Re: [R] Compare linear regressios for significant differences of the slopes

[Rainer M Krug]

Dieter Menne wrote:
> Rainer M Krug wrote:
>>> I have (8 measures * 96 groups) = 768 datasets for which I did linear
>>> regressions using lm().

Sorry for my (probably incorrect) usage of "group" and "measure".

Here a (probably better) description of my design:

I ran 96 different simulations (spread of a species along a transect) 
over four generations, based on different parameter sets. These resulted 
in 96 results (groups). Now I have 8 different ways to describe the 
result of one simulation based on x individuals further away then 
distance d, where x is replaced by 1, 5, 10, 50, 100, 500, 1000 and 5000 
(measures). For each group / simulation, I did linear regressions for 
each measure

 > lm.measure_1 <- lm(distance ~ generation)
...

resulting in lm.measure_1 to lm.measure_8

Within each group (based on one simulation), I get a different slope for 
each measure.

What I want to know is if these resulting slopes differ within one group 
/ simulation.

>>>
>>> Now I want to compare the slopes for each of the 8 measures in each of 
>>> the 96 groups. As I understand , I can not use
 anova(lm1, ..., lm8)
>>> as the lm1 ... lm8 are based on different datasets.
>>>
> 
> Instead of doing this in two steps, you would better use lme in package nlme 
> to
> test the hypothesis in one run. I don't understand the details of you design,
> but is looks like the oxboys example in Pinheiro/Bates (the book of nlme) 
> could
> give you a first starter.
> 
> Dieter
> 
> __
> R-help@stat.math.ethz.ch 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.


-- 
Rainer M. Krug, Dipl. Phys. (Germany), MSc Conservation
Biology (UCT)

Department of Conservation Ecology and Entomology
University of Stellenbosch
Matieland 7602
South Africa

Tel:+27 - (0)72 808 2975 (w)
Fax:+27 - (0)21 808 3304
Cell:   +27 - (0)83 9479 042

email:  [EMAIL PROTECTED]
[EMAIL PROTECTED]

__
R-help@stat.math.ethz.ch 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.

Re: [R] Compare linear regressios for significant differences of the slopes

[Rainer M Krug]

Hi

I haven't received any ideas yet - I just wanted to confirm if this is a 
simple question? Should I follow the idea of checking if slope +- stddev 
slope overlap?

Thanks,

Rainer

Rainer M Krug wrote:
> Hi
> 
> I have (8 measures * 96 groups) = 768 datasets for which I did linear
> regressions using lm().
> 
> Now I want to compare the slopes for each of the 8 measures in each of 
> the 96 groups. As I understand , I can not use
>> anova(lm1, ..., lm8)
> as the lm1 ... lm8 are based on different datasets.
> 
> I also read in previous discussions in this list, that I can see if the 
> slope +- stddev(slope) overlap, but this seems a long process for the 
> huge number of comparisons.
> 
> Therefore my question: is there a way to compare the slopes of lm() 
> which are based on different datasets and what is the easiest way to do
> it for this large number of datasets?
> 
> Thanks in advance for your help,
> 
> Rainer
> 


-- 
Rainer M. Krug, Dipl. Phys. (Germany), MSc Conservation
Biology (UCT)

Department of Conservation Ecology and Entomology
University of Stellenbosch
Matieland 7602
South Africa

Tel:+27 - (0)72 808 2975 (w)
Fax:+27 - (0)21 808 3304
Cell:   +27 - (0)83 9479 042

email:  [EMAIL PROTECTED]
[EMAIL PROTECTED]

__
R-help@stat.math.ethz.ch 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.