, titled "Why great
Olympic feats raise suspicions" (www.nature.com/news/why-great-ol... 阅读全帖 |
|
g**1
发帖数: 10330 | 14 Freeland demands ‘immediate release’ of detained Canadians Kovrig and
Spavor
http://www.theglobeandmail.com/politics/article-freeland-demands-release-of-detained-canadians/
STEVEN CHASE
PUBLISHED DECEMBER 21, 2018
UPDATED 2 HOURS AGO
Canada is now calling for the “immediate release” of two Canadians
detained by China after the Vancouver arrest of Huawei executive Meng
Wanzhou in what amounts to a significant shift in tone by Ottawa toward
Beijing.
Foreign Affairs Minister Chrystia Freeland made ... 阅读全帖 |
|
W*******n
发帖数: 4140 | 15 NYS Workers' Comp: How Alpha 3T MRI Fouls Even on The DVDs?
By Limin Wang
March 03, 2020
Introduction:
This realistic story mainly tells how a medical diagnostic imaging MRI
facility, Alpha 3T MRI (145 East 32 Street, Ground Floor, New York, NY 10016
. Phone: (212) 868-9210), gave me, an apparent workers’ compensation case (
NYS WCB# G2029240) patient but actually a victim of attempted murders, a DVD
completely blank in its content but with my information printed on the disk
skin, soon after the... 阅读全帖 |
|
l****z
发帖数: 29846 | 16 Hollywood’s Vision of Conservatives: Nasty, Filled With Hate, And Near
Psychotic
April 5, 2012 by Warner Todd Huston
Aaron Sorkin is about to unleash his vision of what conservatives and
Republicans are like in a new HBO series called The Newsroom and it ain’t
going to be pretty. It seems like more proof that liberal Hollyweirders don
’t know anything about conservatives. They are all Pauline Kaels now.
The premise of the series gives us a famous, trusted, objective, unbiased
cable network new... 阅读全帖 |
|
c******c
发帖数: 418 | 17 It's just a " frikin' " joke, hehe.
But I seriously doubt you really understand that american lady's point.
She never suggested that "freedom of speech" means everything comes from the
media is true or unbiased. Rather, what she implied is that in a society
with "freedom of speech", you have access to all sort of information, biased
or unbiased. An intelligent person should be able to digest these
information and form his/her own opinion, instead of believing one way or
the other.
So when she sa |
|
w*p
发帖数: 28 | 18 看看下面这个牛人的建议 ----
when you fight it in court keep in mind a few tings....
(I am NOT providing legal advice, only information)
if they paced you, they have to have produce a certified calibration of the
car speedo done within 6 months, if they dont have it then you walk because
their speed measureing device has not been proven within a legal degree of
certainty as accurate..as LONG AS YOU know to ASK FOR IT.
Same with radar, they need to have a certification that the tuning forks
used to test the ... 阅读全帖 |
|
b*****d
发帖数: 61690 | 19 http://www.cbisociety.org/
Nature should adhere to fact-based and unbiased reporting
Philip Campbell, Ph.D.
Editor-in-Chief, Nature
Dear Dr. Campbell:
We write on behalf of the Chinese Biological Investigators Society (CBIS) to
express our deep concern regarding a recent news article, titled "Why great
Olympic feats raise suspicions" (www.nature.com/news/why-great-olympic-
feats-raise-suspicions-1.11109, August 1, 2012), in which Ewen Callaway
discussed the performance of Ye Shiwen, a 16-year ol... 阅读全帖 |
|
n*****n
发帖数: 1029 | 20 刚才有网上ID为你背书过你不是做agent的，那么我在这里要向你道歉。因为如果
你的观点是与个人利益没有关系的，那么你的观点就可以被认为是unbiased，而
我们俩就仅仅是观点上的不同了。所以我要向怀疑你的发帖动机的行为道歉。
说到关于房地产投资，其实俺的运气还不错，还没有出现过negative cash
flow的，即便是在房价高企的硅谷，再加上硅谷动辄一年就上涨十万的房子value，
呵呵，所以应该说俺对于房地产风险的提醒其实与俺的个人经历完全无关，所以
俺的观点也是unbiased的。
间,
. |
|
c******a
发帖数: 10623 | 21 ☆─────────────────────────────────────☆
Drake (气宗：六脉神剑) 于 (Fri Jun 28 09:07:32 2013, 美东) 提到:
告巴里奥斯了
不知道最终会啥结果
☆─────────────────────────────────────☆
Bernanke (Ben) 于 (Fri Jun 28 09:17:34 2013, 美东) 提到:
恒大以为自己官商勾结的模式在国内无敌也可以横行世界。
☆─────────────────────────────────────☆
sandyfriend (superman) 于 (Fri Jun 28 09:18:37 2013, 美东) 提到:
不太清楚 正式的文本怎么样
但是怎么感觉有点chiness english 感觉。
英文部分
http://sports.sina.com.cn/j/2013-06-28/20256643659.shtml
☆─────────────────────────────────────☆
emsct (12... 阅读全帖 |
|
l**a
发帖数: 12455 | 22 你unbiased? LMFAO
整个版上最biased就数你
period
别以为大家不知道你是什么粉什么黑，懒得说就是了，当年你做版主的时候，版上的污
言秽语，比粪坑还臭，不要以为大家都没有看到，都不记得了，粉谁黑谁，大方承认，
还算个爷们，不要遮遮掩掩，打着姜粉的旗号，实为某黑，没意思，就这样，还要标榜
自己unbiased，以为别人都眼瞎了看不到你当年做版主时候的所作所为？ |
|
c***t
发帖数: 383 | 23 ☆─────────────────────────────────────☆
gjstx (gjstx) 于 (Wed Apr 24 04:14:02 2013, 美东) 提到:
对朱令的案件关心了很久。最初是在报上看到清华女生得了怪病生命垂危，通过互联网
的帮助被确诊为铊中毒。以后又读到清华另一女生孙维被怀疑为投毒人，但因为权力的
干预而逍遥法外。再后来又陆续了解到案情和受害者家庭情况。这一阵子网上又开始炒
作该案。因为对这个案子的关心，我也思考过很久，也读到过这十几年来涉情人们的种
种反应。通过思考我认为，孙维的涉嫌可能性很低。这个案子需要换一个思路去解决。
这篇文章中，我将讨论孙维作案可能性低的原因。
首先要确立到底是几次中毒的问题。说一次中毒的目前来看缺乏依据。另一个问题是，
如果是二次中毒的话，第二次中毒发生在什么时间段。有人说两次中毒都发生在朱令第
一次发病前。但是目前我还没有发现临床病例可以支持这个说法。从临床表现来看，第
二次中毒应该发生在朱令返校后到二次发病前这段时间。当然，还有一个毒源地问题。
到底是一个毒源还是两个毒源？从常理分析，如果是人为投毒，两个... 阅读全帖 |
|
l**********t
发帖数: 5754 | 24
welcome to the training camp :)
even 逻辑性很强的老E is just human (he may fantasize with ID though) .
There maybe impartial & unbiased science, but there is no unbiased
scientists. If you read a book promoting "evolution theory", there is no
doubt that the theory will be touted as THE theory that covers all
biological disciplines from immunology to pharma-chem. |
|
l**********t
发帖数: 5754 | 25
I made a generic statement about a common wisdom without targeting anyone or anyting
. Did anyone come forward to claim to be the target? Why would it become a subject of complaining if you are unbiased as you claim?
If one ID calles anther ID mad dog -- that would be a direct personal attack
and should be penalized according to the forum rule. If you are unbiased, you shall find out these real PAs and report to the moderators.
BTW, nice photo editing. I'm going to save a copy. |
|
j*******7
发帖数: 6300 | 26 Stepping Toward God With a Wallet and a Dollar
I’ve been talking to my dad about the existence of God for several years.
He describes himself as an agnostic who leans toward atheism, but it’s
clear from our discussions he’s as far from theism as anyone could be. He’
s also an evidentialist who worked as a police officer and detective for
nearly 30 years. We tend to think a lot alike (I was also an atheist
detective until the age of 35), and I can relate to his skepticism. Many
years ago, while w... 阅读全帖 |
|
m**e
发帖数: 857 | 27 华人生物学家协会出面要求撤稿
http://www.cbisociety.org/
Nature should adhere to fact-based and unbiased reporting
Philip Campbell, Ph.D.
Editor-in-Chief, Nature
Dear Dr. Campbell:
We write on behalf of the Chinese Biological Investigators Society (CBIS) to
express our deep concern regarding a recent news article, titled "Why great
Olympic feats raise suspicions" (www.nature.com/news/why-great-olympic-
feats-raise-suspicions-1.11109, August 1, 2012), in which Ewen Callaway
discussed the performance of Ye Shiwe... 阅读全帖 |
|
D*a
发帖数: 6830 | 28 为什么就是 unbiased estimate了？那我要是取了五个样本，同样可以得出一个SD啊。
当然我们大家都会说五个不够。但是从统计学上怎么理解最后一句话“ this standard
error is an unbiased estimate of the standard deviation of the height of
chinese females.”？
)
of |
|
a**m
发帖数: 184 | 29 Being unbiased means that the estimate from the sample space is equal to the
real value in the entire population. The true value derived from the sample
population (here the standard error) might be inaccurate depending on size
of the samples.
为什么就是 unbiased estimate了？那我要是取了五个样本，同样可以得出一个SD啊。
当然我们大家都会说五个不够。但是从统计学上怎么理解最后一句话“ this sta.....
...
★ Sent from iPhone App: iReader Mitbbs Lite 7.56 |
|
D*a
发帖数: 6830 | 30 为什么就是 unbiased estimate了？那我要是取了五个样本，同样可以得出一个SD啊。
当然我们大家都会说五个不够。但是从统计学上怎么理解最后一句话“ this standard
error is an unbiased estimate of the standard deviation of the height of
chinese females.”？
)
of |
|
a**m
发帖数: 184 | 31 Being unbiased means that the estimate from the sample space is equal to the
real value in the entire population. The true value derived from the sample
population (here the standard error) might be inaccurate depending on size
of the samples.
为什么就是 unbiased estimate了？那我要是取了五个样本，同样可以得出一个SD啊。
当然我们大家都会说五个不够。但是从统计学上怎么理解最后一句话“ this sta.....
...
★ Sent from iPhone App: iReader Mitbbs Lite 7.56 |
|
g*****n
发帖数: 241 | 32 exofacial tunnel of xxx receptor, pocket
另外an unbiased method里的unbiased怎么翻译比较好
谢谢 |
|
i*******e
发帖数: 349 | 33 My understanding is the "best" part in BLUE refers to a estimator having
minimum variance among the class of linear unbiased estimators (LUE), which
is similar to the concept of UMUE (uniformly minimum-variance unbiased
estimator). A consistent but biased estimator does not belong to the class
of LUE, thus can never be the best in the class. Meanwhile, a BLUE can be
consistent, for instance WLS under assumptions below. I am not sure a BLUE
or UMUE must be consistent. There may exist counter exam |
|
f*******r
发帖数: 257 | 34 We need to note that BLUE means "best"' linear unbiased estimator. It
guarantees unbiasedness, but not consistency. I agree that under certain
assumptions, WLS or GLS should be consistent, but that has nothing to
do with it being BLUE.
"Best" is sometimes over-emphasized. It just means it will have the
lowest standard error among all the unbiased estimators.
This does not come in without a price: you make
assumptions about the error structure to gain efficiency. In reality, we
don't care |
|
y****e
发帖数: 28 | 35 I don't think N is a random variable under the classical statistical
framework. N is an UNKNOWN parameter. The expectation of N does not mean
much.
When we talked about an unbiased estimate T of N, we are not talking about
the expectation of N, however, we are talking about the expectation of T
such that E(T)=N, where T is random variable depending on the random
variable n.
Use the method of moment as given by many other posters, we can know that E(
n)=(N+1)/2,
Therefore, if we define T to be 2*... 阅读全帖 |
|
on
发帖数: 199 | 36 it's easy to get an exponential weighted moving average:
mean(t) = q * mean( t-1) + (1-q) * x(t)
where x(1), x(2), ... are the data points.
My question is: how to get an "unbiased" estimate for standard devidation? A
naive formula would be:
var(t) = q * var( t-1) + (1-q) * ( x(t) - mean(t) )^2
but I don't think this is an unbiased estimate, and my simulation says it is
not.
any one knows or a link to reference please? many thanks. |
|
A*******s
发帖数: 3942 | 37 你这个weighted之后的estimate，是unbiased的么？如果是unbiased的，是BLUE么？如
果是biased的，那么prediction error variance会减少么？有没有证明？ |
|
a*****3
发帖数: 601 | 38 再为陈老师支一招career path: 陈老师既然师从大师，科班出身，能坚持思考十多年
，那就姑且屈尊在主流杂志上每年灌几篇文章，想必总不是难事。
等到被主流社会jsm接受以后，树立起江湖地位，再慢慢抛出自己的pra方法论，著书立
说，毁人不倦；在招收几个phd student. 比如drburnie,让其专门研究PRA在生活中的
实际应用，研究不出来不让毕业。
如果‘精算师’来报考陈老师的phd,毕业论文题目就叫
“关于weighted之后的estimate，是unbiased的么？如果是unbiased的，是BLUE么？如
果是biased的，那么prediction error variance会减少么”
整不出来，不让毕业。
如: 果是biased的，那么prediction error variance会减少么？有没有证明？ |
|
on
发帖数: 199 | 39 Thanks.
I understand the meaning of dimensionality, etc, and why we call it degree
of freedom.
What puzzled or amazed me is this: in many estimators, when we adjust for
degree of freedom, then we get an unbiased estimator. A simple example is
the unbiased estimator for std has divisor N-1 instead of N where N-1 is the
degree of freedom. I can go through the algebra, but the question is: what
intuition explain that the role of degree of freedom? Or is it just another
example of the grace of math? |
|
d******e
发帖数: 7844 | 40 其实你完全不懂validation的意义。呵呵。
都是估计也是有很大不同的，你应该没听说过有一种东西叫做bias-variance trade
off。estimator的性能取决于估计的bias和估计的variance。
你以为估计是unbiased和low biased就是好的？用成百山千阶的多项式几乎可以完美
fit训练数据，bias极小，但variance极大，这种model的脑残程度跟大师和大师的
model真的有一拼啊。
呵呵。顺便多告诉你点知识，对于一个3维以上高斯分布，如果在意L2 risk下的性能的话
，最好的mean的estimator并不是unbiased的sample mean。不过这个结论对于你可能太
高端了，感兴趣的话就自己去看看吧。
http://en.wikipedia.org/wiki/James%E2%80%93Stein_estimator
没有意义的缘故。
用B去 |
|
h***i
发帖数: 3844 | 41 对于公式 phat(1-phat)/n ，它与 p(1-p)/n 之间的关系是不确定的，可能大也
可能小，这种情况下，correction是不准确的。
建议你复习复习unbiased estimator，用N－１就是要得到一个unbiased estimator of
var of phat而已。这你还有啥疑问？而且，你那句，var of phat= phat（１－phat
）／n，你忘记左边加hat了. |
|
h***i
发帖数: 3844 | 42 unbiased estimator of variance,
say, you have a variance estimator of var(phat), name it has, hat(var(phat))
so, unbiased estimator means:
E(hat(var(phat)))=var(phat)
你的example是一个样本而已.如果你再不明白，就找本统计基础教材翻翻吧。 |
|
d********h
发帖数: 2048 | 43 你说的是另一种分布，p1,p2,...pn, 每一个都是binomial,这时，variable是p(p1,p2,
..)；现在
我们只关注p1,variable是x(0,1,0..)。
p1是基于1000个Bernoulli分布，根据这1000个sample size，我们是足以得到p1_hat,
p1的variance是根据p1_hat*(1-p1_hat)来估算的，也就是说对于p1的variance，它是
类似于单样本的一个p1_hat.如果是continuous normal的话，p1是基于1000个值的，(
x1-p1)^2+....
另外的问题就是当p1_hat=0.5时，corrected variance超出了p1的最大范围。
我的看法是，p*(1-p)/(n-1)做为correction是有问题的，这也是为什么你很难看到
unbiased binomial estimator的说法，在讨论binomial的，更多的提法是sample
proportion是unbiased，而不提variance。 |
|
h***i
发帖数: 3844 | 44 对于公式 phat(1-phat)/n ，它与 p(1-p)/n 之间的关系是不确定的，可能大也
可能小，这种情况下，correction是不准确的。
建议你复习复习unbiased estimator，用N－１就是要得到一个unbiased estimator of
var of phat而已。这你还有啥疑问？而且，你那句，var of phat= phat（１－phat
）／n，你忘记左边加hat了. |
|
h***i
发帖数: 3844 | 45 unbiased estimator of variance,
say, you have a variance estimator of var(phat), name it has, hat(var(phat))
so, unbiased estimator means:
E(hat(var(phat)))=var(phat)
你的example是一个样本而已.如果你再不明白，就找本统计基础教材翻翻吧。 |
|
d********h
发帖数: 2048 | 46 你说的是另一种分布，p1,p2,...pn, 每一个都是binomial,这时，variable是p(p1,p2,
..)；现在
我们只关注p1,variable是x(0,1,0..)。
p1是基于1000个Bernoulli分布，根据这1000个sample size，我们是足以得到p1_hat,
p1的variance是根据p1_hat*(1-p1_hat)来估算的，也就是说对于p1的variance，它是
类似于单样本的一个p1_hat.如果是continuous normal的话，p1是基于1000个值的，(
x1-p1)^2+....
另外的问题就是当p1_hat=0.5时，corrected variance超出了p1的最大范围。
我的看法是，p*(1-p)/(n-1)做为correction是有问题的，这也是为什么你很难看到
unbiased binomial estimator的说法，在讨论binomial的，更多的提法是sample
proportion是unbiased，而不提variance。 |
|
A*******s
发帖数: 3942 | 47 我的两分钱--这是个面试必问的问题，我觉得答好不容易，答得全面了面试官还会容易
confused...
text说的都没错，但是需要了解为什么这么说的前提，以及实际面对的data和model的
性质。比如说“with multicollinearity, model's estimates are still unbiased
but have higher variance.” 这话自然没错，但是unbiased estimates的前提是你的
model没有mis-specification，或者mis-specification没有大的影响。如果real
model有10个variable但你只包括了9个，有bias。如果real model是nonlinear的但你
搞了个linear的，有bias。而且real model很可能是由一堆latent variables'
nonlinear functions组成的，在这种情况下，即使你把所有能观察到的variable都加
进去，也不能把所有的latent variables和他们的functional forms都包括到，m... 阅读全帖 |
|
D*********Y
发帖数: 3382 | 48 Where does statistical error come from?
A little background:
Regression does least squares
solution to least squares is linear combination of error + truth
Hence normality sets in and CLT sets in
E(alpha-hat) = alpha (This is called unbiased)
E(beta-hat) = beta (This is called unbiased)
Thus accuracy of alpha and beta depend on where the data is collected
more spread out X's generate better slope estimates
But might introduce unwanted data to problem. Hence design of where to put
the X's must ta... 阅读全帖 |
|
g********n
发帖数: 2314 | 49 by SweatStudio June 9, 2009 4:20 PM PDT
I'm still looking for unbiased reviews! Here's how I would score the
PALM PRE vs iPHONE 3GS comparison according to the features that are
important to ME.
1. PHYSICAL KEYBOARD- I would like the feel of the real thing and I
think it's quicker for texting. Palm Pre 2 pt., iPhone 3Gs 1 pt..
2. VIDEO from my phone. Pre 0, iPhone 3Gs 1. (If it was HD then that
would be plus 3 points!)
3. LONG BATTERY life. Pre 1.5 pts, iPhone 3Gs 1 pt. (Pre has a slight
advanta... 阅读全帖 |
|
d*******t
发帖数: 2 | 50 我在读高中，12年纪。我从小就喜欢中文，所以我的中文可以写。我这是第一次来到这
个地方里。我很喜欢中国，所以我从小就学习过中文，但是我没有去过中国，我想以后
可以去。
我在美国受到很多教育，包括对中国和很多的communism的教育。这些教育都告诉我，
中国，苏联，和别的很多communism国家都很邪恶，很坏。我从小就得到这样的教育，
没有别的另外的声音。所以从小学我就被告诉中国苏联没有自由，新闻的自由，语言的
自由，中国苏联还有north korea都很穷，饿的人死， 等等。
我小的时候没有问题，应为我不会去问我自己这个教育对不对。但是我很喜欢看书，很
多时候我不喜欢看美国的书的新闻，喜欢看外国的，应为我有时候不相信美国的书和新
闻（虽然我们国家的很多人都觉得美国的书和新闻是最fair,unbiased的）。后来我很
慢发现其实我的教育并没有告诉我精确的东西，中国苏联还有north korea都不是那样
，不是那样邪恶，等等。这些东西，如果我不看外国的书和新闻我不会被告诉的。比如
我对中国的历史很性趣，我看过中国的communist revolution,还有中国以前的总统Mao
... 阅读全帖 |
|
