[R-sig-ME] Linear mixed model in lme4

[Diana Michl]

Hi Ricardo,

if you have fixed and random effects, then lme4 can definitely do this 
analysis. But your formula would have to look quite different. I also 
don't get your data overview - if you have it in a table, rather send 
that than a single column. While I still wouldn't know what FA7, FV7, 
and your other letter-number combinations refer to, which might make a 
difference to your model.

You're aware that you wouldn't write your equation in lme4 as you did 
here, right? You would not write mu+ and +e, but Y ~ variable1 + 
variable2 + random effect.

1. What is your Y? Is Y the specific tree clone you're trying to predict?
2. Your Female+Male is most likely one variable with 2 levels (Female 
and Male), not two. So in your formula, it would be "sex" instead or 
however you want to call it.
3. I don't know what FemxMale refers to.
4. What does Clone refer to?
5. What would your random effect(s) be? If you don't have any, lme4 is 
not right for you.

 From what you're writing, I don't think your formula is correct. From 
the data you've sent, I can't get the proper info.
So we would really need more info on what you're trying to find out and 
model.

Diana


Am 29.09.2017 um 18:52 schrieb Ricardo Francisco Duran Reyes:
> Dear all,
> I am a forestry researcher from Chile and I want to use the Lme4 packages for fitting a linear mixed model according this equation:
>   Y=mu+Female+Male+FemxMale+Clone+e
>   Where some trees are clones with know family and other are clones with unknow parents, others are family data with both parents know and other are family data with just one parent know.
>   Is lme4 capable for doing this analysis?
>   An example of how data looks is here:
>   Family
>
> Female
>
> Male
>
> Clone
>
> Type of data
>
> AH
>
> FA7
>
> FV7
>
> AH714
>
> Clonal data
>
> AH
>
> FA7
>
> FV7
>
>
>
> Full sib progeny
>
> LB
>
> FA7
>
> Unknown
>
> LB315
>
> Clonal data (one parent known)
>
> Unknown
>
> Unknown
>
> Unknown
>
> BA465
>
> Clonal data (unknown family)
>
> BT
>
> FA21
>
> FV50
>
>
>
> Full sib progeny
>
> BA
>
> G184
>
> Unknown
>
>
>
> OP progeny
>
>
> I would appreciate any help
>
> Best regards,
>
> Ricardo Dur�n
>
>
> 	[[alternative HTML version deleted]]
>
>
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models

-- 
Diana Michl, M.A.
PhD candidate
International Experimental
and Clinical Linguistics
Universität Potsdam
www.ling.uni-potsdam.de/staff/dmichl
www.duoinfernale.eu


	[[alternative HTML version deleted]]