R help - Feb 2008 - fitted values are different from manually calculating

Hello,

on a simple linear model the values produced from the fitted(model) function
are difference from manually calculating on calc. Will anyone have a clue...
or any insights on how fitted function calculates the values? Thank you.

-- 
-- Yianni

	[[alternative HTML version deleted]]

Hi

A simple example of a linear model:

x<-1:10
y<-3*x+1
m1<-lm(y~x)
 
y
# [1]  4  7 10 13 16 19 22 25 28 31

fitted(m1)
# 1  2  3  4  5  6  7  8  9 10 
# 4  7 10 13 16 19 22 25 28 31 

The fitted and calculated values look identical to me.

Can you give an example of how your calculated values do not match? Or
have I misunderstood your question?

Regards

JS 

 
---

-----Original Message-----
From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org]
On Behalf Of gatemaze at gmail.com
Sent: 19 February 2008 14:41
To: r-help at stat.math.ethz.ch
Subject: [R] fitted values are different from manually calculating

Hello,

on a simple linear model the values produced from the fitted(model)
function are difference from manually calculating on calc. Will anyone
have a clue...
or any insights on how fitted function calculates the values? Thank you.

--
-- Yianni

	[[alternative HTML version deleted]]

______________________________________________
R-help at r-project.org 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.

why do you say this? Check for instance the following code:

x1 <- runif(100, -5, 5)
x2 <- rnorm(100)
x3 <- rep(0:1, each = 50)
y <- 2 + 0.5 * x1 + 2 * x2 - 3 * x3 + rnorm(100)

fit <- lm(y ~ x1 + x2 + x3)

all.equal(
    as.vector(fitted(fit)),
    as.vector(model.matrix(fit) %*% coef(fit))
)


I hope it helps.

Best,
Dimitris

----
Dimitris Rizopoulos
Ph.D. Student
Biostatistical Centre
School of Public Health
Catholic University of Leuven

Address: Kapucijnenvoer 35, Leuven, Belgium
Tel: +32/(0)16/336899
Fax: +32/(0)16/337015
Web: http://med.kuleuven.be/biostat/
     http://www.student.kuleuven.be/~m0390867/dimitris.htm


----- Original Message ----- 
From: <gatemaze at gmail.com>
To: <r-help at stat.math.ethz.ch>
Sent: Tuesday, February 19, 2008 3:41 PM
Subject: [R] fitted values are different from manually calculating

> Hello,
>
> on a simple linear model the values produced from the fitted(model) 
> function
> are difference from manually calculating on calc. Will anyone have a 
> clue...
> or any insights on how fitted function calculates the values? Thank 
> you.
>
> -- 
> -- Yianni
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org 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.
> 

Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm

On Feb 19, 2008 8:41 AM,  <gatemaze at gmail.com> wrote
> on a simple linear model the values produced from the fitted(model)
function
> are difference from manually calculating on calc. Will anyone have a
clue...
> or any insights on how fitted function calculates the values? Thank you.
 ______________________________________________
> R-help at r-project.org 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.
As the posting guide (you did read the posting guide, didn't you?)
says, it helps if you can provide a reproducible example.   Otherwise,
we can only guess at what you mean.

Try taking a fitted model and examining

model.matrix(model)

and

coef(model)

It should be the case that

model.matrix(model) %*% coef(model)

is reasonably close to fitted(model).

I just saw that Dimitris wrote almost the same thing but, since I have
written it, I'll mail it anyway.

Hi Yianni,

This just proves that you should be using R as your calculator, and not the
other one!

Regards, Mark.


gatemaze wrote:
> 
> Hello,
> 
> on a simple linear model the values produced from the fitted(model)
> function
> are difference from manually calculating on calc. Will anyone have a
> clue...
> or any insights on how fitted function calculates the values? Thank you.
> 
> -- 
> -- Yianni
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org 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.
> 
> 
-- 
View this message in context:
http://www.nabble.com/fitted-values-are-different-from-manually-calculating-tp15568106p15569205.html
Sent from the R help mailing list archive at Nabble.com.