R help - Jan 2018 - How to run mixed model with related independent variables

I've data that look like:

Outcome             V1_AA  V1_EU  V1_NA  V2_AA  V2_EU  V2_NA
0              0.046     1.001     0.954     0.045     1.001     0.954
0              0.007     1              0.993     0.007     1              0.993
1              1.774     0.217     0.009     1.774     0.217     0.009
1              0.004     1.996     0              0.004     1.996     0
1              1.001     0.997     0.002     1.001     0.997     0.002
0              0.94        0.998     0.061     0.94        0.998     0.061
0              0.587     1.407     0.006     0.587     1.408     0.006
1              0.019     1.978     0.003     0.018     1.979     0.003

Column Outcome is dependent variable. It's dichotomous either 0 or 1.
Column 1st, 2nd, 3rd are three components of V1, similarly next three for V2.
Sum of V1_AA, V1_EU and V1_NA will be two at each row. Similarly for V2
variable's components.
Here the three predictors (I'm referring as component) are related. If AA is
higher then, NA and EU will be lesser.

I cannot simply use multivariate regression as:

Y ~ V1_AA + V1_EU + V1_NA

How do I proceed with these data?

Thanks!


	[[alternative HTML version deleted]]

Wrong list.

R-help is for help on R programming and related functionality, not
statistics, though the intersection is sometimes nonempty.

However, you appear to be seeking what might be described as a statistics
tutorial. You might try a statistics list like stats.stackexchange.com or
just do some studying on your own. I believe you need to learn about
"generalized linear models" which is implemented in the glm() function
in
the stats package (as well as others, probably). However, you will need to
gain some background to use it properly, and this is not the venue for that.

Cheers,
Bert



Bert Gunter

"The trouble with having an open mind is that people keep coming along and
sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )

On Fri, Jan 26, 2018 at 9:09 AM, Sariya, Sanjeev <ss5505 at
cumc.columbia.edu>
wrote:
> I've data that look like:
>
> Outcome             V1_AA  V1_EU  V1_NA  V2_AA  V2_EU  V2_NA
> 0              0.046     1.001     0.954     0.045     1.001     0.954
> 0              0.007     1              0.993     0.007     1
> 0.993
> 1              1.774     0.217     0.009     1.774     0.217     0.009
> 1              0.004     1.996     0              0.004     1.996     0
> 1              1.001     0.997     0.002     1.001     0.997     0.002
> 0              0.94        0.998     0.061     0.94        0.998     0.061
> 0              0.587     1.407     0.006     0.587     1.408     0.006
> 1              0.019     1.978     0.003     0.018     1.979     0.003
>
> Column Outcome is dependent variable. It's dichotomous either 0 or 1.
> Column 1st, 2nd, 3rd are three components of V1, similarly next three for
> V2. Sum of V1_AA, V1_EU and V1_NA will be two at each row. Similarly for V2
> variable's components.
> Here the three predictors (I'm referring as component) are related. If
AA
> is higher then, NA and EU will be lesser.
>
> I cannot simply use multivariate regression as:
>
> Y ~ V1_AA + V1_EU + V1_NA
>
> How do I proceed with these data?
>
> Thanks!
>
>
>         [[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]]