[R] how to get Residual Standard Error

[Uwe Ligges]

Zhongming Yang wrote:
> 
> Thanks for your answer.
> 
> But I really want to know whether I can get "Residual Standard Error",
> directly. If I use summary(), there is an item "Residual Standard
> Error". So I think we might can access this information directly.
> 
> Thanks again,

Well, you can get it with summary(x)$sigma, if class(x) == "lm"
(Attention: it might be completely different for other classes!).
summary() calculates much more than this value, thus it is much faster
to calculate it *directly*, i.e. in the way Douglas Bates already
pointed out.

Uwe Ligges


> > summary(mod)
> Call:
> loess(formula = y ~ x)
> 
> Number of Observations: 10
> Equivalent Number of Parameters: 4.95
> Residual Standard Error: 8.734e-16
> Trace of smoother matrix: 5.47
> 
> Control settings:
>   normalize:  TRUE
>   span      :  0.75
>   degree   :  2
>   family   :  gaussian
>   surface  :  interpolate         cell = 0.2
> 
> >>> Douglas Bates <bates at stat.wisc.edu> 12/13/02 04:15PM >>>
> "Zhongming Yang" <Zhongming.Yang at cchmc.org> writes:
> 
> > Hi,
> >
> > I use lm or loess to make smoothing. After smoothing I need
> "Residual
> > Standard Error" in my script. Could you please tell me how can I get
> > this information?
> 
> A preferred way would be to use
>  sqrt(deviance(fm)/df.residual(fm))
> if fm is your fitted model.
> 
> pFor example
> 
> > data(Formaldehyde)
> > fm <- lm(optden ~ carb, data = Formaldehyde)
> > summary(fm)
> 
> Call:
> lm(formula = optden ~ carb, data = Formaldehyde)
> 
> Residuals:
>         1         2         3         4         5         6
> -0.006714  0.001029  0.002771  0.007143  0.007514 -0.011743
> 
> Coefficients:
>             Estimate Std. Error t value Pr(>|t|)
> (Intercept) 0.005086   0.007834   0.649    0.552
> carb        0.876286   0.013535  64.744 3.41e-07 ***
> ---
> Signif. codes:  0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1
> 
> Residual standard error: 0.008649 on 4 degrees of freedom
> Multiple R-Squared: 0.999,      Adjusted R-squared: 0.9988
> F-statistic:  4192 on 1 and 4 DF,  p-value: 3.409e-07
> 
> > sqrt(deviance(fm)/df.residual(fm))
> [1] 0.0086487
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> http://www.stat.math.ethz.ch/mailman/listinfo/r-help
>