m*****e
发帖数: 692 | 1 问题：如果要对一维数据做piecewise linear regression但是不知道结点位置和分段
，请问最好的算法是什么，在节点连续或者不连续的情况下。。。谢了~ |
|
PT
发帖数: 148 | 2 【 以下文字转载自 Computation 讨论区 】
发信人: PT (Cruiser), 信区: Computation
标 题: how to solve ill-conditioned linear systems?
发信站: BBS 未名空间站 (Sun Oct 4 22:01:48 2009, 美东)
Are there any freely available codes for doing these? Thanks. |
|
J*y
发帖数: 271 | 3 Linear regression line 是通过 minimizes the sum of the SQUARE of the
vertical distances from the points to the line.
为什么不是那条 Sum of the vertical distances 最小的线？
谢谢 |
|
f**e
发帖数: 350 | 4 Linear regression by default uses least sqaures.
If you use the second criterion, this is called the least absolute deviation
estimator, which is more difficult to minimize. |
|
|
B****n
发帖数: 11290 | 6 It is a good book, but not for most people learning linear algebra. |
|
u***r
发帖数: 4825 | 7 Introduction to Linear Algebra
4th Ed
by Gilbert Strang |
|
M****i
发帖数: 58 | 8 Consider the following second order linear ODE with mixed boundary condition: f''(t)+a(t)f(t)=0, f'(0)=u, f(1)=0, where u is a fixed real number and a(t) is a fixed continuous function on [0,1]. Is the solution to this equation unique? If so, how to prove it? Thanks! |
|
N******n
发帖数: 3003 | 9 【 以下文字转载自 Statistics 讨论区 】
发信人: NobleBen (NB), 信区: Statistics
标 题: 问个linear algebra的简单推导
发信站: BBS 未名空间站 (Wed Feb 15 15:49:57 2012, 美东)
谢谢
上面公式 到下面是怎么推出来的？
主要是上面的一个常数(1+nh)到下面的matrix中（In+h11'）的转换，谢谢 |
|
L*******t
发帖数: 2385 | 10 请教一下各位大牛：
Linear First order PDE的解一般用characteristic method来解。。请问，有没有一
般的存在唯一性定理啊？
谢谢！ |
|
发帖数: 1 | 11 N. Trefethen. David Bau, III Numerical Linear Algebra被各类大学研究所广泛使
用，本人有其中大量习题的解答，很多网上搜索不到。微信打赏5元，我就给您发
一份。WeChatID tj198411 |
|
B*********h
发帖数: 800 | 12 ☆─────────────────────────────────────☆
maglion (da木头) 于 (Mon Mar 5 19:48:55 2007) 提到:
When M.A.E is preferred over M.S.E.? How to optimize the former, since it's
not 2nd derivable?
☆─────────────────────────────────────☆
maglion (da木头) 于 (Mon Mar 5 19:50:05 2007) 提到:
I was asked this. I can't even find the answer in my graduate-level linear
regression book. Any high-hand can share knowledge?
s
☆─────────────────────────────────────☆
pseudo (small man) 于 (Mon Mar 5 20:19:19 200 |
|
|
h*******d
发帖数: 272 | 14 求书
linear programming and network flows 3rd by M.S.Bazaraa.J.J.Jarvis and H.D.
Sherali 电子版
谢谢大家 等待中。。。 |
|
w******a
发帖数: 27 | 15 要解MILP ( mixed integer linear programming)问题，请问Matlab 有没有解这类问
题的ｔｏｏｌｂｏｘ, 或者第三方提供的免费软件包。 |
|
Y******u
发帖数: 1912 | 16 i don't think this is linear optimization |
|
y********e
发帖数: 93 | 17 if it's positive-definite, matlab will solve it using Cholesky factorization
, which is fast. If not, it will use LU decomposition, which is slow.
If the performance is really an issue and you really want to optimize it,
try using parallel iterative solver implemented in CUDA. It will improve
your performance by a factor at a cost within $1k.
There are two or three existing CUDA linear solver package out there for
free. Try google it and compile them. |
|
L*******t
发帖数: 2385 | 18 想请教一下大家，如果我对High Dimension data，10维，20维，100维，做linear
inerpolation，有没有比较快速curse of dimensionality free的算法？
谢谢了！ |
|
|
t*****y
发帖数: 30 | 20 I am using linear multiregression to fit my data
ie y=ax1+bx2+cx3+dx4+ex5+fx6+g
The final R squre from the fitting is 81.94%. It is also the correlation
coefficient of experimental y and fitted y, which can be plotted.
I am wondering if there is nonlinearity buried in the data since 81.94% is
not very high.
But from the plot, I couldn't see very obvious curvature. But even if
the real relationship is nonlinear, it should be a curved plane in 6
dimensional space. I suppose I am not able to visul |
|
o**p
发帖数: 2 | 21 You may check this book:
D. Bertsimas and J. Tsitsiklis
INTRODUCTION TO LINEAR OPTIMIZATION
For polytop and face, you may consult with Integer Programming
book. |
|
c*******e
发帖数: 8624 | 22 "Linear Programming"
VASEK CHVATAL
W H Freeman and Company |
|
n*******l
发帖数: 2911 | 23
Let {Vi}, i=1:n be n vectors.
a1*V1 + a2*V2 +...+an*Vn
is a convex linear combination of {Vi} if
all ai>= 0 and a1+a2+...+an = 1. |
|
p********a
发帖数: 5352 | 24 ☆─────────────────────────────────────☆
Seven2007 (weiwei) 于 (Fri Apr 27 15:26:18 2007) 提到:
生物背景的没修过calclulus and linear algebr，也能拿到admission of MS of
statistics (自费)? 如果修了这些课，有可能拿到 TA ？
另外统计和生统区别在哪？课程，就业方向， 有知道的说说。 是不是有生物背景的
修生统有优势？ 不知现在统计就业如何？
今年拿到生物的博士，还不知何去何从？
☆─────────────────────────────────────☆
nannankevin (南南) 于 (Fri Apr 27 15:38:53 2007) 提到:
生物和生统几乎没有任何关系
☆─────────────────────────────────────☆
orange06 (orange06) 于 (Fri Apr 27 16:38:08 2007) 提到:
很多学校要求学过微积分和线性代数，概率统计 |
|
r********t
发帖数: 41 | 25 Is there any result talking about the convergence of linear regression (or
likelihood based) with diverning number of predictors?
Say n observations yi, and xi.
the dimension p of xi diverges as n, say p=p(n).
however the response may depend only on the first 10 predictors.
Many thanks! |
|
h******e
发帖数: 1791 | 26 我也在用R学习linear regression，这个命令是今天下午才知道的。明天就要交报告了
，恐怕今天晚上要熬夜了。 |
|
p********a
发帖数: 5352 | 27 ☆─────────────────────────────────────☆
himalaya (Tea) 于 (Fri May 16 22:20:31 2008) 提到:
现在有一组simulated的数据. 数据一共有1000行,每一行中有10列 分别是ID,X1,X2,X3
,I1,I2,I3,I4,I5,Y. X1,X2,X3,Y都是continuous的, I1-I5是indicator variable. 要
求对Y做linear regression. 我作出来的model效果很差 R-square<0.1.
大家能不能给点建议啊 多谢啦!
☆─────────────────────────────────────☆
himalaya (Tea) 于 (Fri May 16 22:24:20 2008) 提到:
对Y 做了box-cox transformation也没用
☆─────────────────────────────────────☆
gysonny (Mushroom) 于 (Fri May 16 23:26:14 200 |
|
m*****8
发帖数: 27 | 28 对于simple linear regression,y(i)=E(Y|X=x(i)).
One of the assumptions concerning the errors is
E(e(i)|x(i))=0, so if we draw a scatteplot of the e(i) versus x(i),we would
have null scatterplot, with no patterns.
问题是为什么要做这样一个假设，E(e(i)|x(i))=0说明e(i)和x(i)没有correlation吗
？如果是的话，怎么推出来的呢？谢谢! |
|
w********e
发帖数: 944 | 29 In the simple linear regression, the predictor X is considered as a constant
. For any level of X, X(i), the response variable Y(i) is a random variable
with mean dependent on X(i). |
|
h***i
发帖数: 3844 | 30 OLS estimator 不一定是 MLE,就是用method of moment.不是likelihood based
method.
没有用到任何distribution assumption，
当然有normal assumption的话，肯定是MLE.
如果你还有疑问,翻一下Applied linear regression 3rd edition by Sanford
Weisberg
Chapter 2 section 2.4, page 27, 第3段.
Y|
L2. |
|
s********s
发帖数: 8 | 31 This is the weakest assumption for linear regression, which
basically says the estimator should be an unbiased estimator
for E(Y|X=x(i)) or conditional mean .
For your second the question, no, this assumption doesn't say
there's no between e(i) and x(i). We can have a variance matrix
for e(i)'s which is related to x(i)'s.
Hope the above helps. Not necessarily this is the only answer and correct.
would |
|
h******a
发帖数: 198 | 32 Wiley::Introduction to Linear Regression Analysis, 4th Edition
Douglas C. Montgomery, Elizabeth A. Peck, G. Geoffrey Vining.
这本讲regression不错 |
|
h*********o
发帖数: 151 | 33 如题，ex，y = f(x,z)+e 怎么做local linear estimation啊？用什么package什么
function啊？谢谢啦！ |
|
q********i
发帖数: 795 | 34 同意你后半部分的comment, 但是hierarchical linear model跟baysian没有必然联系
。很多multi-level random effects model都可以看成是hierarchical model，根本用
不着prior.一般proc mixed,甚至proc glm都能做。
data |
|
l*******y
发帖数: 22 | 35 你说的正是我所迷惑的地方
hierarchical linear model和random effect model 或者 multi-level model看似很
像，但是有好几个疑点
第一： 前者经常在bayesian学派的书籍中出现，后者几乎只在频率学派的书中出现，
这是否说明这两类模型是两派分别提
出来的？所以还是有所区别的吧。
第二： 有一本书《mixed models》中讲到一点这两者的区别，说他们虽然结构相似，
但是前者的prior是自己给定的，而
后者的“prior”的参数是通过各种优化算法计算出来的，比如em，newton。。
可否指点一下这两者究竟有何关系？ |
|
h******a
发帖数: 198 | 36 hierarchical linear model是一种模型假设， 如果不用bayesian的话，其实都可以归
类到mixed model来处理 |
|
s*****n
发帖数: 2174 | 37 non-linear 有可以算 r square 吧, 算 correlation of fitted values and observe
d values.
如果考虑model selection的话, 就 cross validation 好了. |
|
x*******u
发帖数: 500 | 38 linear regression model 对y 有normal的要求, 请问它对x有没有要求? 如果x r
ight skew, 是不是一定要tranform 或者改成categorical variable? 请大牛指教
. 谢谢. |
|
o******6
发帖数: 538 | 39 如果MLR中含INTERACTION TERM的话，VIF肯定大，我知道CENTER THE VARIABLES的话可
以REDUCE MULTICOLLINEARITY问题，ORIGINAL MODEL是：
E(Y|X,Z)=b0+b1*X+b2*Z+b3*X*Z;where X*Z is the interaction term;
我现在要用standardized multiple linear regression,那么：
YC=(Y-MEAN OF Y)/Sy;
XC=(X-MEAN OF X)/Sx;
ZC=(Z-MEAN OF Z)/Sz；
interxz=(X*Z-MEAN OF X*Z)/Sxz
MODEL应该用一下哪一个（我觉得应该是2）?
1) E(YC)=b0+b1*XC+b2*ZC+b3*XC*ZC
2）E(YC)=b0(INTERCEPT,WILL BE 0)+b1*XC+b2*ZC+b3*interxz
那么下面的公式对不对:
E(X*Z)=corr(X,Z)*Sx*Sz+E(X)*E(Z)（这样就可以从SAS中得到，我不认为应该是直接
计算X*Z然后用P |
|
s*********t
发帖数: 3 | 40 有个关于Generalized Linear Mixed Models(GLMMs）的问题：
请问在R或SAS中能否得到 covariance matrix between fixed effect estimators (\
beta) and variance component estimator for random effect(\sigma)
在R或SAS中可以得到fixed effect estimators的variance matrix，也可以得到
variance component estimator(\sigma)的variance。但是能否输出它们两者的
covariance呢？
多谢～ |
|
w****h
发帖数: 1 | 41 有人说seber的linear regression analysis 不错，到底如何~或者别的好书，评论评
论呗 |
|
|
x*******u
发帖数: 500 | 43 如果目的是predict， 请问linear regression model是否还需要满足variance
normality和constant variance assumption？
谢谢 |
|
n******p
发帖数: 283 | 44 or linear model by Searle
Thank you so much! |
|
i******a
发帖数: 27 | 45 在复习以前的统计知识，发现当时用的课本好像是这本
Applied Regression Including Computing and Graphics
by R. D. Cook and Sanford Weisberg
时间久了，现在回头一看，怎么觉得罗里罗嗦的说不清楚，跳来跳去，看得头大。
请版上推荐一些好点的 linear regression 方面的书？有没有哪里可以下载电子版本
就最好了。
多谢！ |
|
s*r
发帖数: 2757 | 46 我看到有些人推荐这个
Harrell, F. E., Jr. (2001). Regression modeling strategies: With
applications to linear models, logistic regression, and survival analysis.
New York: Springer-Verlag. |
|
l*********s
发帖数: 5409 | 47 we use Applied Linear Statistical Models by Michael H.Kutner |
|
n*****s
发帖数: 10232 | 48 obs大概50个左右，linear regression的话可选自变量应该也比较充足。
问题就是如何区分哪种情况适合哪种model，哪位有经验的给说说 |
|
c******a
发帖数: 725 | 49 time series is for forecasting
linear regression can, more or less, imply causality if you use independent
variables. |
|
l***a
发帖数: 12410 | 50 doesn't linear regression also has some sort of "forecast" ability, when use
lead independent data as predictors?
independent |
|
