由买买提看人间百态

topics

全部话题 - 话题: covariate
1 2 3 4 5 6 7 8 9 10 下页 末页 (共10页)
z****e
发帖数: 2024
1
class overb{
public:
virtual overb f(){}//invalide covariant type
};
class overd:public overb{
public:
virtual overd f(){}//invalide covariant type
};
再看:
class overb{
public:
virtual overb* f(){}//valide covariant type
};
class overd:public overb{
public:
virtual overd* f(){}//valide covariant type
};
难道overd 不是 overb吗? 这不正好满足type 的 <=关系吗?
1. overd 对应 overb
2. overd* 对应 overb*
请问1, 和 2 , 有什么不一样?为什么一个是Covariant Return Type,另一个不是呢
c******Z
发帖数: 160
2
需要用SAS9.1 (Analyst Application)做repeated measures, 但无论如何也不知道
该用什么covariance structure, 请牛人千万指点, 非常感谢!
Q1: Is the default covariance structure the variance components (VC) in
repeated measures?
Q2: Is VC actually the factorial ANOVA, with same variance but zero
covariance? Or,does VC contain different variance but zero covariance?
Q3: When trying VC, the p-value of “Null Model Likelihood Ratio Test” is
exactly 1. What does this mean and why?
Q4: When trying all OTHER covariance structures, the p-
n*****t
发帖数: 41
3
来自主题: Statistics版 - 如何选择covariate的问题
在做数据分析,打算先fit linear model,然后general linear model,然后 linear
mixed model,甚至GEE。首先需要确定model包括哪些covariates.我用backwards删除
法。一步步把最不significant的项删掉。但是发现用lm和general linear model with
correlation重复这个做法时,最后得到的covariates不一。问题是这个covariates应
该怎么选?是用最简单的模型linear model选出来,然后就一直用这些covariates呢,
还是每换一种模型就要重新选择covariates?谢谢
A********a
发帖数: 133
4
1. APT is a risk/optimization system bu Sunguard http://www.sungard.com/apt/learnmore, people use APT/Northfield/Axioma/Barra to measure and control their factor/risk exposure. All these systems provide risk/covariance estimation.
2. There have been different approaches to estimate covariance/correlation
matrices, factor-models (above), Bayesian shrinkage estimations (Ledoit &
Wolf), high-frequency (realized vol, realized covariance matrix), dynamic
measures (DCC-GARCH, Exponential weighting, ... 阅读全帖
m*i
发帖数: 8
5
My following sas script has problems but I don't how to solve it.
Thanks in advance if anyone could help or provide some ideas.
%let covariates=age gender center EV1;
/*deleting records with missing covariates---complete obs only*/
data temp1;
set temp0;
do h=1 to %numwords(&covariates)-1;
%let name=%scan(&covariates,&h);
if &name=. then delete;
end;
The sas log showsthe following information:
WARNING: Apparent symbolic reference H not resolved.
WARNING: Apparent symbolic reference H not
W**********E
发帖数: 242
6
看一些文献关于研究病人局部贫血后得中风的风险,关于如何解释TIME DEPENDENT
COVARIATE的问题有些不清晰。
时间变量--从诊断局部贫血到出现中风的这一时间段。
CENSOR --1=中风; 0是没有或CENSORED
多个变量
1)年龄
2)BMI
。。。
K)在中风前6天内ASPIRIN的用量 (TIME DEPENDENT COVARIATE)。因为研究表明最
近的服药对中风的风险有影响。
假定3个变量
模型: h(T)=ho(T)EXP(B1*AGE+B2*BMI+B3*ASPIRIN(T))
那么如何解释这个B3系数?我怎么觉得和中风时间无关啊(尽管是一个TIME
DEPENDENT COVARIATE)?
比如年龄和BMI不变,中风前6天ASPIRIN用量为5 VS 中风前6天ASPIRIN用量为0的
HR 不就是 EXP(B3*5-B3*0)和时间(t)无关?如果前6天每天用药相同量(2 per day, 3 per day etc), HR会不会和时间(t)有关?
通常我碰到的TIME DEPENDENT COVARIATE要么是BINARY(时间前后... 阅读全帖
q**j
发帖数: 10612
7
sorry. There are T years and N observation with K independent variables in e
ach year. I can get a set of K estimates each period. My problem now is the
get a smooth estimate for the covariance of the K parameters, ie. a K by K m
atrix.
Sample covariance is not stable. Most Bayesian model innovate on the mean, w
ith less attention on covariance. When they actually focus on covariance, th
ey use Wishart distribution, which is very hard to optimize due to the gamma
function, when I try to find the... 阅读全帖
x******a
发帖数: 6336
8
A question regarding using PCA to capture the pairwise covariance matrix.
Suppose I have 10 times series and 250 data point for each time series in
the format of a matrix. Let's call it A of shape 10*250,Let us call the
covariance matrix COV and it is a 10*10 nonnegative defined matrix.
I would like to capture this matrix COV with a one-factor model,
0.Is PCA the right direction on this?
1.Assuming 0. is right. We find the largest eigenvalue lamdbda_M and the
correponding vectors v_M of COV. The... 阅读全帖
e**l
发帖数: 62
9
大概只知道inverse covariance matrix can tell conditional independence
structure.
本人不是统计也不是金融背景,只是计算数学,有方法弄出高维数据(multivariate
gaussian)的
inverse covariance matrix. 想找到在金融经济方面应用
大概两个大想法
1。需要用到inverse covariance matrix来算的公式
2.需要知道conditional dependence or not的金融模型或者简单问题
多谢大牛!!!
e**l
发帖数: 62
10
大概只知道inverse covariance matrix can tell conditional independence
structure.
本人不是统计也不是金融背景,只是计算数学,有方法弄出高维数据(multivariate
gaussian)的
inverse covariance matrix. 想找到在金融经济方面应用
大概两个大想法
1。需要用到inverse covariance matrix来算的公式
2.需要知道conditional dependence or not的金融模型或者简单问题
个人猜想大概在风险计算方面有点用 不过所知甚少 希望大牛提点一二
多谢大牛!!!
d*******1
发帖数: 854
11
你这个datastep 和macro的loop 全搞混了.macro运用的最高境界就是"不用".
改如下:
%let covariates=age gender center EV1;
/*deleting records with missing covariates---complete obs only*/
data temp1;
set temp0;
if n (of &covariates)<4 then delete;
run;
m*i
发帖数: 8
12
I don't want to delete any obs with n(of &covariate)<4. My goal is to delete
the obs with any one of the 4 covariates is missing. I keep only complete
obs(without any missing for all 4 covariates).
Thank you very much.
e**l
发帖数: 62
13
大概只知道inverse covariance matrix can tell conditional independence
structure.
本人不是统计也不是金融背景,只是计算数学,有方法弄出高维数据(multivariate
gaussian)的
inverse covariance matrix. 想找到在金融经济方面应用
大概两个大想法
1。需要用到inverse covariance matrix来算的公式
2.需要知道conditional dependence or not的金融模型或者简单问题
多谢大牛!!!

发帖数: 1
14
来自主题: Biology版 - covaris和biorupter哪个好?
biorupter用着用着就不准了,工程师来维护一次,又好不少,然后用着用着又坑爹了。
看来以后要换到covaris了?升级版的covaris现在一次能处理8个样品了。
v*c
发帖数: 42
15
来自主题: Mathematics版 - Variance and covariance question
if the variance of Y is var(y)=sigma^2.
Then if we assume f_hat(Y) is some function of Y, with parameter alpha_hat.
Then is the covariance of f_hat(Y) and f(Y) the same as var(Y)=sigma^2?
What is the covariance between f_hat(Y) and expectation of f(Y)? 0?
THanks,
i*****r
发帖数: 1302
16
比如说有两列数据他的mean不是0,但在计算variance和covariance的时候数据保持不变
,但mean都改成0,这叫做zero-mean deviation, 就是看和zero拨动大小, 有这么种分析
方法么?
今天老板让我这么计算variance和covariance,我说我从来没听说过有这么做的.
是我孤陋寡闻么? 这么做make sense么?
w**********y
发帖数: 1691
17
Lots of statistical models need the inverse covariance matrix..
In finance, portfolio management uses it.
Google "inverse matrix optimal portfolio selection"
"inverse matrix optimal portfolio selection with Singular Covariance Matrix"
"Optimal mean-variance portfolio selection using Cauchy–Schwarz maximization"
In some basket products in credit, it should also be useful.
k*******d
发帖数: 1340
18
如果你有1000个stock,要估计一个covariance matrix.要看多久的历史数据来估计是
合理的?如
何保证估计出来的covariance matrix是positive semidefinite的?在实际中如果出现
估算出
来的cov matrix 不是p.d.的怎么办呢? Jull的书上有简单提了一下,但是太简略了。
y*****h
发帖数: 34
19
做simulation,有true covariance matrix
还有 estimated covariance matrix
请问各位高手,用什么来衡量估计的好不好啊,在矩阵的情况下,相对应的bias, MSE,
应该怎么计算啊。。
谢谢!
x*******i
发帖数: 1791
20
可以计算bias和mse。 你可以看看关于MLE和REML的讨论。
basic idea is:
E( e*Sigmahat*e' )是一个quadratic form,可以写成两部分,这两部分包含你的Sigma。
where:
e是model residual. Sigmahat是你的covariate matrix的估计值。Sigma是true
covariate matix。
顺这个思路搞搞试试。
q**j
发帖数: 10612
21
打算得到比较smooth (stable)的mean and covariance estimates。现在mean用了baye
sian model,已经相对比较smooth了。但是Bayesian的covariance也不smooth,而且牵
涉到wishart distribution,在mle的时候非常volatile。请问这方面的大侠有什么指教
么?
当然还是要efficient的estimator。多谢了。
y*****y
发帖数: 98
22
the K variables are independent, why do you need a covariance matrix?
anyway. the covariance estimation could be very hard due to large K and
small N. the Bayesian approach is to put a prior structure (conjugate
Wishart or objective prior etc.). but i don't think that the Wishart prior
is difficult if there is no constraint. everything is conjugate. estimation
should be pretty straightforward.
by the way, you have time associated. the model should be temporal.

发帖数: 1
23
来自主题: Statistics版 - Covariance matrix estimate
统计学的不好,请教一下大家
问题 : 给定一组random variable (f1, ..., fm), 如何根据sample 来估计
covariance matrix呢?基于什么度量分析误差呢?
当observation data 数目小于 m 时,该如何处理呢?
sample covariance matrix 可以算作一个选项。
有相关note 或 书请推荐了。谢谢
a*s
发帖数: 23
24
【 以下文字转载自 Statistics 讨论区 】
发信人: AIs (AIs), 信区: Statistics
标 题: 请教“期望协方差”expected covariance的定义
发信站: BBS 未名空间站 (Sat Aug 22 04:16:38 2009, 美东)
在看Yi Ma的Segmentation of Multivariate Mixed Data via Lossy Coding and Comp
ression
http://decision.csl.illinois.edu/~yima/psfile/Ma-PAMI07.pdf)一文中有个关于
协方差的计算(sec 4.2),大概意思是:假设有向量w_1, w_2,...w_m,假设可以聚类为
k簇(标记为1、2、...k),其中向量w_i属于类j的概率为p_ij,文中直接给出了第j簇
(类)的期望协方差的计算公式,但我实在推不出这个式子,网上也找不到这个概念的
定义。请大家帮忙讲解一下和给个出处,谢谢!

发帖数: 1
25
see below:
For example, with the function type
A -> B // functional notation
public B meth(A arg) // how this looks in Java
we have the following:
Let C be a subtype of A, and D be a subtype of B. Then the following is
valid:
B b = meth(new C()); // B >= B, C < A
Object o = meth(new C()); // Object > B, C < A
but the follwoing are invalid:
D d = meth(new A()); // because D < B
B b = meth(new Object()); // because Object > A
hence, to check whether ... 阅读全帖
n*w
发帖数: 3393
26
Java应该不支持covariance?除了c#, 主流的还有哪个?
h**********c
发帖数: 4120
27
看过一个讲座,忘了,
我理解covariant是change the ceiling,contravariante是有一个floor.
实际中没用过,不过JEE里好多吗喜欢这么用。
S**********e
发帖数: 620
28
来自主题: Biology版 - covaris和biorupter哪个好?
当然covaris要更好一些,主要是低温吧,不过有点累,每次一个。
bioruptor是很难控制的,大家认为那两个圈圈在转会使得所有的样本之间受到的能量
没有差异,但是其实并非如此。曾经花了一个多月bioruptor,最终放弃。即使保证冰
水温度,而且机器转动,每个管子装同样的样品,但是最终跑完DNA条带千差万别。居
然不如最原始的方法稳定性高。或者当时我用的那台机器坏了,但是从此再也不碰它了。
k*****n
发帖数: 323
29
来自主题: Biology版 - covaris和biorupter哪个好?
covaris比较稳定,但比较容易overshearing for ChIP,shearing 多孔板,不过一次
性的管子和板子这类的耗材贵。 bioruptor老型号坑爹般的不稳定,新的据说不错。同
楼上,之前被坑得没脾气,还是老款经典探入式超声仪靠谱
l********e
发帖数: 415
30
来自主题: Biology版 - covaris和biorupter哪个好?
的确如楼上各位所言,covaris好
Z******5
发帖数: 435
31
最近单位(国内广州)计划采购一台超声破碎仪,主要做文库构建及染色质打断, 看
中了Covaris E220和E220evolution。
代理商给的报价是E220 14万美金, E220evolution 19万美金。
请教一下大家在国外买大约多少钱?
Z******5
发帖数: 435
32
最近单位(国内广州)计划采购一台超声破碎仪,主要做文库构建及染色质打断, 看
中了Covaris E220和E220evolution。
代理商给的报价是E220 14万美金, E220evolution 19万美金。
请教一下大家在国外买大约多少钱?
m******l
发帖数: 613
33
来自主题: Computation版 - covariance model如何使用viterbi回溯
我用covariance model写了一个分析RNA的程序,是用来实现alignment和二级结构预测的
但在最后实现的时候不知如何回溯
上网找了很久,找到一个用viterbi回溯的c源代码
但是,量太大,而且本人使用语言为java,转换后运行不好,极度发愁中
请问各位哪里有如何对covariace model进行回溯的算法和源代码
我现在被逼得很急,都快烦死了
p*****k
发帖数: 318
34
discussed here:
http://www.mitbbs.com/article_t/Quant/31258743.html
one approach is to rewrite X as \int_0^t (t-s) dBs
[details:
http://www.mitbbs.com/article_t/Quant/31235249.html
]
then variance:
\int_0^t s^2 ds and \int_0^t (t-s)^2 ds
covariance:
\int_0^t s*(t-s) ds
o******l
发帖数: 35
35
How hard is it to calculate the inverse covariance matrix of multivariate
gaussians? Isn't it just basic linear algebra?
l******n
发帖数: 9344
36
Hahaha...

How hard is it to calculate the inverse covariance matrix of multivariate
gaussians? Isn........
★ Sent from iPhone App: iReader Mitbbs 6.0 - iPhone Lite
A********a
发帖数: 133
37
U need reduce the dimension of the problems, first because stock returns are
likely driven by a few factors, second because there are missing obs for
such data sets. For the first, u need a factor model (Barra, Northfield, APT
, etc), for the latter, u need some robust methods to accommodate missing
observations, e.g., Em algo, Stambaugh's method and others.
To make the covariance matrix spf is easy, do the eigen-decomp, and ...
q**j
发帖数: 10612
38
sample covariance 就是正定的。如果要fancy,看newey west的经典paper。
A********a
发帖数: 133
39
sample covariance is too noisy.
Among 1000 stocks, u may have some with less than 1000 obs, better use
factor based method, check out BARRA document, if u want fancy, go RMT.
w****i
发帖数: 143
40
PCA or factor model to reduce dimension.
Should covariance matrix always be positive semidefinite?
l****o
发帖数: 2909
41
The best paper series are respectively by a Deutsche Man called T G Anderson@Duke
regarding realized covariance, a british man called neil sherpard@oxford,
and two swithland man called Olivier Ledoit and Michael Wolf@Zurich.
o***n
发帖数: 82
42
时间序列1:
date price
1 $10
2 $11
3 $12
4 $11
5 $13
时间序列2:
date price
1 $20
2 $25
3 $26
4 $23
5 $27
一般就是用这个公式:sum(xi-avgx)(yi-avgy)/5.
如果要用到rolling呢?假如day of rolling=3,这种情况怎么算covariance?
thanks
f******r
发帖数: 11
43
想要求covariance的robust estimator。比如S-estimator。请问R有什么方程可以求?
谢谢!
l********s
发帖数: 430
44
来自主题: Statistics版 - variable and covariate 的区别?
variable includes dependent variables, covariate only independent variables.
l********3
发帖数: 69
45
想用autoregressive model 来modeling covariance.
数据如下:
id treatment week0 week4 week6 week8 week12
1 1 79 79 80 80 80
2 1 83 85 85 86 87
3 1 81 82 82 83 82
4 1 81 81 82 82 81
5 1 80 82 82 82 86
6 1 76 76 76 76 75
7 1 81 83 83 85 85
8 1 77 79 79 81 81
9 1 84 87 89 . 86
10 1 74 78 78 79 78
11 1 76 77
H*******e
发帖数: 726
46
Please recommend any books or papers that deal with normal density when the
covariance matrix is rank deficient. Thanks in advance.
m*****8
发帖数: 654
47
来自主题: Statistics版 - 一个covariance的问题
一个categorical variable, 一个continuous variable的covariance,又没有人知道
一般怎样处理? 比如a=0 b就是小数字 a=1 b就是大数字。
谢谢
c**********e
发帖数: 2007
48
1. Yes.
2. No. VC means same variance and same covariance (but not zero).
c*******o
发帖数: 8869
49
来自主题: Statistics版 - 急问一个analysis of covariance的问题
用baseline做covariate 去分析 post baseline 变量Y 和change from baseline of
Y (Y-baseline), 另外一个factor 是treatment/vehicle. 现在要测试Y 和Y change
from baseline 在treatment 和vehicle 之间有没有差别. 这两个p value 应该是一样
的把? 我的怎么不一样呢?
o******6
发帖数: 538
50
☆─────────────────────────────────────☆
qian091 (november) 于 (Wed Mar 5 12:09:13 2008) 提到:
请教:已知error属于multivariate t distribution,covariance matrix 的MLE是什么
形式?和normal下的(n-1)/n * sample covariace matrix不同吧。
thanks!!
☆─────────────────────────────────────☆
jesonchang (jesonchang) 于 (Wed Mar 5 21:09:07 2008) 提到:
t is actually a scaled mixture normal. It seems that there is no closed form
solution for MLE, but EM algorithm should work definitely.
☆─────────────────────────────────────☆
1 2 3 4 5 6 7 8 9 10 下页 末页 (共10页)