Skip to content

help

4 messages · hatice gürdil, Bert Gunter, Bill Dunlap

Original
hatice gürdil
# 
Code a is working. But code b is given error like given below. How can I
write code b?
+                        sigma=matrix(c(1, .3, .3, 1), ncol=2))
[,1]        [,2]
[1,] -0.97622921 -0.87129405
[2,]  0.54763494  0.16080131
[3,] -1.16627647  0.31225125
[4,]  1.72541168  2.06513939
[5,]  0.05372489 -0.07525197
[6,] -0.85062230 -1.02188473
+                        sigma=matrix(c(.3, 1,1,1,.3, 1, 1,1, .3), ncol=3))

Error in rmvnorm(round(500, 0), mean = c(0, -1), sigma = matrix(c(0.3,  :
  mean and sigma have non-conforming size
Bert Gunter
# 
A 2 dim distribution must have a 2 x 2 covariance matrix. Your mean in b)
specifies 2 dim, but your covariance matrix is 3x3.

If you haven't just made a typo and you don't know what this means, then
either consult statistics references or find someone to help you.

Cheers,

Bert Gunter

"The trouble with having an open mind is that people keep coming along and
sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )


On Tue, Mar 16, 2021 at 10:55 AM hatice g?rdil <haticegurdil1985 at gmail.com>
wrote:

  
  


  


      

    

    

      
      

        


  

        

      Bill Dunlap
    

    

      
      #
    

  


  

      
The length of the mean vector must match the number of rows and
columns of the sigma matrix.  Once you give 3 entries in the mean
vector you will run into the problem that the sigma you are using is
not positive (semi-)definite - a variance must be the product of a
matrix and its transpose.

-Bill

On Tue, Mar 16, 2021 at 10:55 AM hatice g?rdil

        
<haticegurdil1985 at gmail.com> wrote:

            

      
      
      
    

        

      
      
    

  
  


  


      

    

    

      
      

        


  

        

      hatice gürdil
    

    

      
      #
    

  


  

      
Thank you so much
I thought that ncol is for dimension .
ncol= 2, 2x2 matris for 2 dimension
ncol= 3, 3x3 matris for 3 dimention

I have to work a little more considering what you said.

Cheers,

Hatice G?rdil.

Bill Dunlap <williamwdunlap at gmail.com>, 16 Mar 2021 Sal, 21:09 tarihinde
?unu yazd?: