[R] Improvement of Regression Model

[Bert Gunter]

These questions are off topic for this list. Try a statistical list
like stats.stackexchange.com.

Probably better yet, as your statistical skills sound like they are
somewhat limited, consult a local statistician for help.

-- Bert

On Wed, Sep 5, 2012 at 7:54 AM, Vignesh Prajapati <vignesh at tatvic.com> wrote:
>
> Hello folks,
>
>     I am on learning phase of R. I have developed Regression Model over six
> predictor variables. while development, i found my all data are not very
> linear. So, may because of this the prediction of my model is not exact.
>
>    Here is the summary of model :
> Call:
> lm(formula = y ~ x_1 + x_2 + x_3 + x_4 + x_5 + x_6)
>
> Residuals:
>      Min       1Q   Median       3Q      Max
> -125.302  -26.210    0.702   26.261  111.511
>
> Coefficients:
>             Estimate Std. Error t value Pr(>|t|)
> (Intercept) 48.62944    0.27999 173.684  < 2e-16 ***
> x_1         -0.67831    0.08053  -8.423  < 2e-16 ***
> x_2          0.07476    0.49578   0.151 0.880143
> x_3         -0.22981    0.06489  -3.541 0.000399 ***
> x_4          0.01845    0.09070   0.203 0.838814
> x_5          3.76952    0.67006   5.626 1.87e-08 ***
> x_6          0.07698    0.01565   4.919 8.75e-07 ***
> ---
> Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
>
> Residual standard error: 33.76 on 19710 degrees of freedom
> Multiple R-squared: 0.006298, Adjusted R-squared: 0.005995
> F-statistic: 20.82 on 6 and 19710 DF,  p-value: < 2.2e-16
>
> I have certain questions with this model
>
> 1. Any way to improve the accuracy of this model?
> 2.Which of the value is most useful among Residual standard error,degrees
> of freedom, Multiple R-squared, Adjusted R-squared, F-statisti,  p-value
> for choosing best model from numbers of model ?
> 3.Is it appropriate to use polynomial model with these data?
> 4.In case when i am using polynomial model for regression, which degree is
> most appropriate for it?
>
>
> Thanks
> Vignesh
>
> ______________________________________________
> 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.
>



--

Bert Gunter
Genentech Nonclinical Biostatistics

Internal Contact Info:
Phone: 467-7374
Website:
http://pharmadevelopment.roche.com/index/pdb/pdb-functional-groups/pdb-biostatistics/pdb-ncb-home.htm