Thank you very much Salvador.
Yes, I think most of my data are pseudoreplicates, the sampling unit was
the plot and there was several measurements through time at the plot. This
is why I was thinking in the mixed model to take into account the structure
of my data.
Maybe I don?t need to think in hour, day and month and use:
model <- lmer(index ~ habitat + (1 | plot), data = mydata, REML = FALSE)
Manuel
El mar., 21 may. 2019 a las 14:45, Salvador SANCHEZ COLON (<
salvadorsanchezcolon at prodigy.net.mx>) escribi?:
Apologies for my insistence:
"...I agree that using the mean you miss a lot of information. The
simplest
case would be no interaction between random effects. Say,
(1|month)+(1|day)+(1|hour)+(1|plot). ..."
...and that also assumes that the only effect of random factors is on the
intercept, but not on the slope of the relationship between the fixed
factor(s) and the response. Overall, if you want to consider (isolate) all
the possible random effects that might be involved in your design, you
would need a very complex model. But you previously suggested that some of
those factors might not be that important and perhaps may be dismissed; in
my view, I wonder if some of your dat are actually pseudoreplicates (e.g.,
measurements at different times of the same day) and, if so, a parsimonious
way to handle them is by averaging across them and analyzing the average
values.
Best regards,
Salvador S?NCHEZ-COL?N
En Mar, 21 Mayo, 2019 en 14:37, Joaqu?n Aldabe <joaquin.aldabe at gmail.com>
escribi?:
Para: Manuel Sp?nola; r-sig-mixed-models at r-project.org
I agree that using the mean you miss a lot of information. The simplest
case would be no interaction between random effects. Say,
(1|month)+(1|day)+(1|hour)+(1|plot). As far as I understand, if you think
that, for example, hour effect depends on the day, then you should
consider
a nested structure of randoms effects.
Let us know your progress!
joaquin
<
https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail
<#DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2>
El mar., 21 may. 2019 a las 14:01, Manuel Sp?nola (<mspinola10 at gmail.com
Thank you very much Thierry.
Manuel
El lun., 20 may. 2019 a las 8:59, Thierry Onkelinx (<
thierry.onkelinx at inbo.be>) escribi?:
Aggregating the data will remove al lot of information. And might
introduce bias in case of an unbalanced design.
You need to think about the (combination of) variables which have a
effect. (1|plot) + (1|plot:hour) assumes a plot effect and an effect
each combination of plot and hour, but no common hour effect.
Days are nested in months. The corresponding random effect is
(1|month:day). You have (1|day) + (1|day:month) which is nonsense.
You really need to do some reading on mixed models. I recommend Zuur
(2009) Mixed Effects Models and Extensions in Ecology with R
ir. Thierry Onkelinx
Statisticus / Statistician
Vlaamse Overheid / Government of Flanders
INSTITUUT VOOR NATUUR- EN BOSONDERZOEK / RESEARCH INSTITUTE FOR NATURE
FOREST
Team Biometrie & Kwaliteitszorg / Team Biometrics & Quality Assurance
thierry.onkelinx at inbo.be
Havenlaan 88 bus 73, 1000 Brussel
www.inbo.be
///////////////////////////////////////////////////////////////////////////////////////////
To call in the statistician after the experiment is done may be no
than asking him to perform a post-mortem examination: he may be able
what the experiment died of. ~ Sir Ronald Aylmer Fisher
The plural of anecdote is not data. ~ Roger Brinner
The combination of some data and an aching desire for an answer does
ensure that a reasonable answer can be extracted from a given body of
///////////////////////////////////////////////////////////////////////////////////////////
<https://www.inbo.be>
Op ma 20 mei 2019 om 16:07 schreef Salvador S?nchez-Col?n <
salvadorsanchezcolon at prodigy.net.mx>:
Hola Manuel:
If you are not interested in examining the between-hours or
variability, then you might consider analyzing the average of your
values and thus simplify the model.
Best regards,
Salvador
Salvador S?NCHEZ-COL?N
On May 20, 2019, at 8:54 AM, Manuel Sp?nola <mspinola10 at gmail.com>
Thank you very much Thierry.
I just only want to accomodate the nested repeated measure of my
I measure the index at the same plot, several times in an hour,
days and during several month.
3 "habitats", within each habitat 12 plots, and on each plot I
index several times, within hours, several days and several months.
I am not interested in the evolution of the index in time, just to
for the repeated measure of my design (I measured the index
time on each plot).
Maybe I don't need to worry about hour, day and month?
Manuel
El lun., 20 may. 2019 a las 2:00, Thierry Onkelinx (<
thierry.onkelinx at inbo.be>) escribi?:
Dear Manuel,
You'll need to think about the structure of your random effects.
current random effect structure is (1|plot) + (1|plot:hour) +
(1|plot:hour:day) + (1|plot:hour:day:month). Which might not be
had in mind.
Best regards,
ir. Thierry Onkelinx
Statisticus / Statistician
Vlaamse Overheid / Government of Flanders
INSTITUUT VOOR NATUUR- EN BOSONDERZOEK / RESEARCH INSTITUTE FOR
FOREST
Team Biometrie & Kwaliteitszorg / Team Biometrics & Quality
thierry.onkelinx at inbo.be
Havenlaan 88 bus 73, 1000 Brussel
www.inbo.be
///////////////////////////////////////////////////////////////////////////////////////////
To call in the statistician after the experiment is done may be no
than asking him to perform a post-mortem examination: he may be
what the experiment died of. ~ Sir Ronald Aylmer Fisher
The plural of anecdote is not data. ~ Roger Brinner
The combination of some data and an aching desire for an answer
ensure that a reasonable answer can be extracted from a given
///////////////////////////////////////////////////////////////////////////////////////////
mspinola10 at gmail.com>:
Dear list members,
I am measuring an index in plots, in different hours, different
different months in 3 different "habitats".
12 plots by "habitats".
I would like to estimate the mean index in the 3 environments.
Is this model appropriate to achieve my goal?
model <- lmer(index ~ habitat + (1 | plot/hour/day/month), data =
REML = FALSE)
Best,
Manuel
--
*Manuel Sp?nola, Ph.D.*
Instituto Internacional en Conservaci?n y Manejo de Vida