[R-sig-ME] Fwd: Re: ANOVA for large data sets

[Ben Bolker]

  cc'ing to r-sig-mixed-models -- I really can't have offline
conversations about statistical advice ...

-------- Forwarded Message --------
Subject: 	Re: [R-sig-ME] ANOVA for large data sets
Date: 	Sun, 16 Nov 2014 19:10:23 +0000 (UTC)
From: 	Aneta <aneta871 at yahoo.com>
Reply-To: 	Aneta <aneta871 at yahoo.com>
To: 	Ben Bolker <bbolker at gmail.com>



Hi Ben,

Thank you very much for your response. Yes I need to automate separate
analysis.

*The outline of the experiment:*

10 replicates of reference and 10 replicates of test samples are tested
under 5 independent conditions. 6 time points per condition are collected.

All samples at each condition and at each time point are tested by
multiple methods (five of them). One method has from 3 to 12 different
attributes.

I need to compare reference and test sample at each attribute level per
each condition I need to determine if there is a difference or not
between reference and test material.

I believe I need to use loops as you suggested.

I also need to address one more thing in ANOVA. Some of my attributes
that I am testing start at different level and I need to account for it
in ANOVA. There is a few % difference in the starting material
(reference versus testing material). Would you please help me out how to
address it in ANOVA using R?

Thank you very much for your help,

Aneta




On Sunday, November 16, 2014 8:22 AM, Ben Bolker <bbolker at gmail.com> wrote:


Aneta <aneta871 at ... <mailto:aneta871 at ...>> writes:


>  Hi Everyone, I am very new to R programming and I need your help
> regarding two way ANOVA model.  I have one variable (response) and
> three factors (Source, Batch and Time). I am always going to have a
> difference within time so probably I do not want to include it (??)
> in the analysis.  I need to identify if there is a difference
> between the Source. I know how to run the test for one sample.
> However I do not know how to process multiple samples (large data
> sets) with multiple variables sharing the same three factors.
> Please help me out! Please let me know if you need more
> clarification and I will be happy to provide it to you.  I am
> looking forward to your response.  Best!  Aneta

  There is indeed probably not enough detail here for us to help
you.  Consider looking at http://tinyurl.com/reproducible-000
for more information about writing good reproducible examples in R.
It's not clear whether you're looking for information about how
to use for loops to automate separate analyses over different data
sets, or to use the multiple samples as random effects in a mixed
model.  As far as being very new to R programming, there are many,
many resources available online (and lots of good books) -- it's
probably best to read some things that are relevant to your subject
area, and to browse the [r] tag on StackOverflow.

_______________________________________________
R-sig-mixed-models at r-project.org
<mailto:R-sig-mixed-models at r-project.org> mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models