[R] Creating a data set within a function

[Anup Nandialath]

Dear Friends,

I'm trying to find if there is a way to automate creation of the design matrix. 
Suppose we are interested in say running an autoregressive model. The user 
inputs the following data

myfunAR - function(y, order)
{.
..
}

now here y is the data series and order represents the level of the process. In 
other words if order=2 then we have an AR (2) process. Now it is easy to to 
create the y vector within the function, but I'm not clear on how to create the 
design matrix. 

For instance if order=2 then

y - as.matrix(rnorm(100))
ynew - as.matrix(y[3:nrow(y),1])
x - as.matrix(cbind(rep(1, nrow(y)-2), y[2:(nrow(y)-1),1], y[1:(nrow(y)-2),1]))

ynew and x gives me the response vector and design matrix respectively. 
however, I'm trying to write a general function which will accomodate any 
order. Hence given the user inputs y and the order, is there a way to program 
the creation of the x matrix automatically. 

The long way would be

if (order=1)
{%5}

if (order=2)
{%5}

but this will force me to limit at some point.Is there an alternative way to 
program this??

Thanks in advance
Regards

Anup



   
-
Building a website is a piece of cake. 

[[alternative HTML version deleted]]

__
R-help@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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Creating a data set within a function

[Gabor Grothendieck]

Check out ?embed

On 8/19/07, Anup Nandialath [EMAIL PROTECTED] wrote:
 Dear Friends,

 I'm trying to find if there is a way to automate creation of the design 
 matrix. Suppose we are interested in say running an autoregressive model. The 
 user inputs the following data

 myfunAR - function(y, order)
 {.
 ..
 }

 now here y is the data series and order represents the level of the process. 
 In other words if order=2 then we have an AR (2) process. Now it is easy to 
 to create the y vector within the function, but I'm not clear on how to 
 create the design matrix.

 For instance if order=2 then

 y - as.matrix(rnorm(100))
 ynew - as.matrix(y[3:nrow(y),1])
 x - as.matrix(cbind(rep(1, nrow(y)-2), y[2:(nrow(y)-1),1], 
 y[1:(nrow(y)-2),1]))

 ynew and x gives me the response vector and design matrix respectively. 
 however, I'm trying to write a general function which will accomodate any 
 order. Hence given the user inputs y and the order, is there a way to program 
 the creation of the x matrix automatically.

 The long way would be

 if (order=1)
 {%5}

 if (order=2)
 {%5}

 but this will force me to limit at some point.Is there an alternative way to 
 program this??

 Thanks in advance
 Regards

 Anup




 -
 Building a website is a piece of cake.

[[alternative HTML version deleted]]

 __
 R-help@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
 and provide commented, minimal, self-contained, reproducible code.


__
R-help@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
and provide commented, minimal, self-contained, reproducible code.