Dear R users,
I am now working on the hierarchical clustering methods, and
confused about the following problem.
As you know, to form clustering from the hierarchical tree generated by
the pairwise distance bw the elements, we have to set a threshold value
to cut the tree horizonally such that t
Dear R users,
Do you know if there are some specific functions under R
to do clustering?
To be specific, I have a d-dimensional vector x, and wish
to clustering these d variables of x into some finite groups
given self-defined distance measure.
So please offer me some point on this problem.
Than
Dear All
I have a problem of calculating the derivative of dxm matrix A with respect
to another dxm matrix B,
where A= [a1 a2 ... am] and B =[b1 b2 ... bm] with
ai and bj are vectors.
Actually the matrix A itself is the first order derivative
of a scalar J with respect to B, i.e., A = dJ/dB,
wher
Dear All,
In the N-dimensional space, give a data point A and a curve f,
how to write the explicit expression for calculating the
minimal distance between A and f?
Or have to use some nonlinear optimization method to calcualte it?
Thanks for your point.
Fred
[[alternative HTML vers
Dear All,
In the N-dimensional space, give a data point A and a curve f,
how to write the explicit expression for calculating the
minimal distance between A and f?
Or have to use some nonlinear optimization method to calcualte it?
Thanks for your point.
Fred
[[alternative HTML version
Hey, R-listers
When we say a function f(t) is smooth, does this mean that
f has infinite differentials with respect to t?
Or any other formal definition on this?
Thanks for your points.
Fred
[[alternative HTML version deleted]]
__
[EMAIL PR
Dear R listers,
Just a simple question.
If we say an nxm matrix (n>m) is full rank of m,
does this mean that this matrix has linearly independent columns?
They are the same definition or needs some proof?
Thanks for your answer.
Fred
[[alternative HTML version deleted]]
__
Dear R-listers,
I am now using principal curves for data analysis.
The definition of it required the accurate concept
of curve continuity (C0, C1, ..., CK) and curve
smoothness.
So if anyone can introduce the exact definition
of continuous for curves and what is the most
popular textbooks for me?
Hey, R-listers,
Given the observed N random scalar variable x, with
zero mean and unit variance, can we separate the
two independent component x1 and x2 such that
x = x1 + x2 (x1 and x2 are assumed to be zero mean)?
Maybe there is no way to figure it out, and just
wanna get some help and try it.
Hey, R-listers,
I have a question about determining the orthogonal
basis vectors.
In the d-dimensinonal space, if I already know
the first r orthogonal basis vectors, should I be
able to determine the remaining d-r orthognal basis
vectors automatically?
Or the answer is not unique?
Thanks for y
Thank, Jerome
The question is if this generalized inverse can make
their product to be identity matrix?
- Original Message -
From: "Jerome Asselin" <[EMAIL PROTECTED]>
To: "Feng Zhang" <[EMAIL PROTECTED]>; "R-Help"
<[EMAIL PROTECTED]>
Sent
Dear R-listers,
I have a dxr matrix Z, where d > r.
And the product Z*Z' is a singular square matrix.
The problem is how to get the left inverse U of this
singular matrix Z*Z', such that
U*(Z*Z') = I?
Is there any to figure it out using matrix decomposition method?
Thanks a lot for your help.
F
Hey, R-listers
I am going to plot a scatter-plot matrix using R.
For example, give a matrix X=[x1, x2, ..., xn]
where each xi is a column vector, how to plot
all the pair scatter-plots between two different
xi and xj?
Is PAIRS able to achieve this function?
Thanks for your help.
Fred
_
Hey, R-listers,
I am now going to use Bayesian mathod to estimate
a matrix parameter C.
It is assumed that C is an orthogonal matrix already.
We know, if C is an arbitrary column vector, we may
use multivariate Gaussian prior on it.
However, now it is a matrix, so what can I do to
define a proper
Hey, Rlisters.
Does anybody know how to use the package "PCURVE" to estimate a
2-Dimensional principal curve?
My 2-D data x is stored as a .txt file, looks as following:
xx xx
xx xx
...
xx xx
So how to write the command to get the principal curve?
Thanks for your point.
Fred
_
Hey, R-listers
I am a new user of R and just found the package of PCURVE which can estimate principal
curve for arbitrary
dimensional data set.
Now I have some 2-Dimensional data set X, which is stored as an Nx2 matrix in data.txt
file and looks as following:
-1.5551 2.4183
1.0051 1.0102
0.90644
Not for calculation on numbers,
just to derive the symbolic formulation with
theta, x..
- Original Message -
From: "Spencer Graves" <[EMAIL PROTECTED]>
To: "Feng Zhang" <[EMAIL PROTECTED]>
Cc: <[EMAIL PROTECTED]>
Sent: Thursday, March 27, 2003 6:08
Hey, R-listers
I was totally confused by a seemling simple first derivative
function.
Given the Kullback-Leibler divergence function between
a true pdf function P(x,theta) and an approximation pdf
function Q(theta)=q1(theta1)*q2(theta2)*...*qn(thetan),
where theta=[theta1,theta2, ..., thetan]'.
KL
Hey, all
Given a square matrix, how can I check if this matrix
is positive definite or not?
Thanks.
Fred
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Hey
I am now studying the statistical indepdence between
arbitray two random variables.
And want to use Cumulant or related method as
the starting point.
So anybody has some hints on providing me some
good textbooks or papers on cumulant or statistical
indepdence criteria?
Thanks a lot.
Fred
_
Thanks, Su.
But I want to plot the several plots in the same
x-y axis setting, not in multiple subplots.
- Original Message -
From: "Steve Su" <[EMAIL PROTECTED]>
To: "Feng Zhang" <[EMAIL PROTECTED]>
Sent: Wednesday, March 05, 2003 12:29 AM
Subject: Re:
Hey,
I want to draw several plots sequently, but have to make them dispaly in one
figure.
So how to achieve this?
Thanks.
Fred
__
[EMAIL PROTECTED] mailing list
http://www.stat.math.ethz.ch/mailman/listinfo/r-help
Hey, R-listers
Now I am going to estimate or approximate a surface in
3-D space given a large enough number of (x,y,z) data sets.
So for these 3-D data points, is it possible to get a surface
function, like z=f(x,y) to represent this underlying surface?
Thanks for your time and point.
Fred
___
Hey, R-listers
I am going to approximate arbitrary 1-D data density by
mixture of Gaussian models.
The problem is that given a set of data generated from an
unknown density function, and want to use a Gaussian mixture density model
to approximate it.
Now how to determine the number of components,
Hey, all
Will you please tell me how to generate multiple
square orthogonal matrices for data transformation usage?
Thanks.
Fred
__
[EMAIL PROTECTED] mailing list
http://www.stat.math.ethz.ch/mailman/listinfo/r-help
Hely, R-list
Now I have non-parametric curve function, that is,
I only use N 2-Dimensional data points to represent
this curve, without explicit function formulation.
And given a new measurement (x1,x)', how can I calculate the shortese
Euclidean distance from this new
data point to the above cur
Hey
Now I am going to check the independence of random variables using cumulant
function.
So if R has such package or functions to calculate
the sample cumulant of a random vector?
Thanks a lot.
Fred
__
[EMAIL PROTECTED] mailing list
http://www.stat.
: "Feng Zhang" <[EMAIL PROTECTED]>
To: "R-Help" <[EMAIL PROTECTED]>
Sent: Tuesday, February 11, 2003 12:11 AM
Subject: [R] Covariance matrix for GMM
> Hey, All
>
> Now I generate a data vector X (d-dimension column vector) from a Gaussian
> Mixture Model (G
Hey, All
Now I generate a data vector X (d-dimension column vector) from a Gaussian
Mixture Model (GMM).
That is, the pdf of vector X is
f(X) = a1*N(u1, Cov1) + a2*(u2, Cov2)
where a1+a2 = 1, N is multidimensional normal distribution, ui is the mean
vecotr, Covi is the covariance matrix, i=1, 2.
ata
>C = cov(ZeroedX); %%Covariance matrix of ZeroedX
>[U,L] = eig(C); %% Eigen decompostion of C
> SE = diag(L);
[0.89181.10981.2337]'
>SE(1)/sum(SE)
0.3813
This is the case that I was confused by.
Fred
- Original Message -
From: "Liaw, Andy" <[EMAI
Thanks for those replies.
But I tested several cases, and found the two
percentage from SVD and EVD are not
the same.
So how to explain the difference and which
one should be the right one for use
in PCA?
- Original Message -
From: "antonio rodriguez" <[EMAIL PROTECTED]>
Hey, All
In principal component analysis (PCA), we want to know how many percentage
the first principal component explain the total variances among the data.
Assume the data matrix X is zero-meaned, and
I used the following procedures:
C = covriance(X) %% calculate the covariance matrix;
[EVector
Hey
Does anybody know if R can plot the 3-dimensinal
stem graphs?
In Matlab, there is such similare function to plot
3D plots, stem3(X,Y, Z), where X, Y , Z (column vectors) are
coordinate values of data points.
Thanks.
Fred
__
[EMAIL PROTECTED] mai
Hey, all
Can anybody tell me the definition or form of
cumulant generating function for a series
of random variables x1, x2, ?
I know the moment generationg function
is E[exp(tx)], and want to know the relationships
bw cumulants and moments.
Thanks.
Fred
__
Hey, All
Now I have a data set which is n-dimensional.
And want to plot the Scatter Plot Matrix which
is n by n.
Does R have such function to achieve this?
Thanks for your point.
Fred
__
[EMAIL PROTECTED] mailing list
http://www.stat.math.ethz.ch/ma
Dear R'ers
I am trying to use some distribution to test the hypothesis
on my prediction error.
Given a large numbe of sample data with unknown distribution, I first find
some funtion to make regression.
Now for each new data point, I can calculate the prediction error xi. So how
to represent the S
Dear all,
Just a stupid question confused me for a long time.
Now suppose p_dim random vector x (column vector) are from
a multivariate normal N(mu, Sigma).
Given a sample size n, (x1, x2, ., xn),
and the sample mean is x_bar, sample covariance is S.
I can infer that
n(x_bar - mu)'*inverse(S)
37 matches
Mail list logo