R help - Aug 2015 - accessing confidence interval values from the 'predict' function

Dear all, 

I'm wondering how can I access the confidence interval values ('upr'
and
'lwr' values) produced by the 'predict' function. For example, I
fitted
a linear regression line using: 

 fit <- lm(y ~ x) 

I then wanted to calculate a 95% confidence interval for the line, and
did this using: 

 ci <- predict(fit, data.frame(x), interval="confidence") 

I see that the 'ci' object has 'upr' and 'lwr' variables
stored in it,
but am not sure how to access them properly. 

I find I can do it using: 

 upper <- as.data.frame(ci)$upr
 lower <- as.data.frame(ci)$lwr 

However, I'm wondering is there a more 'proper' way to do it in R? I
find that things like ci$upr don't seem to work, but am not sure what's
the right way? 

Kind Regards, 

Avril 

 


-- 
 The Wellcome Trust Sanger Institute is operated by Genome Research 
 Limited, a charity registered in England with number 1021457 and a 
 company registered in England with number 2742969, whose registered 
 office is 215 Euston Road, London, NW1 2BE. 
	[[alternative HTML version deleted]]

Dear Avril

I think you will find that predict.lm returns a matrix not a data frame. 
I find str() useful when R does things I did not expect or quite understand.

Michael

On 10/08/2015 09:20, alc wrote:
>
>
> Dear all,
>
> I'm wondering how can I access the confidence interval values
('upr' and
> 'lwr' values) produced by the 'predict' function. For
example, I fitted
> a linear regression line using:
>
>   fit <- lm(y ~ x)
>
> I then wanted to calculate a 95% confidence interval for the line, and
> did this using:
>
>   ci <- predict(fit, data.frame(x), interval="confidence")
>
> I see that the 'ci' object has 'upr' and 'lwr'
variables stored in it,
> but am not sure how to access them properly.
>
> I find I can do it using:
>
>   upper <- as.data.frame(ci)$upr
>   lower <- as.data.frame(ci)$lwr
>
> However, I'm wondering is there a more 'proper' way to do it in
R? I
> find that things like ci$upr don't seem to work, but am not sure
what's
> the right way?
>
> Kind Regards,
>
> Avril
>
>
>
>
-- 
Michael
http://www.dewey.myzen.co.uk/home.html

Avril,

The more direct way to access these columns from the matrix is:

ci[, "lwr"]
ci[, "upr"]

Jean

On Mon, Aug 10, 2015 at 3:20 AM, alc <alc at sanger.ac.uk> wrote:
>
>
> Dear all,
>
> I'm wondering how can I access the confidence interval values
('upr' and
> 'lwr' values) produced by the 'predict' function. For
example, I fitted
> a linear regression line using:
>
>  fit <- lm(y ~ x)
>
> I then wanted to calculate a 95% confidence interval for the line, and
> did this using:
>
>  ci <- predict(fit, data.frame(x), interval="confidence")
>
> I see that the 'ci' object has 'upr' and 'lwr'
variables stored in it,
> but am not sure how to access them properly.
>
> I find I can do it using:
>
>  upper <- as.data.frame(ci)$upr
>  lower <- as.data.frame(ci)$lwr
>
> However, I'm wondering is there a more 'proper' way to do it in
R? I
> find that things like ci$upr don't seem to work, but am not sure
what's
> the right way?
>
> Kind Regards,
>
> Avril
>
>
>
>
> --
>  The Wellcome Trust Sanger Institute is operated by Genome Research
>  Limited, a charity registered in England with number 1021457 and a
>  company registered in England with number 2742969, whose registered
>  office is 215 Euston Road, London, NW1 2BE.
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> 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.
>
	[[alternative HTML version deleted]]