l********l
发帖数: 13 | 1 很好的分析。个人感觉Canay的paper很好的涉足了现在比较hot的Partial（Set）
identification的问题，用了比较好的工具，EL,Bootstrap。
从个人的角度来说，很佩服他用Large deviation这套方法，因为我觉得很有风险。可
能由于他在UW上过这方面的课程。毕竟这套方法主要是在概率里用，也就搞
information theory和纯概率的人搞一下。拿这么一篇可以80%猜到referee是谁的
paper做jobmarket paper还真是有胆量。
另外，俺不是很看好large deviation在计量里的运用，即使kitamura也比较悲观，呵
呵。 |
|
kx
发帖数: 16384 | 2 转自匿名区
比如两个player 在进行某种竞争, A 和 B，每个人的type 可以是h 或者l, 这是
private info. 现在
计算incentive compatibility 条件，假设A 是type h, 他在计算自己如果不follow
type h 的
equilibrium strategy, 而是deviate 到 type l 的equilibrium strategy，效用会
是多少。
这个时候，A 是应该假设B 会follow equilibrium strategy, 不管B 是type h 还是
type l, 还是
应该假设如果B 和他一样也是type h 的话，那么B 也会deviate 到用type l 的
strategy? 我们假设
players 用symmetric strategy, 即如果他们是同一type 的话，那么就用同一
strategy.
不知道我有没有说清楚。 谢谢！ |
|
l*****n
发帖数: 76 | 3 why? is the direct effect of R1 removed already by taking the difference
between two cases?
suppose one standard deviation of R1=1
one standard deviation of V=1
case1 R2=a+b*1+c*1*1
benchmark case R2=a+b*1+c*1*0
the difference between case 1 and benchmark case will be Delta_R2=c*1*1
This is the effect of interaction term, right?
R1
dif |
|
|
a*****g
发帖数: 19398 | 5 By Jay P. Greene
My advice for scholars wishing to contribute to public discourse during this
election season is simple: Just tell the truth. One might think it
unnecessary to urge scholars to be honest, but it is shocking how easily
education researchers are tempted to deviate from the truth in the hope of
gaining influence, affecting outcomes, and obtaining greater status. The
hard reality is that scholars always have limited influence, cannot easily
anticipate or control outcomes, and are for... 阅读全帖 |
|
o********g
发帖数: 162 | 6 numerical recipes 上就有呀,我给你COPY 一个在这里, page 289.
#include
float gasdev(idum)
return a normally distributed deviate with zero mean and unit variance,
using ran1(idum) as the source of uniform deviates
int *idum;
{
static int iset=0;
static float gset;
float fac,r,v1,v2;
float ran1();
if (iset == 0) {
do {
v1=2.0*ran1(idum)-1.0;
v2=2.0*ran1(idum)-1.0;
r=v1*v1+v2* |
|
i*****0
发帖数: 34 | 7
CV=Standard Error/mean
standard error = standard deviation/(n)^0.5
n=2 still have standard deviation
what's wrong with this? |
|
l********y
发帖数: 2295 | 8 oh, did not read the right half of the picture.
epidural has more mass effect on the brain.
Acute epidural hematoma occurs with modest trauma to the side of the head.Emergency craniotomy produces dramatic cure.
Acute subdural hematoma has the same sequence, but the trauma is much bigger, the patient is usually much sicker (not fully awake and asymptomatic at any point), and the neurologic damage is severe (because of the initial blow). If midline structures are deviated, craniotomy will help, bu... 阅读全帖 |
|
n*****n
发帖数: 119 | 9 别处看到的，觉得还不错，不排除有些拼写错误~
POMR (Problem-Oriented Medical Records)表格式住院病历
Biographical data:
一般项目：
Name Age Sex Marital status Nativity Race
姓名 年龄 性别 婚否 籍贯 民族
Occupation Date of admission Informant History
职业 入院日期 病史叙述者 病史
Chief complaint
主诉
History of present illness
现病史
Past history
既往史：
Previous health status: well ordinary bad Infectious diseases
平素健康状况： 良好 一般 较差 传染病史
Immunizations Allergies: N Y clinical manifestation
预防接种史 过敏史 无 有 临床表现
allergen: Trauma: Surgery:
过敏原 外伤... 阅读全帖 |
|
e****0
发帖数: 678 | 10 • Exaggerated deep tendon reflexes can be seen in lock in syndrome.
• Non bleeding varices are managed with nonselective beta-
adrenergic antagonists, such as propranolol.
• Sclerotherapy, endoscopic band ligation, and surgery are
indicated after a patient has a first episode of variceal bleeding.
• TIPS is a last resort in variceal bleeding unresponsive to
medical and endoscopic intervention.
• Ischemic colitis
CT—thickening of eth bowel ... 阅读全帖 |
|
r**********7
发帖数: 243 | 11 不是我翻的，借花献佛，有错的大家指正，祝好运！
Noncontrast head CT (10/20/2013):
Findings:
The 4th ventricle is not well visualized. Suspicious high density in
the posterior cranial fossa. No obvious dilation or expansion of the
rest ventricles, cisterns or sulcus. No midline deviation. No obvious
cerebral density or morphology change. The bony calvarium is within
normal limits.
Contrast enhanced brain MRI (10/22/2030):
Sequence:T1W/T2W/DWI/FLAIR/MRA
Paramagnetic contrast agent, 0.2 ml/kg, IV bolus.
Findings:
Bilatera... 阅读全帖 |
|
s*******w
发帖数: 1879 | 12 我觉得吧，你这个状态跟我头两个月的时候很像，其实说到底就是对自己要求太高了，
太骄傲了。
我头两个月这么弄的很抑郁，后来一度去看therapist，而且当时一连投了十几个
leadership position全部不中，头两门出来的考试成绩都是below average，压力非常
大。
后来归根结底觉得是自己觉得自己是根葱，想honor，想aoa，想be someone，但其实在
这种地方满地人精的地方根本不可能。
想开了就觉得没啥了，我就烂人一个，考试不垫底就行了。我的要求现在很简单，我们
平均分1个standard deviation之内就行了，想通了快活多了，分低就低呗，反正考过
了。考不过也没事，就补考呗，反正不怕没饭吃，以前薄后都过来了还怕毛啊。
话说你考试能记住不错了，考完一个月忘记不是太正常，正常人都会忘好么。
你们学校的embryology本来就horrible，呵呵呵。不过话说回来，我们的也horrible，
我高不了多少，反正没达到1 standard deviation below average的那个分数，呵呵呵。
无所谓啦，我们attending说啦，除非你以... 阅读全帖 |
|
p******d
发帖数: 3737 | 13 看到caloric nystagmus，不太明白，上来请教。
书上看到的，大部分是以cold water为例的。在brain stem intact的unconscious病人
，cold water引起眼睛向灌水方向deviate。这个用温水可以吗，是会向灌水的反方向
deviate吗？ |
|
b******k
发帖数: 58 | 14 A) take a data set of any time-series variable Xt. Xt could be
normally
distributed or not (just make sure all the elements in your set are
positive) - poisson, power law, pick a distribution.
(1) estimate the annualized standard deviation of Xt (call it Sx).
This
is our estimate of the "normal vol."
(2) take the logs (Xi+1/Xi), yielding a "new" data set Zt [with one
less
element], and estimate the annualized standard deviation of Zt (Sz
by
the same convention) - the "lognormal vol."
- what is |
|
c**********e
发帖数: 2007 | 15 why Z_t is one less element than X_t. As Z_t=log(X_t+1/X_t), aren't
the number of elements the same?
Does "the annualized standard deviation of Xt" mean "the annualized standard
deviation of return of Xt"? Otherwise, how is it annualized?
Thanks. |
|
m********t
发帖数: 16 | 16 i use stata as follows:
bs "interest rate" "r(sd)",rep(1000)
then i get a standard deviation
but i want to repeat this procedure for 500 times
(i want 500 standard deviations)
how can i do that?
i don't like to type in the same command 500 times
3q! |
|
w**********y
发帖数: 1691 | 17 行吧.俺自己看明白了..terminology啊....
你说的股票volatility实际上是 说它的return的standard deviation...而return的定
义是
(St-S0)/S0..我误以为是St-S0的standard deviation了.
所以我的式子应该变成..
总收益=(w/s1)*X1+((1-w)/s2))*X2=w*r1+w*r2,
where r1=(X1-S1)/S1;r2=(X2-S2)/S2.
那么,总收益的variance=(w)^2*0.2^2+(1-w)^2*0.3^2+(w)(1-w)*0.2*0.3
|
|
l*******1
发帖数: 113 | 18 expectation of the stock price is 100*(1+2*0.01)=102
standard deviation is 2%, which is 2
103 is 0.5 standard deviation away,
1-N(0.5)=31% |
|
l*******l
发帖数: 248 | 19 1.Find the number a which maximizes E(X+aY), where X and Y are random
variables.
2. You have two fair dice, A and B. You first throw A, then B, then A again,
etc. You stop the first time you see six. What is the probability that the
die A will give you the first six?
3. Suppose you have a portfolio of 100 bonds, each with a 1% yearly default
rate. What are the odds that no bonds in the portfolio default in a given
year? Estimate this to the first digit. What happens if there is
correlation b... 阅读全帖 |
|
w****i
发帖数: 143 | 20 4. The 2 year expected return is 1.05^2, standard deviation is sqrt(2)*20%.
Thus, the 1 standard deviation downward is 1.05^2-sqrt(2)*20%*norminv
again,
the
default |
|
F*******1
发帖数: 75 | 21 Suppose I have sample data S1, S2, S3, ..., Sn and I fit the data with mean
reversion model St+1 = St + a(u+St) + s*error, where error is iid with mean=
0 and stdev=1. And I estimated a, u, and s using regression. My question
is can we calculate the expected value of the sample standard deviation (
standard deviation of S1, S2, S3, ..., Sn ) in terms of a and s?
Thanks in advance for any help! |
|
l*****n
发帖数: 72 | 22
It is very trick. When you attach more element -1. You make the mean
closer to the attached -1 value. Then all the attached elments -1 have very
small change over mean, when the change scaled by the sequence standard
deviation, it is even smaller, close to zero. Meanwhile, the only positive
element 1 has large change over the mean and scaled by the standard
deviation will boost it to infinite. Then, sum of the total relative changes
still be close to zero. It has no way to greater than 0. |
|
S******y
发帖数: 1123 | 23 # in case you would like to do it in Python.
def mean(ls):
return sum(ls)/len(ls)
def deviation(ls):
m = mean(ls)
return [x-m for x in ls]
in_file='C:\\type_data.txt'
f = open(in_file, 'r')
my_list = []
my_type=None
for line in f:
typex, value = line.split()
if my_type != typex and my_type!=None:
for loc,x in enumerate(deviation(my_list)):
print my_type,my_list[loc], x
my_list=[]
my_list.append(float(value))
my_type=typex
for loc,x in enum |
|
T*******I
发帖数: 5138 | 24 I am comfused with your question. The standard deviation of the residual
error is a single point measure for the dataset in the regression analysis.
How could you get more than one standard deviations with your dataset? |
|
T*******I
发帖数: 5138 | 25 However, the standard deviation is just a single point measure. How could it
change along with the change of the IV? That is impossible. Therefore, I
said you might make a mistake in your first statement. What you try to know
might be the relationship between the residuals (rather than the standard
deviation of the residuals) and the IV. |
|
w********r
发帖数: 86 | 26 有一个实验组，一个对照组，两组中每个病人的血压都是测三次以后得到的平均值。也
就是说两组中每个值都有一个Standard deviation，我想用t test比较两组的平均值是
不是一样，请问能不能直接用t test做？
还有就是两组的平均值的standard deviation怎么算？ |
|
d****m
发帖数: 1 | 27 I have a survey about 6 vendors' rating scores.
20 people were asked to rate n requirements for each vendor.
The overall vendor's assessment should be the average of those requirements.
My question is what are the right formula to calculate vendor rating's
Standard deviation and confidence interval.
Since rating came from two dimensions, from same 20 people and same n
requirements. I can not simply treat each rating as one observation hence I
have 20*N observations then use simple standard devia... 阅读全帖 |
|
f***a
发帖数: 329 | 28 每个系数加一个standard normal error不就行了吗，standard deviation用来控制变
化大小。response对不同系数的sensitivity不一样，所以各个standard deviation可
以不同。 |
|
y***i
发帖数: 11639 | 29 我的情况下是pairedwise，但我也感兴趣这个问题non-pairwise的情况下怎
么做。standard deviation拿不到，但我想可以用每个小组的平均值的standard
deviation 反推出来。
不？ |
|
P****D
发帖数: 11146 | 30 他要effect size就是相当于要standard deviation。你知道哪个都行。反正所谓
effect size也是根据standard deviation算出来的。 |
|
g******n
发帖数: 339 | 31 你这个自我称呼让我回到了遥远而性感的古代。“垆边人似月，皓腕凝霜雪”，哈哈，
想得太多了。
回到这个讨论的问题吧， 一般来说，effect size 指的是diffrence of the means or
proportions。不过在medical jurnal上好像也有人把这个均值的差除以一个standard
deviation,算是一个standardized effect size. If the end point is a
continuous variable, and the comparison is between 2 groups with common
standard deviation assumption, then the standardized effect size, along with
alpha and beta, would be sufficient for a sample size calcultion based on
normal approximation. However, this is not the case for ... 阅读全帖 |
|
z**********i
发帖数: 12276 | 32 我用PROC CAPABILITY来CHECK NORMALITY.
看图形很NORMAL,但PVALUE 很小.这个到底是NORMAL DISTRIBUTION吗?
多谢!
Variable: RBMI
Moments
N 37667 Sum Weights
37667
Mean 0.05291262 Sum Observations 1993.
05967
Std Deviation 0.00865415 Variance 0.
00007489
Skewness -0.3560206 Kurtosis 0.
79177021
Unc... 阅读全帖 |
|
c*********r
发帖数: 1802 | 33 我觉得根据已知条件，1求pooled standard deviation是对的。。。
2里面，under normality assumption，有pooled mean 和pooled SD，也很容易求出各
个percentile的值。。。
,
deviation |
|
y*****w
发帖数: 1350 | 34 (1) This is a "crossover ANOVA" which involves the feature of paired t-test.
It is exactly in the process of estimating "standard deviation of
differences" which involves the STDDEV of difference in AB, the STDDEV of
difference in BA, and the between-subject correlation between AB and BA.
(2) On the other hand, when directly applying paired t-test, we would need
to input the STDDEV of A, the STDDEV of B, and the correlation of within-
subject pair of measurements. See the link at
http://support.... 阅读全帖 |
|
y***i
发帖数: 11639 | 35 看文章
http://jcb.rupress.org/content/180/4/665.full.pdf+html?with-ds=
figure 2C 用了chi-square test 不能理解
我的理解数据是这样的：
以figure2 C,chromosome 2的图，第5天的数据为例子 （红框内数据）,这一天的数据
是monastrol significant,所以有个星号
control conditon有5%的cell 有deviation (supplimentary tableS2 红框内数据)
monastrol condition下， clone 10 有21.9%的cell 有deviation(supplimentary
tableS2 红框内数据)，然后根据chi square test,这是significant.
我的理解是只有一个数据的话，没办法做统计。如果control和monastrol condition分
别有3个数据的话，勉勉强强可以用student t test。请问我的想法对不对。如果我的
想法是错的，这里的数据的确能做chi squar... 阅读全帖 |
|
d********h
发帖数: 2048 | 36 我想说的是
Because the sample mean usually differs from the population mean, the
variance and standard deviation that we calculate using the sample mean will
always be smaller than it would have been had we used the population mean.
Therefore, when we use the sample mean to generate an estimate of the
population variance or standard deviation, we will actually underestimate
the size of the true variance in the population To adjust for this
underestimation, we use n - 1 in the denominator of our samp... 阅读全帖 |
|
d********h
发帖数: 2048 | 37 我想说的是
Because the sample mean usually differs from the population mean, the
variance and standard deviation that we calculate using the sample mean will
always be smaller than it would have been had we used the population mean.
Therefore, when we use the sample mean to generate an estimate of the
population variance or standard deviation, we will actually underestimate
the size of the true variance in the population To adjust for this
underestimation, we use n - 1 in the denominator of our samp... 阅读全帖 |
|
s*********y
发帖数: 24 | 38 5555，这个学期上了一门统计课，这次有一个统计的题目怎么也不知道如何入手？
请哪位高手帮忙一下，能给详细点的步骤更好。小女子不甚感激！
Suppose that the variability values (such as standard deviation) of heights
and right cubit lengths are interchanged, if someone looks at the students
of our section what would be expected observations in terms of overall
height and cubit length variability and distribution?
Gender Height Right Cubit
No. (M / F) (cm) (cm)
1 F 164.0 44.1
2 M 180.4 50.7
3 F 170.0 45.6
4 ... 阅读全帖 |
|
d*********1
发帖数: 63 | 39 怎么合理比较一个学校去年和今年在national standardized test上的成绩啊？去年和
今年的national standard deviation很接近 但national mean相差比较大。我的想法
是把两年的成绩根据当年的national mean 和 standard deviation转换成z score。但
问题是再怎么比较两个z score呢？比如两个分别为0.12和0.21，但如何判断这个差别
是否大到需要引起重视呢？
谢谢！ |
|
c********h
发帖数: 330 | 40 不知道对不对，我觉得是这样的:
A.bar = sample mean from A, n = sample size of A
B.bar = sample mean from B, m = sample size of B
Y.bar = sample mean from A+B
= (n*A.bar + m*B.bar) / (m+n)
X.bar = A.bar
Y.bar - X.bar = m/(m+n) * (B.bar - A.bar)
It seems that if m/(m+n) is small, i.e. A dominates B, then Y.bar - X.bar is
going to be small. But the m/(m+n) also decrease the variance of Y.bar - X.
bar. Roughly speaking, you only need Y.bar - X.bar to deviate twice of its
standard deviation, not the std of B.... 阅读全帖 |
|
r****5
发帖数: 618 | 41 What proportion of points are within two standard deviations (2sd) and three
standard deviations (3sd) of the regression line?
We have data. How can we calculate sd of the regression and count the
number out of 2sd and 3sd? Can we use Minitab to do it? Thanks. |
|
s**********8
发帖数: 25265 | 42 Design Controls
INTRODUCTION
Coverage
QUALITY SYSTEM
Personnel Training
DESIGN AND DEVELOPMENT PLANNING
Interface
Structure of Plans
DESIGN INPUT
Input Checklists
DESIGN REVIEW
Combination Devices
Preparation For Reviews
Why Design Reviews
Types Of Design Review Meetings
Design Review Requirements
End Of Initial Design
DESIGN OUTPUT
Documenting Design Output
Acceptance Criteria
Design Output Approval
DESIGN VERIFICATION AND VA... 阅读全帖 |
|
s**********8
发帖数: 25265 | 43 DEFINITIONS:
I. HUMANITARIAN USE DEVICE (HUD): A device that is intended to benefit
patients
by treating or diagnosing a disease or condition that affects fewer than 4,
000
individuals in the United States per year.
II. HUMANITARIAN USE DEVICE EXEMPTION (HDE): Food and Drug Administration
(FDA) approval of an HDE permits the marketing of an HUD, subject to
restrictions
on charges and use. Specifically, HUDs cannot be sold for profit, except in
the
limited circumstance when indicated for use in c... 阅读全帖 |
|
a*i
发帖数: 1652 | 44 http://en.wikipedia.org/wiki/Corrective_and_preventive_action
Corrective and preventive action (CAPA, also called corrective action /
preventive action) is a concept within good manufacturing practice (GMP).
CAPA focuses on the systematic investigation of discrepancies (failures and/
or deviations) in an attempt to prevent their recurrence (for corrective
action) or to prevent occurrence (for preventive action). To ensure that
corrective and preventive actions are effective, the systematic
inves... 阅读全帖 |
|
G*******e
发帖数: 219 | 45 http://news.nurse.com/apps/pbcs.dll/article?AID=2005505010320
Caution: Nerve Injuries During Venipuncture
Sue Masoorli, RN
Sunday May 1, 2005 Print Select Text Size: Comments
Share this Nurse.com Article
Share on facebook Share on twitter Share on email
Permanent damage can result
when a needle point makes
contact with a nerve.
"Nurse, I feel an electric shock going down my arm." Would this patient
complaint mean anything to you when you insert an IV catheter or draw blood?
This feeling of s... 阅读全帖 |
|
k*****3
发帖数: 226 | 46 让人惊奇的是此报到十四日就发出了
Eutimes report
March 14, 2014
Russia “Puzzled” Over Malaysia Airlines “Capture” By US Navy
By: Sorcha Faal, and as reported to her Western Subscribers
A new report circulating in the Kremlin today prepared by the Main
Intelligence Directorate of the General Staff of the Armed Forces (GRU)
states that Aerospace Defence Forces (VKO) experts remain “puzzled” as to
why the United States Navy “captured and then diverted” a Malaysia
Airlines civilian aircraft from its intended flight-... 阅读全帖 |
|
D**u
发帖数: 288 | 47 笼统的说用Posterior Beta 和 Normal都可以，但是一般的网页CTR都非常小，不要忘
记Normal approximate Binomial对 p是有要求的，不能太小。所以最好还是用
Posterior Beta 。
道理都是一样的，先确定一个error bound，10%, 5%， 或者1%， 然后，根据
Posterior Beta或者Normal的standard deviation的表达式计算n。
幸运的是，两个distribution的standard deviation的表达式都很简单，可是计算过程
中，都还需要额外的参数， 那就是p0对于Normal，（a，b）对于Posterior Beta 。
所以你的link中的针对Normal的Wald方法，直接取p0=0.5了，这样就有一个很简单的式
子可以用了。这是个maximum variance 假设，但是，这个对于CTR来说偏差太大了，不
建议使用，当然还有一些更复杂方法的来correct Normal的这个issue， 不过表达式都
很复杂。当然，你若问是否可以估计一个相对较小的p0,比如0.01，答... 阅读全帖 |
|
l*******s
发帖数: 7316 | 48 20.This rule does not apply to plans featuring set allotments of data (e.g.
3GB), or any plan or Add On (i.e., an allotment of minutes, SMS, MMS or data
offered separately from a plan) first offered on or before 9/13/16. This
rule applies to plans featuring unlimited minutes, unlimited SMS, unlimited
MMS and unlimited data, and Add Ons offered after 9/13/16 in order to
prevent Abuse and to protect the RingPlus community as a whole. “Abuse”
includes failure to abide by RingPlus Legal Notices, the... 阅读全帖 |
|
l*******r
发帖数: 39279 | 49 by deviate
难怪deviate对阿修罗这么熟悉呢，看A啊，但大傻肯定觉得这样的人生有血有肉挺好。
小猪的生活经验很丰富啊
都在讨论非诚勿扰，
关于女人怎样的才受欢迎等等
所以想起来一些我遇到过的姑娘
且容我回忆一下：
故事一：
第一个，其实是个仅仅有一面之缘的小女孩。但是因为其人生实在彪悍，我没法子把她
排第二去。
姑且称之小A
当年她20岁，在悉尼读书。东北小孩，高挑白皙。和我是这么说的：我家原来还挺有钱
的，后来破产了，没钱了，所以家里就把我送澳洲来了。
我当时想了半天都理不顺这个逻辑--我以前老觉得出国自费读书是件挺费钱的事
当时的小A有一个老公，一个男友，一个sugar daddy
老公是假结婚用的。小A同学自认读书不行，但又想拿pr留在本地，没法子就假了。A说
：其实他挺帅的，我还蛮喜欢他。我问她既然喜欢为什么不真嫁给人家。“他有女朋友
的啊，不喜欢我......我每个月都得付钱给他，因为得靠他拿身分“
男朋友也是东北人
"挺幼稚的，没出息的东西，就会用钱；还用我的钱。”说起来小A咬牙切齿。那时候我
和她在火车站附近的一个rsl俱乐部等她男友来接她。
“那你干吗还跟 |
|
l*******r
发帖数: 39279 | 50 ☆─────────────────────────────────────☆
deviate (小猪) 于 (Thu May 20 08:29:29 2010, 美东) 提到:
今天去看一老朋友的豆瓣主页，丫读了15543本书，全是正经书，单单列表就有1037页！
难怪每次我回国丫就敦促我读书。
读书癖，一定是读书癖！
（ps:要说言情小说和漫画咱也清扫过几个小书店，但要都外国文学哲学美学之类的书
，连此人零头的零
头都到不了）
☆─────────────────────────────────────☆
xiaobao1996 (1996!) 于 (Thu May 20 08:30:24 2010, 美东) 提到:
要是为了读书而读书就没意思了
☆─────────────────────────────────────☆
deviate (小猪) 于 (Thu May 20 08:39:11 2010, 美东) 提到:
此人是真的爱读书，什么都喜欢看一些，家里自己还弄了个图书馆的，藏书有8000多本
，据说经手的大
抵有3万
上次回国他就送了我14 |
|
