k****r
发帖数: 24 | 1 AGENDA – TUESDAY, SEPTEMBER 20, 2011
8:00 a.m. Welcome and Introductions of the 2011 NIH Director’s Pioneer
Awardees
8:30 a.m. Cheng Chi Lee, Ph.D.
University of Texas Health Science Center at Houston
5’-AMP-Induced Deep Hypometabolism in Mammals: Insight Into Its Mechanism
and Potential Applications
9:00 a.m. Karla Kirkegaard, Ph.D.
Stanford University School of Medicine
Quenching Rainbows: Suppressing Diversity in RNA Viruses
9:30 a.m. Evgeny A. Nudler, Ph.D.
New York University Sc... 阅读全帖 |
|
b*******n
发帖数: 8420 | 2 去大公司做实验的基本上也都是有两把刷子的，至少得发个PNAS或者JCI级别的文章。
而且这帮人也相对更unbiased，如果这帮人重复几遍用了各种试剂和条件都做不出来，
我觉得学术界里的人能真正重复出来的可能性更小。 |
|
p*****m
发帖数: 7030 | 3 所以你也承认不是什么问题都可以在一无所知状态下光靠逻辑给分析出来咯？实际上这
样的例子多了，任何一个通过unbiased screen（不管是biochem, genetic,还是
bioinformatic screen)找到的东西你都不可能在未知状态下猜出来
至于你说的这个数学家，不就是佩雷尔曼证明彭加莱猜想么。我虽然不是学数学的，也
知道你这个例子不说明啥，佩雷尔曼已经证明了，他只不过懒得把具体的步骤全部都写
出来而已。和你说的生物问题完全是两码事。而且数学和自然科学的研究方法也完全没
有可比性。 |
|
p*****m
发帖数: 7030 | 4 我真不知道我说的怎么trivial了，在我看来screen这种unbiased的研究方法才是最有
挑战性的，等一切数据都ready了，足够让你form一个hypothesis再去验证了，那最困
难的部分已经完成了。
补充彭加莱猜想证明的就是丘成桐的弟子，他当然会这么说了
数学和自然科学的本质区别，就是前者是纯粹逻辑驱动的，后者至少在相当部分上是数
据驱动的，没有观察和实验，光靠归纳和演绎你什么都得不到。万有引力是观测+演绎
出来的还是闭着门脑子里蹦出来的？相对论呢？进化论呢？现代分子生物学呢？ |
|
x*****4
发帖数: 27 | 5 还有为什么“screen这种unbiased的研究方法才是最有挑战性的”，说句实话这个我不
是很懂。你是做SELECTION的吗？ 我们这个领域的我觉得没有什么SCREEN啊。为什么这
个是最挑战行的？ 是设计实验难？还是工作量巨大耗钱？ |
|
w********f
发帖数: 60 | 6 harway, 按照你的设想,你希望客观地了解这篇文章作者的立场和观点,那么你应该认真
看看comments
It is a shame to see Nature, which nearly all scientists, including myself,
regard as the one of the most prestigious and influential physical science
magazines to publish a thinly-veiled biased article like this. Granted, this
is not a peer-reviewed scientific article and did not go through the
scrutiny of picking referees. But to serve as a channel for the general
populous to be in touch with and appreciate sciences, the authors and
editor... 阅读全帖 |
|
f******r
发帖数: 437 | 7 请你认真读读这个，我觉得这回复 comments的作者水平很高，
很遗憾的是nature 偷偷的把这个回复给删了， 留下很多中国人名字的谩骂贴。
我非常支持这个回帖作者的观点， 应该用事实和科学的方法回击nature,
nature 作为一个科学界的顶级杂志，发表这种文章， 必须要付出代价.
Lai jiang's comment (#47487) has been "anomalously" deleted by online editor
. I re-post it here:
Lai Jiang said:
It is a shame to see Nature, which nearly all scientists, including myself,
regard as the one of the most prestigious and influential physical science
magazines to publish a thinly-veiled biased article like this. Granted, this
is not a pe... 阅读全帖 |
|
b**********D
发帖数: 145 | 8 Jianglai 的回复
It is a shame to see Nature, which nearly all scientists, including myself,
regard as the one of the most prestigious and influential physical science
magazines to publish a thinly-veiled biased article like this. Granted, this
is not a peer-reviewed scientific article and did not go through the
scrutiny of picking referees. But to serve as a channel for the general
populous to be in touch with and appreciate sciences, the authors and
editors should at least present the readers with... 阅读全帖 |
|
i****g
发帖数: 3896 | 9 http://blog.sciencenet.cn/blog-2237-598917.html
致《自然》杂志总编的信：有关叶诗文的新闻报道 精选
英文原信附后，大意如下：
斐尔,
你可能因Ewen Callaway对叶诗文的报道而被email狂炸，过去二十小时，给你
email的人里面小部分也给我来信。
如果你奇怪《自然》非本质部分一篇报道为何带来这么大的反应，你应该高兴
中文读者比世界其他读者更看重你们的新闻报道，与科学相关的（即使关系很小）也可
能重于《纽约时报》，中文媒体报道用你们的新闻也远多于一般西方媒体用你们的新闻。
Callaway报道最好也是草率、最差是种族偏见：1)最初的副标题暗示叶可能舞
弊; 2)Callaway用了两件事实说明叶惊人地异常，而两件都错了; 3)Callaway没咨询意
见不同的专家，导致报道不平衡，低于公平报道的最低标准。所以，Callaway至少不负
责任，可能太快就暗示中国运动员容易舞弊。他肯定没有达到新闻报道的通常标准。
我很高兴看到在我草拟此信的过程中，《自然》可能意识到了原副标题... 阅读全帖 |
|
b****y
发帖数: 81 | 10 strongly sp!
well done
http://blog.sciencenet.cn/blog-2237-598917.html
致《自然》杂志总编的信：有关叶诗文的新闻报道 精选
英文原信附后，大意如下：
斐尔,
你可能因Ewen Callaway对叶诗文的报道而被email狂炸，过去二十小时，给你
email的人里面小部分也给我来信。
如果你奇怪《自然》非本质部分一篇报道为何带来这么大的反应，你应该高兴
中文读者比世界其他读者更看重你们的新闻报道，与科学相关的（即使关系很小）也可
能重于《纽约时报》，中文媒体报道用你们的新闻也远多于一般西方媒体用你们的新闻。
Callaway报道最好也是草率、最差是种族偏见：1)最初的副标题暗示叶可能舞
弊; 2)Callaway用了两件事实说明叶惊人地异常，而两件都错了; 3)Callaway没咨询意
见不同的专家，导致报道不平衡，低于公平报道的最低标准。所以，Callaway至少不负
责任，可能太快就暗示中国运动员容易舞弊。他肯定没有达到新闻报道的通常标准。
我很高兴看到在... 阅读全帖 |
|
l***s
发帖数: 841 | 11 But any detection system would have the same issue. For example, you can
never say that all RNA molecules are hybridized with the same sensitivity
and specificity using nannostring probes. Actually, qPCR is considered more
unbiased compared to probe hybridization. |
|
a**m
发帖数: 184 | 12 laugh
lz was talking about standard error not standard error of the mean
standard error is an estimate of standard deviation
say, you cannot get the standard deviation of the height of chinese women,
cuz you simply cannot sample all of them
however, you can sample (btw, here "sample" refers to measure their height)
1000 of them and get the standard deviation, which, to be more technical,
should be called the standard error.
and this standard error is an unbiased estimate of the standard deviatio... 阅读全帖 |
|
a**m
发帖数: 184 | 13 laugh
lz was talking about standard error not standard error of the mean
standard error is an estimate of standard deviation
say, you cannot get the standard deviation of the height of chinese women,
cuz you simply cannot sample all of them
however, you can sample (btw, here "sample" refers to measure their height)
1000 of them and get the standard deviation, which, to be more technical,
should be called the standard error.
and this standard error is an unbiased estimate of the standard deviatio... 阅读全帖 |
|
E**********t
发帖数: 56 | 14 首先，我觉得当你做过一段时间某一个实验以后，逐渐积累了经验，也就相对容易判断
实验的可靠性。有些实验结果最后给出的如果只是柱形图，那这中间可以做的事情太多
也太容易，但有些实验，实验结果本身比较难以修改，可能会相对可信些。
另外，我同意之前有个网友提到的观点，这个和实验室的PI关系可能比较大。一般来说
，如果一个实验室长期能够坚持做一个可延续的方向，有多篇工作发表，我比较倾向于
相信他们的结果。原因一是对于任何一个领域或者简单到一个蛋白，如果没有一段时间
的积累，很有可能对获得的结果产生错误的判断，这也是为什么杂志愿意接受一些
established的研究人员的文章。另外，这样的PI也会注意自己在本领域的reputation
，所以可能轻易不会冒险去主动作假。
一般来说，背靠背在同一期杂志，从不同实验室发表的文章比较可信。同样道理，如果
一个文章被大量引用，那么他的主要观点的可信性就更好些。
还有，我觉得如果实验最初是通过unbiased的筛选获得的，那么结果多数可信些。
最后，如果数据需要公开提交，比方说microarray的结果，这些结果就摆在那里，所
以可信度自然也应该好些。
至... 阅读全帖 |
|
h*******g
发帖数: 2201 | 15 This is not the first example of Nobel prize awarded to someone who does not
deserve it(for example, read about the discovery of Pulsar in Astronomy),
and will not be the last. A true scientist will not be so much puzzled by
these prizes rather than immersed in doing the science he or she loves.
These prizes are intended to measure the impact of scientific discovery of
scientists, and if the objective impact of scientists' work is not reflected
unbiased by these prizes, it is the failure of thes... 阅读全帖 |
|
s******y
发帖数: 28562 | 16 版上火药味好浓啊，大家看看文章散散心吧。
新出的文章认为actin 的总体动态以及相关的serum response factor 是一个生理时钟。
Cell. 2013 Jan 31;152(3):492-503. doi: 10.1016/j.cell.2012.12.027.
Blood-borne circadian signal stimulates daily oscillations in actin dynamics
and SRF activity.
Gerber A, Esnault C, Aubert G, Treisman R, Pralong F, Schibler U.
Source
Department of Molecular Biology, Sciences III, University of Geneva, and
National Centre of Competence in Research Frontiers in Genetics, 1211 Geneva
, Switzerland.
Abstract
In peripheral ti... 阅读全帖 |
|
l**********1
发帖数: 5204 | 17 非植物 或哺乳的数据库区别也 植物的也 一样在完善
关键是楼主有无NGS and HMM （Hidden Markov Models 的背景或能找到那种背景的
合作人
pls refer
PMID 23435661
by Van der Does D et al., (2013).
Salicylic acid suppresses jasmonic acid signaling downstream of SCFCOI1-JAZ
by targeting GCC promoter motifs via transcription factor ORA59.
Plant Cell. 25: 744-61.
Abstract:
ignored
In silico promoter analysis of the SA/JA crosstalk transcriptome revealed
that the 1-kb promoter regions of JA-responsive genes that are suppressed by
SA are significantl... 阅读全帖 |
|
l*******i
发帖数: 153 | 18 我觉得你应该学习一下啥叫“Conflict of interest”。
下面一段话是直接摘自science的：
To meet its responsibility to readers and to the public to provide clear and
unbiased scientific results and analyses, Science believes that manuscripts
(including Brevia, Essays, Perspectives, Policy Forums, Reports, Research
Articles, Reviews, and Viewpoints) should be accompanied by clear
disclosures from all authors of the nature and level of their contribution
to the article, their understanding regarding the obligation to share data
a... 阅读全帖 |
|
s******s
发帖数: 13035 | 19 right, 这个找本统计分析书看到下半本就知道了。有一种东西
叫做minimum variance unbiased estimator (MVUE)，意思比较直
接。Turn out, 可以证明，对正态分布来说，sample的mean和var
恰好是population的mean和var的MVUE, 其他的statistics可能有其他
的好性质，但是MVUE听上去多爽啊，所以回到stat101, 大家
开始都学mean, var |
|
s******s
发帖数: 13035 | 20 靠，我说了这么多，你都当废话了？！
算数平均是Normal的MVUE, 这个还不深刻啊。在这么多各式各样的
statistics里面，有很多estimator都是有biased，不准确；除去
这些，剩下的一大堆unbiased的estimator里面，各个的方差有大
有小，未必精确。这个MVUE就是准确的estimator里面最精确的一
个，这个多么伟大的性质啊！ |
|
f**********e
发帖数: 1994 | 21 那大老来做个题。有什么分布的 sample mean 不是真正的 mean 的 unbiased
estimator？或是他们的 mvue 是别的函数？柯西分布这种怪东西不算 |
|
s********n
发帖数: 2939 | 22 现在这种例子越来越多了
http://www.nytimes.com/2014/06/05/health/in-first-quick-dna-tes
In a First, Test of DNA Finds Root of Illness
Joshua Osborn, 14, lay in a coma at American Family Children’s Hospital in
Madison, Wis. For weeks his brain had been swelling with fluid, and a
battery of tests had failed to reveal the cause.
The doctors told his parents, Clark and Julie, that they wanted to run one
more test with an experimental new technology. Scientists would search
Joshua’s cerebrospinal fluid for piece... 阅读全帖 |
|
v**********m
发帖数: 5516 | 23 http://m.f1000research.com/articles/3-291/v1
波士顿地区的千老联合会的报告，文章提到的问题非常典型和深刻，该文已经在圈内得
到了包括大佬们的极大肯定(恐惧)。
OPINION ARTICLE
Shaping the Future of Research: a perspective from junior scientists[v1;
ref status: approved 1, approved with reservations 1,http://f1000r.es/4ug]
Gary S. McDowell1*, Kearney T. W. Gunsalus2*, Drew C. MacKellar3, Sarah A.
Mazzilli4, Vaibhav P. Pai1, Patricia R. Goodwin5, Erica M. Walsh6, Avi
Robinson-Mosher7, Thomas A. Bowman8, James Kraemer9, Marcella L. Erb10, Eldi
Schoenfeld1... 阅读全帖 |
|
r******g
发帖数: 600 | 24 实验很solid
并且多数都是unbiased study
多半没问题的 |
|
c******n
发帖数: 16403 | 25 4icu.org Web Popularity Ranking methodology
Universities and Colleges are sorted by our exclusive 4icu.org Web
Popularity Ranking.
The ranking is based upon an algorithm including three unbiased and
independent web metrics extracted from three different search engines:
*
- Google Page Rank
*
- Yahoo Inbound Links
*
- Alexa Traffic Rank
The aim of this website is to provide an approximate popularity ranking of
worldwide Universities and Colleges based upon the popula |
|
e**e
发帖数: 3 | 26 You are calculating the biased sample variance and with one sample
value getting a variance of zero.
Calculate the bias-corrected (unbiased) sample variance instead, which
for one single sample always gives an undefined variance.
Monte |
|
L*******g
发帖数: 913 | 27 换句话，是不是问RNG的initilization是否unbiased? |
|
x***e
发帖数: 62 | 28 proof by contradiction;
suppose you can construct a function:
F(x1,x2....xn) as your estimator
calculate the expected value of your F(x1,x2,...xn);
E(F(x1,x2,...xn)); show that can never be p/(1-p);
it is getting nasty;
E(F((x1,x2...xn))=F(0,0,..0)*(1-p)^n+sum(F(Xi=1))*p*(1-p)^(n-1)+.....
+F(1,1,...1)*p^n;
and since the only possible value for Xi's are 0 and 1;
so F(0...0)=0; F(Xi=1)=1 or O; F(Xi=1,Xj=1)=0,1,2; .....
F(1,1,...1)=0,1,...(n/2)^(n/2);(if n is even)
and then you just calulate those |
|
p*****e
发帖数: 989 | 29 Efficiency, in most case, only means min. variance for all linear
unbiased estimators. this is just the conclusion of the trivial
Gauss-Markov theorem, should be taught in any linear regression class;
or page 3 in any regression book.
If the errors are NORMAL, (like in your case), MLE will be the same as
LSE, it reaches the Rao-Cramer lower bound, (info. matrix)
how come you are reading robust estimators, while having
no clue of those basic results???????????
FTing......
efficiency
efficiency? |
|
s*****w
发帖数: 2065 | 30 再问一个问题，以上这些都是假设Y和X没有问题的。
如果知道观察到的Y是biased，因此E也是biased，而且知道Y(t-1)和Y(t)是负相关的，
那么用WLS的时候用Y(t-1)当weight是不是就能解决问题呢？得出来的B(^)还是不是
unbiased和consistent啊？因为现在E(E)<>0了。 |
|
n*****1
发帖数: 172 | 31 "更准确"是指? unbiased? efficient? consistent?
假设你原本的OLS是BLUE, 那你restricted OLS出来的就不是BLUE了啊 |
|
d******w
发帖数: 39 | 32 哦 谢谢二位
恩 那我现在表达：如果限制条件正确的话，估计的OLS会更加unbiased,and extra
variable can also be eliminated.
但如果限制条件不对，restricted OLS就不是BLUEl了。
对不？ |
|
s******i
发帖数: 7 | 33 I need to translate some course description into Chinese. Pls help:
Linear Algebra:
invariant subspaces,
direct sum decompositions,
canonical forms,
inner product spaces.
Probability and Mathematical Statistics:
central limit theorem, point estimation, hypothesis testing, moment-generating
functions, normal sampling theory, sufficiency, best estimators, maximum
likelihood estimators, confidence intervals, most powerful tests, unbiased
tests, and chi-square tests.
Elasticity Mechanics :
Phenomen |
|
l*****i
发帖数: 3929 | 34
I need to translate some course description into Chinese. Pls help:
Linear Algebra:线性代数
invariant subspaces,不变子空间
direct sum decompositions, 直和分解
canonical forms, 规范型
inner product spaces.内积空间
Probability and Mathematical Statistics:概率和数理统计
central limit theorem中心极限定理, point estimation点估计, hypothesis testing
假设检验, moment-generating functions（不知道）, normal sampling theory（不知
道）, sufficiency（不知道）, best estimator, maximum
likelihood estimators, confidence intervals, most powerful tests, unbiased
t |
|
R*****s
发帖数: 28 | 35 The problem is like this:
Let X be a normal distribution with mean mu and standard deviation sigma.
Suppose M samples are drawn from X. However, only N ( N < M ) samples are
observable to us, with the property that these N samples have the largest
values of the set of M samples.
What are maximum likelihood estimates of mu and sigma?
Are they biased or unbiased?
Anyone has ideas? Can we use a truncated normal? |
|
g*****u
发帖数: 14294 | 36 这两个都是r.v. std的估计，只是一个是biased, 一个是unbiased. |
|
l***o
发帖数: 7937 | 37 哥伦比亚大学很差进！
http://www.albany.edu/~scifraud/data/sci_fraud_4236.html
Columbia's attorneys are battling a similar complaint brought by a former
Columbia mathematics student, Sheng-Ming Ma, against former mathematics
department chair Duong Phong. In a complaint filed in March 1998 in the New
York Supreme Court for New York City, Ma claims Phong took a math proof he
had done as a thesis project and published it as his own in a paper co-
authored with Elias Stein of Princeton University. Phong has de... 阅读全帖 |
|
r******k
发帖数: 97 | 38 "I don't know who copied whom"
Dare you say you are unbiased?
because
.
excluded |
|
p********m
发帖数: 325 | 39 SMGC (海云龙鹤); meganli1998 (megan); VictorG (VictorG); triathlon (三湘四水
春暖花开); herby (小臭宝); zhanghaowei4 (dahuaidan); mei5 (mei);
timingchain (timingchain); bythesea (海阔, 天空); sunshadow (影子);
PearlGiver (Joy); leap1993 (leap), tommyding (Tommy); mark7 (小马哥); swh
(小猪跟着大猪跑); springstep (春天的脚步........), autumn33 (cici), 和几位给
我写信的朋友 ：
谢谢各位的鼓励和祝福!
另外， 还想强调一点，挑选tutor 时背景知识人品很重要，但tutor阳光的心态和对学
员的信心最重要，而自己对tutor的信任决定了培训的结果。 这就是“观察者效应”的
一个完美范例。
希望我这个尽量客观的帖子可以给大家今后选择tutor提供一些unbiased 的信息。
祝大家感恩节快乐， 心想事成！ |
|
s********o
发帖数: 3319 | 40 ☆─────────────────────────────────────☆
pathodream (天涯饱看山) 于 (Wed Nov 23 01:00:59 2011, 美东) 提到:
『前言』
与澜静初识于5/22/2011 纽约 ACAP 会议。
当时的自己还没有从Match失败的打击中回过神来。 前路渺茫，无所适从，几近放弃。
第一次参加CME的活动，老刀的“you are not old; you are experienced" 给了我观
念上的改变，Dr.Eng 的面试讲解让我茅塞顿开。会后的闲聊中站在身边的澜静得知我
也申请病理，主动提出“let me have a mock interview with you" . 15分钟里，他
就我的“tell me about myself" 回答提出的批评和建议，对我犹如当头棒喝， 让我
第一次认识到我精心准备的面试答案是多么的不成熟， 第一次意识到我失败的根源，
也第一次发现了战胜自己“learned helplessness" 的武器。
会后给澜静写了感谢邮件， 澜静很是鼓励我， 也一再表示如我有需要，他... 阅读全帖 |
|
J*********4
发帖数: 1274 | 41
====
I hate being judgmental or mean to others, even though I do behave like that
from time to time.
你对楼主的评论，只能反映出你的理解和逻辑能力。
你这指出xxx,也就是cmg的缺陷, 确实有点中国领导指点江山的气派？
给别人unbiased 建议，正是professional的表现。难道非要给一位哈佛材料硬性推销
自己差一些的的program? |
|
d*b
发帖数: 21830 | 42 难怪都看不起LANL的，今天收到的email...
==============================
Can somebody stop this ridiculous military celebration?
On Sep 29, 2011, at 8:29 AM, XXX wrote:
> Hello All,
>
> I would like to follow up YYY's email by telling you that I am also at IDA
and really like it. Before going to Washington, I spent several years
working on DZero and a little time on CMS. I will be at Fermilab on Friday
for the end of the Tevatron extravaganza. If you would like to talk, send
me an email.
>
> Cheers,
>
> XXX
... 阅读全帖 |
|
h*****a
发帖数: 52 | 43 1. There are some unbiased coins (equal probability of having head and tail
when tossed). Initially, all the coins are tossed. The following steps are
followed after that:
- turn all the Head up coins to Tail.
- toss all the Tail up coins.
Find the probability of finding the a coin Head up after 'n' pairs of steps,
( or to frame it differently, find the number of coins with Head up) (Hint:
think in terms of ratio)
Ideas? |
|
z****i
发帖数: 406 | 44 best linear unbiased estimator? |
|
s*******s
发帖数: 1568 | 45 1.
cov(X_1/sum,X_1/sum) + cov(X_1/sum,X_2/sum) + ... + cov(X_1/sum,X_n/sum) = 0
2.
don't know
3.
still unbiased, but less efficient
sum(
variable |
|
w**********y
发帖数: 1691 | 46
we
200
This is similar as one question in my previous interview with Bloomberg.
I think the MLE is only the first step.
The following question should be " How about an estimator by some scaled
mean (actually, 2*sample_mean) or median? Which is better?"
The last question is, any other estimators? Which one is better and how to
evaluate a statistical estimator?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Actually, the UMVU(uniformly minimum variance unbiased) estimator is (n+1)/n
*X_max. Somet |
|
m****a
发帖数: 604 | 47 time series和econometrics学透了
-实践还是很重要的。
比如time series correlation 和cross-sectional correlation同时出现，你怎么消
除？很多时候，如果你试图都消除，会面临obs不够的问题。如果只能消除一个，怎么取舍？
efficiency 和unbiaseness之间怎么取舍？比如FamaFrench BM-size分组 VS
propensity score match,一个更efficient,一个更unbias，那用哪个？ |
|
z***c
发帖数: 2959 | 48 arithemetic average return is the unbiased estimate of expected return
geometric return is the best estimate of historical return |
|
k*******d
发帖数: 1340 | 49 请问第二个是怎么找出来的呢？
我可以证明它是unbiased，如何证明它是minimum variance呢？
怎么找到的这个？用CRLB? sufficient statistics? |
|
w**********y
发帖数: 1691 | 50 In academia, Levy driven O-U process is a popular one.
比如这篇文章:
http://www.kellogg.northwestern.edu/faculty/todorov/htm/papers/pvi.pdf
他给出了GMM的model calibration方法..我对此方法的适用性画一个大大的问号
他另外还有很多文章关于这个方面的.
我dissertation做这个方向,我的理解,大体思路是..先给一个unbiased estimation of
integrated volatility. 然后用一个mean reversion的model去modelling
volatility. |
|
