(no subject)

Please read the posting guide that tells you to a) use a meaningful
subject line b) give a reproducible example if you can c) read the
manuals and help files first

If you have a vector (not a list) of numbers, say x, and you want to
center it on the median you can do

x <- c(1,2,3,4,5)

Then x - median(x) will give you the deviation of x from its median.
Note that operations in R is vectorised, so you do not need to to do
something like "for(i in 1:5) y[i] <- x[i] - median(x)".

Next you want to square this deviation and sum over all elements.

d <- x - median(x)
sum( d^2 )

Or you can do it in one line as  "sum( (x - median(x))^2 )"

Hi, 

 

I have a list of numbers. For each of the numbers, I take sum of squares of
the numbers centered on the number chosen. If it is less than a certain
constant, I will take the average of the numbers chosen.  

 

Anyone can give me a sample code. You help will be greatly appreciated. 

 

Peter


	[[alternative HTML version deleted]]

______________________________________________
R-help at stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html

Adaikalavan Ramasamy                    ramasamy at cancer.org.uk
Centre for Statistics in Medicine       http://www.ihs.ox.ac.uk/csm/
Cancer Research UK                      Tel : 01865 226 677
Old Road Campus, Headington, Oxford     Fax : 01865 226 962

Hi, 

I have a list of numbers. For each of the numbers, I take
sum of squares of the numbers centered on the number chosen.
If it is less than a certain constant, I will take the
average of the numbers chosen.  

Anyone can give me a sample code. You help will be greatly appreciated.

Peter

Let X = (x1, x2, ... , xn} be your list of numbers.

It seems that what you are looking for is the mean of the set Y:

  Y = {y1, y2, ... , ym} such that, for each yj,

    yj is in X and sum[over i]( (xi - yj)^2 ) < const

Is this right?

If so, you can do it straightforwardly with a loop, like:

  x<-rnorm(100)
  const <-150
  for( i in (1:100) ) {if(sum(x-x[i])^2<const) Y[i]<-x[i]}
  Y[!is.na(Y)]
  [1]  0.17096364 -0.32720155  0.19542299  0.13363724
  [5] -0.19961480 -0.24486536 -0.31485802 -0.33369635
  [9]  0.09981291  0.04263151  0.11127977  0.12144595
 [13] -0.27767009 -0.01242218  0.06244776  0.11646301

  mean(Y[!is.na(Y)])
  [1] -0.04101397

but I'm sure somebody out there will come up with a much
more elegant solution!

Best wishes,
Ted.


--------------------------------------------------------------------
E-Mail: (Ted Harding) <Ted.Harding at nessie.mcc.ac.uk>
Fax-to-email: +44 (0)870 094 0861  [NB: New number!]
Date: 11-Nov-04                                       Time: 20:56:08
------------------------------ XFMail ------------------------------

Sorry! I had omitted to copy in an essential line in the code
below:

On 11-Nov-04 Wei Yang wrote:

Hi, 

I have a list of numbers. For each of the numbers, I take
sum of squares of the numbers centered on the number chosen.
If it is less than a certain constant, I will take the
average of the numbers chosen.  

Anyone can give me a sample code. You help will be greatly
appreciated.

Y<-rep(NA,100) ##### This line is needed!
   x<-rnorm(100)
   const <-150
   for( i in (1:100) ) {if(sum(x-x[i])^2<const) Y[i]<-x[i]}
   Y[!is.na(Y)]
   [1]  0.17096364 -0.32720155  0.19542299  0.13363724
   [5] -0.19961480 -0.24486536 -0.31485802 -0.33369635
   [9]  0.09981291  0.04263151  0.11127977  0.12144595
  [13] -0.27767009 -0.01242218  0.06244776  0.11646301
 
   mean(Y[!is.na(Y)])
   [1] -0.04101397

but I'm sure somebody out there will come up with a much
more elegant solution!

Best wishes,
Ted.


--------------------------------------------------------------------
E-Mail: (Ted Harding) <Ted.Harding at nessie.mcc.ac.uk>
Fax-to-email: +44 (0)870 094 0861  [NB: New number!]
Date: 11-Nov-04                                       Time: 20:56:08
------------------------------ XFMail ------------------------------

______________________________________________
R-help at stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html

--------------------------------------------------------------------
E-Mail: (Ted Harding) <Ted.Harding at nessie.mcc.ac.uk>
Fax-to-email: +44 (0)870 094 0861  [NB: New number!]
Date: 11-Nov-04                                       Time: 21:23:33
------------------------------ XFMail ------------------------------