K****n
发帖数: 5970 | 1 我这一辈子还是头一回过“null hypothesis太强了”的日子呢，“参数组控制的再好
”，也能查出来不同这个事情对我来说真是有点儿shock，我以前的直觉是，从10亿只
果蝇里，随机取1亿只果蝇，随机再取1亿只果蝇，这两组的翅膀长度肯定不是
statistically different的。大家真诚滴说，上帝也不会发现这个model uncertainty
吧。如今真是毁三观啊。
statistical power这个我总算明白了。
如果样本很大的情况，有没有null hypothesis不强的选法？
type |
|
P*****D
发帖数: 141 | 2 我们学校的两个MS专业，都是1年半读完。
MS in Medical Statistics 是在 Department of Biostatistics
MS in Clinical Research Coordinator 是在School of Nurse
Clinical Research Coordinator只有周五有课，感觉比较简单，合适part-time。
Medical Statistics 要求比较高，要先修本科的课。
当然最重要的是，那个更好找到工作。
已经错误读完不错学校生物PhD，4年Postdoc，走不下去，人生最黑暗的时候，这一步
实在不能在错了！
谢谢大家！ |
|
P*****D
发帖数: 141 | 3 【 以下文字转载自 Postdoc 讨论区 】
发信人: ProbeID (ProbeID), 信区: Postdoc
标 题: 转行选择 CFA vs Medical Statistics
发信站: BBS 未名空间站 (Wed Jan 29 15:54:13 2014, 美东)
真心请教：生物千老转行选择 读一个MS in Medical Statistics
或者自学 考 CFA （Chartered Financial Analyst）
自己对CFA 比较感兴趣，更有可能坚持，担心没有相关经验，以后找工作有困难。
快奔四了，两个宝宝的妈，这次不能在错误选择了。
|
|
g**u
发帖数: 53 | 4 NJ big Pharm company urgently need hiring another 3 SAS programmer for
opening new study. They don't take part time and intern. Your salary depend
on your work experience. Successful candidates must have MS with Statistics,
Biostatistics, applied statistics, computer science, Computer information
System, Computer Engineering and Math major and be available immediately. If
have not graduated from school, please don't send your resume. If you are
interested in this position, please send your resu... 阅读全帖 |
|
e*******e
发帖数: 1144 | 5 What fields in business school will emphasize "statistical aspect of data
analysis" (e.g., multivariate statistics such as regression, principal
component analysis, etc.)?
Marketing? Or any other field? |
|
|
l***7
发帖数: 3 | 7 我7月份刚从 MS of Environmental Engineering 毕业.
研究的方向是applying hydrology modeling, Statistics, optimization in water
resources area.
本人精通 SWAT, HEC-RAS.
MATLAB用的还不错, thesis就是用MATLAB来写的程序，主要有optimization (single/
multi-objective gentic algorithm), change of input, record output, result
comparison, uncertainty analysis, Statistics analysis.
恳求各位同学如果知道有任何相关工作机会的话，麻烦给我站内信。
谢谢大家了。 |
|
d****n
发帖数: 237 | 8 我看Krzysztof Matyjaszewski的文章，说什么Statistical Copolymers，
这个Statistical Copolymers到底有什么样的分布规律？
Thanks a lot. |
|
f**********g
发帖数: 107 | 9 直觉上来说对任意n都是成立的，因为加上一个r.v.之后方差增大，而first order
statistic和second order statistic之差应该随方差的增长而增长。但理论上我没有
办法证明。 |
|
c*********n
发帖数: 128 | 10 Wierd problem which I don't quite understand.
If you only asked "How large of a sample must it have in order to be sure of
this level of accuracy at the 95 percent (±2 a) level of confidence? "
then it is the very common error-estimation problem in statistics, which is
probably discussed more often in Statistics board.
Say, the real proportion is p, your sample size is N, then the number of
renters out of N is of binomial distribution. Thus, you can estimate the
error, which is discussed in any |
|
f**********g
发帖数: 107 | 11 Let X be a random variable with mean >=0
Y is a random variable with mean >=0, independent of X.
Z=X+Y
Let X(n) and Z(n) be the first order statistics of X and Z respectively,
Do we have E(X(n)) <= E(Z(n))?
换句话说，当加上一个mean大于等于0的R.V.以后，first order statistic是不是一定
变大了呢？ |
|
s******h
发帖数: 539 | 12 1. X(n) + Y(n) ? = Z(n)
Not necessarily true.
Suppose X1, X2, Y1, Y2 are iid Bernoulli(1/2) r.v.'s.
Zi = Xi + Yi (i = 1, 2), then Zi IID~ Binomial(2,1/2).
Their corresponding order statistics are denoted by
X(i), Y(i), Z(i) (i = 1, ..., n).
The first order statistic's Z(1), X(1), Y(1) have the following
properties:
P(Z(1) = 0) = 1 - P( Z1 != 0, Z2 != 0)
= 1 - [1 - P(Z1 = 0)]*[1 - P(Z2 = 0)]
= 1 - [1 - 1/4] * [1 - 1/4]
|
|
c**i
发帖数: 6973 | 13 I am a biologist by training. I learned statistics in Taiwan. Then I came to
US to get a PhD at University of Illinois, which required biostatistics,
which needed no calculus (I had forgotten that by then).
So I do not understand what you say. My thinking and this New York Times
report suggest statistics, mathematics and economics have some overlapping.
Isn't this true?
I mean, you learn mathematics, which enable you to work in Wall Street if
you so choose. |
|
g**u
发帖数: 53 | 14 NJ big Pharm company urgently need hiring another 3 SAS programmer for
opening new study. They don't take part time and intern. Your salary depend
on your work experience. Successful candidates must have MS with Statistics,
Biostatistics, applied statistics, computer science, Computer information
System, Computer Engineering and Math major and be available immediately. If
have not graduated from school, please don't send your resume. If you are
interested in this position, please send your resu... 阅读全帖 |
|
s******e
发帖数: 1073 | 15 Biopharmaceutical Statistics for Drug Development (Statistics: A Series of
Textbooks and Monographs) [Hardcover]
Karl E. Peace (Author)
谢拉! |
|
r******s
发帖数: 2155 | 16 【 以下文字转载自 Business 讨论区,原文如下 】
发信人: pringle (softbutcrisp), 信区: Business
标 题: A statistic question?
发信站: Unknown Space - 未名空间 (Wed Apr 27 18:59:39 2005) WWW-POST
If simple correlation shows that two variables are not significantly
correlated, could the two variables still be statistically associated?
Especially, could the nonsignificant simple correlation be caused by other
confounding factors?
Is it possible that by controlling for the other potential confounding
factors, we could still find th |
|
A***A
发帖数: 98 | 17 We will probably need a clarification on what is meant by "statistically
associated."
If you mean the two random variables are statistically non-independent, then a
zero correlation does not imply independence. It will only imply independence
if the two variables are jointly normal.
A simple counter-example: y = x^2, then cor(x,y) = 0, but the two are clearly
not independent. It's just that the correlation only captures the linear
association between two variables.
Hmm. If there are more than |
|
B*********h
发帖数: 800 | 18 ☆─────────────────────────────────────☆
circumfly (nbzx) 于 (Thu Aug 2 09:30:29 2007) 提到:
Dear all,
I am very interested in statistical arbitrage and quantitative trading.
Could anyone please tell me what
houses or firms are most famous for statistical arbitrage? I hear a few of
them: D E Shaw? ESL ? and.....
Comments are welcome!!
Cheers,
☆─────────────────────────────────────☆
tokyo (我爱clips) 于 (Thu Aug 2 09:40:31 2007) 提到:
hmm, of course medallion fund, flagship of renaissance
☆── |
|
i***0
发帖数: 8469 | 19 Hello,
My name is Shalley and I'm a recruiter at Artech.
Artech has an urgent contract for one of our direct clients:
Job Title: Statistical Programmer - SAS
Location: Bridgewater, NJ
Duration: 3+ Months
Job Description:
Duties:
Provide statistical programming expertise (preferably in SAS) in the
production of analyses, tabulations, graphics, and listings from clinical
trial data. Key responsibilities and skills include, but are not limited to,
the following: Contribute to the preparation of |
|
x****e
发帖数: 1780 | 20 statistics for sure if the school is good enough.
MFE is just a degree assembled from a bunch of subjects and it is not as
flexbile as statistics in terms of career development. |
|
t*******8
发帖数: 67 | 21 Hi, all,
This investment bank is building its Mortgage Modeling effort (defaults,
prepays…) and they now want to hire a PHD in Statistics with 0-3 yrs of
experience preferably from out of industry. Ideally, he wants a PHD in
Statistics from a top school. They want to pay less than $200k total
comp, but would go slightly higher for someone really good.
I got two offers from this group, one candidate joined and the other one
backed out because family is moving to other city. Very quick process.... 阅读全帖 |
|
t*******8
发帖数: 67 | 22 Hi, all,
This asset management firm is building its Mortgage Modeling effort
(defaults, prepays…) and they now want to hire a PHD in Statistics with 0-3
yrs of experience. Ideally, he wants a PHD in Statistics from a top school
. They want to pay less than $200k total comp, but would go slightly higher
for someone really good.
If you are interested, please send resume in word version to tgan@
optionsgroup.com.
Thanks.
Thomas Gan, Ph.D.
Director
Options Group
848.229.1688
http://www.linkedin.co... 阅读全帖 |
|
|
m****e
发帖数: 15 | 24 本人物理phd，对学术热情日益减少，打算看看quant这条路怎么走。在的学校还可以，
综合前十，但是物理一般。
刚开始考虑这件事，打算先上几门statistics的课看看，但是不知道哪些是和quant比
较相关的。请教板上的各位大牛们。
Probabil/measure theory
Linear models
Generalized linear models
Bayesian and modern statistics
Applied stochastic processes |
|
w********h
发帖数: 17 | 25 Princeton used to have a very strong statistics department with big names,
like John Tukey and Geffory Watson. But Tukey and Watson never got along till
both of them passed away. Their internal conflict led to the final collapse of
this premium program in early 90s.
Now the statistical components are scattered around the Princeton campus.
Recently they are making effort trying to re-build the program with a very
successful recruitment of Fan Jianqing, a COPSS winner.
Watson also used to be the s |
|
p****x
发帖数: 46 | 26 【 以下文字转载自 Visa 讨论区 】
【 原文由 javalife 所发表 】
http://www7.nationalacademies.org/visas/Visa_Statistics.html
Visa Questionnaire Statistics
As of February 13, 2004
Total cases reported to IVO: 1160
IVO cases (cases for which IVO has provided some assistance): 956
Statistics for 956 IVO cases
26.2% (250) delayed/pending cases (applicants are still waiting for their
visas to be processed)
73.8% (706) closed/resolved cases
• 66.7% (638) approved
• 3.6% (34) delayed/canceled/visa not received i |
|
p********a
发帖数: 5352 | 27 ☆─────────────────────────────────────☆
north4340 (北) 于 (Wed Mar 28 16:45:09 2007) 提到:
要去面试一个Marketing部门的Statistical Modeller的面试，预定是一个小时
，前面有过一个15分钟的Phone Interview,只是很简单得问了一下背景。工作要求里面
，重点是要求Statistics和SAS的背景。请问一下又过类似经验的人，一个小时的面试
，专业知识问到那个深度？统计和SAS方面准备那一块比较合适。
谢谢。
☆─────────────────────────────────────☆
ciara (青苹果) 于 (Wed Mar 28 19:27:24 2007) 提到:
听起来象是ON-SITE面试, 但好象又不是FINAL面试(一个小时好像短了点?).如果那15分
钟是HR的SCREENING面试, 我个人猜测是技术面试,应该是跟HM谈.专业知识问到深度跟
公司和POSITION相关,JOB描述就是最好的准备指导了.大部分情况下是LOGISTI |
|
l*******g
发帖数: 1 | 28 I am applying for post doctoral positions in statistics or econometrics.and
I graduated from Department of Statistics,Remin University of China.I want
to know the specific research program and the other related information,if
you could tell me the details,I would appreciate that. |
|
s*********e
发帖数: 1051 | 29 don't know how you define statistical modeling. my favorite is elements of
statistical learning by hastie. |
|
w********8
发帖数: 4 | 30 I major in statistics and is looking for entry level jobs. Most of the jobs
I applied are analyst position in banks. Any suggest of what other type of
entry job is avialable for statistic masters?
thanks a million. |
|
p********a
发帖数: 5352 | 31 ☆─────────────────────────────────────☆
PurpleShell (PurpleShell) 于 (Fri Jul 18 21:36:03 2008) 提到:
My friend is on her way to decide a major which will determine all her
future life. So, welcome good advice and reason. She is a working hard
person and want high salary and very good job for a girl. Thank you so much.
Her background: Statistics master and hesitate on the following choice.
1) Finance PHD; What kind of job possible and average salary?
2) Statistical Genetics PHD. what kin |
|
r*****e
发帖数: 11 | 32 I feel statistics has a wide range of areas.
Sometimes I pick-up something and cannot answer other things.
I am wondering if there's any guide or focus on preparing and reviewing
statistics knowledge.
Thank you very much. |
|
a*****b
发帖数: 2789 | 33 已经不再接受resume，谢谢。
从昨天开始电话已经被打爆了，请不要再打电话。email我会一封一封回复大家。
关于公司，是一家non-profit小公司，和ETS等考试机构性质类似。工作很轻松，自由安排时间比较大，所以pay得不高（比100% TA,RA高一些）
Hi all,
因为我换工作了需要尽快离开现在的职位，所以公司急需一个statistical research
associate。要求如下：
The requirements for this position:
• Strong data analysis skills with SPSS or SAS
• Basic knowledge in statistical methods and psychometrics
• Knowledge of SQL and Oracle database
• Quantitative research experiences
• Good oral and written communic |
|
m******1
发帖数: 19713 | 34 I am running a multivarialbe model:
model survtime*death(0)=A B A*B.
Is there a way to output the score test statistic and likelihood ratio test
statistic for A*B from Proc PHREG?
Thanks. |
|
p********a
发帖数: 5352 | 35 【 以下文字转载自 Notice 讨论区 】
发信人: deliver (自动发信系统), 信区:
标 题: papertigra 封 bruclee 在 Statistics 版
发信站: BBS 未名空间站自动发信系统 (Sun Aug 30 20:38:40 2009)
【此篇文章是由自动发信系统所张贴】
由于 bruclee 在 Statistics 版的 PA 行为，
被暂时取消在本版的发文权力 14 天。
版主:papertigra
Sun Aug 30 20:38:40 2009 |
|
h***i
发帖数: 3844 | 36 Bickel 的 mathematical statistics
or
Shao Jun的 mathematical statistics |
|
f*******r
发帖数: 383 | 37 1) J. PITMAN的Probability
2) J. RICE的Mathematical Statistics and Data Analysis
或者C. STONE的A Course in Probability and Statistics |
|
p********a
发帖数: 5352 | 38 【 以下文字转载自 Notice 讨论区 】
发信人: deliver (自动发信系统), 信区:
标 题: papertigra 封 TNEGIETNI 在 Statistics 版
发信站: BBS 未名空间站自动发信系统 (Fri Mar 5 15:42:07 2010)
【此篇文章是由自动发信系统所张贴】
由于 TNEGIETNI 在 Statistics 版的 天才犯众怒 行为，
被暂时取消在本版的发文权力 14 天。
版主:papertigra
Fri Mar 5 15:42:07 2010 |
|
o******6
发帖数: 538 | 39 ☆─────────────────────────────────────☆
Varco (Brook) 于 (Fri Mar 13 23:49:05 2009) 提到:
请教：
这两个方向，那个更有利于以后毕业出来争取教职，或找不到教职在其他地方做研究？
两个老板都得过CRM-SSC AWARD
1.Statistical Genetics
2.Bayesian statistical inference (including the implementation of the
Bayesian paradigm in the health sciences, and the development of
computational algorithms for Bayesian inference)
☆─────────────────────────────────────☆
DVD (时不我待) 于 (Sat Mar 14 00:20:33 2009) 提到:
没有容易不容易，看你做的有多好了
☆───────────────────────────── |
|
l*****a
发帖数: 1 | 40 Hi,
Could anyone recommend some good recruiters for Statistics jobs?
I would like to apply for statistics jobs, like SAS programmer, or
statistician, but couldn't find much myself. Thanks you. |
|
m*****u
发帖数: 25 | 41 Cardiovascular Research Center
Statistical Programmer
Cardiovascular Research Center
Mid America Heart Institute
Saint Luke's-Shawnee Mission Health System
Kansas City, Missouri
The Mid America Heart Institute is currently seeking a Statistical
Programmer for its rapidly growing cardiovascular research program. This
person would work closely with physicians, scientists and department team
members on clinical research projects.
The position would require preparing and maintaining datasets, workin |
|
D******n
发帖数: 2836 | 42 quite normal stat questions, if u know stat u will know the answer, if u don
t know stat why were u asked these questions?
btw, statistics not statistic
control
for |
|
w********u
发帖数: 328 | 43 three curves:
1 & 2 has the coefficient of determination, R square, =0.7
1 & 3 has the coefficient of determination, R square, =0.8
Actually, there is no correlation between 1 & 2, for example, sunshine and
the light, they both light up the room but there is no actual relationship
between them. But 1 & 3 indeed has statistical correlation.
Now, how to prove that 1&3 has statistical correlation but 1&2 does not?
Any idea is welcome, especially with some particular formula.
Thank you.! |
|
k****4
发帖数: 86 | 44 只说statistical programmer，CT Statistician不清楚
如果有这边2-3年的工作经验,25万没问题。不过没前途，我是说，比这边做statistical
programmer还没前途 |
|
b*********e
发帖数: 29 | 45 I love both.
For a CS, we need to tell a machine something.
For a stat, we need to tell people something.
The common idea for these two something is: This is a kind of "Something"
that they do not need to know at all. But, the "machine" and the "people"
always think that they can not be themselves without knowing this kind of "
something".
Agree with you at this point "few statistics professors can truly understand
the basic concept of statistics. "
As to the probability theory, how to understan |
|
B******y
发帖数: 9065 | 46 答案似乎应该是Statistics比CS更难找工作，而不是CS比Statistics更“好”找。 |
|
c***3
发帖数: 56 | 47 Thank you for sharing the information. I just checked the company's website.
It seems that statistical programmer is not liseted on their website. Is
statistical programmer position still available? |
|
n******r
发帖数: 4 | 48 The Statistical Analyst is responsible for producing and reviewing forecasts
. The Analyst uses statistical forecasting methods (GLM, and Longitudinal
Analysis; develop linear and non-linear deterministic forecasting models;
perform residual analysis and run autocorrelations tests); interpret and
present results from technical data analyses to clients using non-technical
language producing forecasts that support demand planning decisions and
utilizes established analytical methods to develop dem |
|
a****3
发帖数: 11741 | 49 当我向我的统计教授问bayesian问题时，他竟然说“I am a frequentist, not
bayesian"来拒绝回答我的问题。我很纳闷这
两种statistics难道是水火不想容的吗？ |
|
w********o
发帖数: 1621 | 50 我自己就比较反感bayesian。你知道从frequentist的角度分析问题，一个模型要用多
少力气去推算asymptotic properties，才能develop estimate, confidence interval
，test statistic and p-value吗？有时候推不出来，就得用bootstrap啊之类的
empirical estimate,或者EM algorithm，总之要多麻烦有多麻烦。所以统计要出点成
绩，那得要深厚的理论基础。
自从有了bayesian，什么都不用，任何能想出来的model都可以用，根本无需证明，只
要有prior information就成。这prior information还是可以试着用的。变成什么理论
都不懂也照样写paper的局面。很多老教授，尤其是对理论很自负的，就会变得对
bayesian有点厌恶。
本来5年才能统计博士毕业，有了bayesian model后，大概3，4年就可以了。 |
|
