y*****y
发帖数: 98 | 1 If there is a cheaper way, why bother using it? However you should use with
caution. Many practicers just abuse it, which really makes people feel
uncomfortable. I would say, it's no problem if one is well trained.
The only problem for Bayesian may be on the philosophical level. But
philosophical issues exist everywhere in the science, not just for Bayesian.
Look at math, bio and many others, not even mention frequentist statistics. |
|
w********o
发帖数: 1621 | 2 我不是反感bayesian这中方法。这个方法简单易学，依葫芦画瓢就可以。但是缺乏传统
统计理论基础的statistician，总归让人觉得不放心。反正我觉得有些投机取巧的意思
。当然我也见过有人统计理论也学得很好，bayesian也很熟的。这样的我就不会反感。
with
Bayesian.
statistics. |
|
p********a
发帖数: 5352 | 3 ☆─────────────────────────────────────☆
aa1343 (aat343) 于 (Wed Aug 25 00:12:09 2010, 美东) 提到:
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？
☆─────────────────────────────────────☆
drburnie (专门爆料) 于 (Wed Aug 25 00:14:06 2010, 美东) 提到:
你的统计教授挺2的，看样子不是啥好学校。
看了看IP，果然不是啥好地方的。
☆─────────────────────────────────────☆
aa1343 (aat343) 于 (Wed Aug 25 00:16:58 2010, 美东) 提到:
挺2是啥意思？ 人家可是耶鲁毕业的呢。非常的牛。就是一问到frequency和bayesian
上，他就轴上了。
☆───────── |
|
p********a
发帖数: 5352 | 4 【 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 封某版版主 drburnie 在 Statistics 版
发信站: BBS 未名空间站自动发信系统 (Mon Sep 6 17:28:06 2010)
【此篇文章是由自动发信系统所张贴】
由于 drburnie 在 Statistics 版的 PA 行为，
被暂时取消在本版的发文权力 7 天。
版主:papertigra
Mon Sep 6 17:28:06 2010 |
|
p********a
发帖数: 5352 | 5 【 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 wuhuya 在 Statistics 版
发信站: BBS 未名空间站自动发信系统 (Mon Sep 6 17:28:56 2010)
【此篇文章是由自动发信系统所张贴】
由于 wuhuya 在 Statistics 版的 PA 行为，
被暂时取消在本版的发文权力 7 天。
版主:papertigra
Mon Sep 6 17:28:56 2010 |
|
x***x
发帖数: 3401 | 6 i would go for statistics.
If you are applying for a biostatistic job, you only need to emphasize your
training in areas like survival analysis, clinical trial etc. A MS in
statistics with these trainings is equivalent to a biostats. |
|
l*******h
发帖数: 11 | 7 面试一个银行的statistical modeler的职位被问到modeling过程中如何运用
statistical optimization。虽然以前上课的时候学到过一点，但是实际project从来
没有用过。请问有经验的TX，一般这里的optimization都具体指什么，用什么样的方法
实现？ |
|
t**u
发帖数: 1572 | 8 没有统计, 怎么有STATISTICAL GENETICS.
同样, 没有GENETICS, 也就没有 STATISTICAL GENETICS. |
|
w******e
发帖数: 8 | 9 Does anyone know this year is named as "Year of Statistics" by UN, sort
of. American Statistical Association would delegate the celebration. I
think it has started, and the celebration would be in US and three cities
in China.
If anyone joins the event, could you please share how it goes??
Thanks ^_^ |
|
m********l
发帖数: 791 | 10
版主你理解错了，我的ID是mechanical。。我本科也的确是念ME的。。
然后MS转到Industrial engineering,然后现在又准备再转到Statistics。
不知道您是不是看将MS看成ME，或是受到了我ID的干扰？
我这个学期开始就全部投身于统计了。。所有有了上面的问题。。
统计里面应该有一个方向是computational statistics的吧,与机械无关。不是机械里面
computational fluid dynamics什么的。。
麻烦再帮我看一下，谢谢哈~ |
|
C******n
发帖数: 284 | 11 我觉得很有前/钱途，可惜我数学太弱了，要不然也想搞computational statistics
finite mixture model现在很热呀,往里加些multilevel，missing data什么的
你要是自己搞个软件，开公司数钱吧
参考Latent Gold by Statistical Innovations, Inc.
good luck! |
|
f*******r
发帖数: 383 | 12 假定要引用 Ronald Fisher 写于1925年的书
“Statistical Methods for Research Workers”
在正文中引用格式为：
Fisher (1936) 。。。。。。
在参考文献中格式为：
Fisher, R. (1925). Statistical Methods for Research Workers 。。。。。。
想请教大家怎么搞定，多谢。 |
|
a********g
发帖数: 42 | 13 我有一组很大的数据， fit model 之后，算它的fit statistics。 如果Kolmogorov-
Smirnov Test Statistic ＝ 1，这代表什么呢？还是有点不清楚它怎么可能达到1呢？ |
|
Y******Y
发帖数: 8753 | 14 你说的是test statistic还是p-value啊。test statistic等于1没什么奇怪呀 |
|
p*****r
发帖数: 341 | 15 不知道自己是否理解有误，MS通常应该是2年的样子，有很多学校提供1年-1.5年的那种program，master of statistical practice,master
of applied statistics, etc.这样的master值得去念吗？ |
|
k*******a
发帖数: 772 | 16 You guys need to check your textbook:
statistic is a function of observed values (X1, X2...Xn), which shouldn't
include parameter. So likelihood function, which is a function of parameter,
is NOT a statistic |
|
I*****a
发帖数: 5425 | 17 and ok, I may try to ask some professors tomorrow or the day after about
suffici
ent likelihood.
I don't believe PROFESSORS that much though. I believe textbooks a lot more,
especially on concepts. But i will try. I will learn stuffs either way.
dummy variable, you can call it theta, beta, t, s, whatever.
if we allow h=1 which is always legal? Yes. We can always let h=1 in the
Factorization Theomrem and get likelihood function which is a sufficient
statistic.
lots of people here do not even ful... 阅读全帖 |
|
a*********r
发帖数: 108 | 18 You are correct. Avidswimmer is conceptually wrong indeed. Likelihood is
never considered as a statistic.
statistic
likelihood
it,
sample
th
textb |
|
a*********r
发帖数: 139 | 19 Make sure ask a professor who fully understands the theory of mathematical statistics based on measure theory and does serious research in mathematical
statistics.
more,
in |
|
a*********r
发帖数: 139 | 20 With respect, actually you are conceptually wrong. Can you point out why I'm
wrong? Can you answer what happens when h=1 in the Factorization Theorem?
The only restriction for h is that h is a Borel-measurable function and it
does not depend on the parameters. Obviously, the constant function 1 is
always a valid choice.
Likelihood function can always be considered as a statistic. When we talk
about likelihood function, we fix x's and consider it as a function of the
parameter theta. Thus, theta ... 阅读全帖 |
|
I*****a
发帖数: 5425 | 21 Come on. Don't get mad. We were just discussing a concept.
No offense here as before.
I think your claim some other people and I don't agree w/ is in the 2nd post
of
this thread, that is "likelihood is sufficient". That's all. And I said I
never saw this term, or alternatively the claim like "some likelihood is
suff
icient". People usually talk about "** statistics are sufficient" instead.
As I replied in the 2nd or 3rd post before this, I tried to search for this
term and failed.
I did ask two ... 阅读全帖 |
|
s********p
发帖数: 637 | 22 GRE Test is offering 50% off on the revised General Test between August 1
and September 30, 2011.
Do not miss this deal, especially for those who want to transfer to / study statistics.
For those who already have graduate statistics degree, you still can use
this deal to take GRE again just for fun. |
|
d****9
发帖数: 517 | 23 【 以下文字转载自 Biology 讨论区 】
发信人: deli99 (fathead), 信区: Biology
标 题: 求推荐：statistic softwares for DoE (Design of experiment) analysis
发信站: BBS 未名空间站 (Tue May 17 10:29:06 2011, 美东)
朋友提的问题，我直接转述了，多谢！
I am looking for a good statistic software for DoE (Design of experiment)
analysis. I know several are popular, such as DesignExpert, JMP, eCHIP and
so on. Do you have any comment on these softwares? Which one would you
suggest for DoE analysis? Thank you so much. |
|
|
TX
发帖数: 468 | 25 We have one more opening for (Entry or Senior) Statistical Analyst in Dallas and currently in phone screen process.
(Fresh) Master or + in Statistics, Economics, Industrial Engineering or other
quantitative field.
2+ years in SAS Data Steps, Macros, and Proc SQL or MS SQL.
Design and program SAS/SQL code to prepare data for analysis and modeling.
Document existing and new SAS and SQL code processes.
Utilize database knowledge, programming skills and data manipulation / query tools to produce act... 阅读全帖 |
|
l****s
发帖数: 165 | 26 Statistics Jobs:
http://jobguiding.com/science-jobs/statistical-analyst.html
in
Dallas and currently in phone screen process.
or
other
modeling.
/
query tools to produce actionable reports to meet client needs.
analytic insights and recommendations to enable continuous, measurable
improvement of client’s marketing campaigns.
with my
email address to send your resume. |
|
c*****a
发帖数: 808 | 27 我以前看过nonparametric 的书，里面有介绍
Practical Nonparametric Statistics (Wiley Series in Probability and
Statistics)
我记得大概流程是有个s(x)的empirical distr function on x1,x2,...xN
然后建立一个null hypothesis some distr function F*(x). you are comparing x1
,x2...xN with F*(x) to see if it is reasonable to say F*(x) is true distr
function of the random sample.
I think the method is rather simple.
F*(x) is usually starting with 0 to 1 , by .01 .05... etc your choice based
on size of n. You usually have to make a chart ... 阅读全帖 |
|
w*******e
发帖数: 666 | 28 为了知道某个marker是不是risk factor。我做了两个survival model （包含这个
marker和不包含）。然后，用R的package risksetROC 得到了两个C statistics。想知
道怎么test 这个这两个C statistics是否 significantly different。
请教大家这个该怎么做？
Your help will be greatly appreciated! |
|
c****s
发帖数: 395 | 29 c statistics is ratio oF concord,
test how many of the results are consistent with the reality.
the idea is similar to calculate response rate
so i suppose you can use t test to calculate the signigicance difference.
but i never know survival also has c statistics |
|
s******e
发帖数: 1073 | 30 Biopharmaceutical Statistics for Drug Development (Statistics: A Series of
Textbooks and Monographs) [Hardcover]
Karl E. Peace (Author)
谢拉! |
|
d*********d
发帖数: 169 | 31 最近经历了一个onsite面试，面完了又要提供publication samples，又说还不行，要
对他们现在的一个研究数据提出具体的统计分析办法。具体有4个问题要回答， 于是我
写了一个Statistical Analysis Plan。结果3天后说是他们决定不招人了。 我感觉受
骗了，他们是不是想骗取这个Statistical Analysis Plan啊？得到了就决定不招人了
，因为之前他们真的不知道怎么分析这个数据，有点儿复杂？ 有没有有类似经历的？
分享一下，及应对办法。多谢！ |
|
D*********2
发帖数: 535 | 32 re statistical inference by George Casella
jun shao's book is better if u go for ph.d. in statistics |
|
k*******a
发帖数: 772 | 33 applied的话，应该数学要求不高，不过可以先从基础学起，比如
probability and statistics II,
statistical data analysis II,
applied regression analysis, |
|
r********n
发帖数: 6979 | 34 看一篇paper里面提到the value of c-statistic is **
这个c-statistics是个什么test出来的啊? |
|
c**********e
发帖数: 230 | 35 目的是想补一点statistics方面的知识, 最好是大学statistics的教材, 请推荐一本易
懂点的. 多谢 :-) |
|
s********n
发帖数: 943 | 36 Our Company is a consulting firm.
We need
Lead & perform statistical analysis on clinical trial studies. Manage,
validate, interpret & report clinical trials data for FDA submission. Write/
review SAP for CSR (phase I, II, III & IV). Develop complex SAS programs
for creating TLG’s, analysis datasets, validation & handle client's
inquiries for analysis and reporting.
Req Master/equiv in Statistics, Math, Biology, Chemistry or related fields
with SAS Advanced Certification. Strong skills in SAS ... 阅读全帖 |
|
I*******o
发帖数: 109 | 37 请问谁有这两本书的PDF:
A Second Course in Statistics:Regression Analysis 7th
Mendenhall & Sinchich
Statistical Analysis of Designed Experiments: Theory and Applications
Tamhane， 2009
我的邮箱:w******[email protected]
万分感谢！ |
|
s*****n
发帖数: 2174 | 38 There is an opening in my team.
http://www.google.com/about/jobs/locations/mountain-view/saleso
Some points in addition to the info on the job page.
1. Mid-to-Senior level position, MS with working experience required. Sorry
this position will not consider new grads without working experience.
Individual contributor role.
2. On the technical side, this position requires good SQL and statistical
programming skills (R preferred but SAS ok). Experience with statistical
experiment design a plus. Exp... 阅读全帖 |
|
a**j
发帖数: 60 | 39 Casella Berge statistical inference
Question # 5.2
Suppose X1, X2… are jointly continuous and independent, each distributed
with marginal pdf f(x) where each Xirepresent annual rainful at a given
location.
(a) Find the distribution of the number of years until the first year’s
rainful, X1, is exceeded for the first time
(b) Show that the mean number of years until X1 is exceeded for the first
time is infinite
question 4.36
不容易输入，我可以email pdf 版的Casella Berge statistical inference 给你
100包子
今... 阅读全帖 |
|
h***i
发帖数: 3844 | 40 statistical inference不是mathematical statistics。
前面那个就是个introduction |
|
f***n
发帖数: 254 | 41 Title：Design of Experiments: Statistical Principles of Research Design and
Analysis
Statistics Series
Author R. O. Kuehl
Edition 2
求第二版。
谢谢。
20包子酬谢。 |
|
|
h*****y
发帖数: 997 | 43 statistical analyst 就是 programmer，但programmer不一定是statistical analyst。 |
|
t*****w
发帖数: 254 | 44 【 以下文字转载自 Biology 讨论区 】
发信人: KeeVan (Kevin), 信区: Biology
标 题: 原来还有too much statistical power这么一说
发信站: BBS 未名空间站 (Fri May 24 20:42:58 2013, 美东)
以前苦逼做生物实验，都是苦恼为啥不significantly different，算statistical
power的时候都是感叹，靠，还要多做那么多个实验才能出结果。
最近被逼研究啥big data，泥马随机搞点儿数据就significantly different，从公式
角度倒是很好理解，但是还是觉得奇怪，搜索了一下，原来也是有人苦恼数据太多的。
真是天上地下啊。 |
|
e**********m
发帖数: 1960 | 45 其实不大需要，个人觉得边学，好好看书，碰到不会的东西自己翻书或者google查查就
好了。。。我不觉得有中英混合的书吧。。。只看中文说可能还会有概念反应不过来的
问题。。。
线性代数的话学multivariate analysis才用到一些，mathematical statistics应该不
大用得到
推荐两本mathematical statistics的书，一本书Jun Shao写的，另一本是Peter Bicke
l写的，应该是北美这边比较主流的教材~
pai包子~~~多谢！ |
|
c*******y
发帖数: 1630 | 46 【 以下文字转载自 Programming 讨论区 】
发信人: commodity (futures), 信区: Programming
标 题: C++ statistical package
发信站: BBS 未名空间站 (Fri Sep 13 08:51:22 2013, 美东)
除了DLIB以外，还有什么比较相近的statistical library?
nlmdl 哪里可以下载到完整的package？
请推荐一下比较好的nonparametric regression的C++ implementation。
谢谢 |
|
A*******4
发帖数: 218 | 47 Statistics in industry行业知识培训系列之：Analytics of Mortgage Banking小班
火爆开班-试听,报名正在进行中
人数：3-5人
内容：
Overview of mortgage industry
SAS programming techniques
Statistical modeling and analytics
Resume calibration and interview tips
Hand-on Project: case study of a mortgage dataset
有兴趣的参加试听的同学请加QQ群:303124359,
还将陆续推出Financial Scorecard, Marketing Mail Campaign, Healthcare,
Insurance Pharmaceutical工业统计实战课程，欢迎进群咨询 |
|
l***d
发帖数: 1828 | 48 【 以下文字转载自 Biology 讨论区 】
发信人: lrpwd (lrpwd), 信区: Biology
标 题: protein discovery需要哪些Statistics skills ?
发信站: BBS 未名空间站 (Thu Nov 28 13:13:21 2013, 美东)
在做新protein的discovery,打算学一些基本统计，请问大家一般用到哪些Statistics
skills?谢谢。 |
|
T*******I
发帖数: 5138 | 49 This is a typical mathematical thinking mode. It is not statistical and
useless in statistics. |
|
b*****g
发帖数: 91 | 50 学了一整个学期的各种statistical learning方法，Linear, DA, tree, svm, random
forest, boosting 等等，到现在只是掌握了各方法基本知识和如何在R中使用。认真读
了那本statistical learning 经典教材，一些方法中，比如SVM 和boosting还是有很
多细节很难理解和完全掌握，
现正在努力找工数据分析方面的工作。interview的时候，有关这些方法，他们会怎么
考我们，会问哪些问题?， |
|
