Hi all, I would be very grateful if you could please give any advice... I am running a linear mixed model on a complete randomised block experiment blocks = 11 treatments = 5 (A,B,C,D,E) data recorded on days 1, 2, 11 and 18 I'm interested in looking at the difference between treatments on a particular day e.g. difference between treatments on day 1 (I am not interested in the difference between treatments on day 1 versus day 11 etc.) My question is: Is it OK to run linear mixed regression models on each day individually? as I'm not concerned with the changes over time..... (Results for individual days show a difference between treatments on day 1 and day 2, and no difference between treatments on day 11 and 18 - this follows with what would be expected in reality) fit <- lme(y ~ Treatment, random = ~1|block) Following this I run a tukey HSD to find comparison between treatments Is this the correct approach ? any advice is greatly appreciated Aside: I did try a more complicated model: fit <- lme(y ~ Treatment*day, random = ~1|block/day) however none of the treatments were significant and it only showed that day 11 and day 8 were significantly different) Many thanks Etn
individual Linear mixed models
3 messages · Etn, ONKELINX, Thierry
Another option would be to fit the model lme(y ~ Treatment*Day, random = ~1|block) and then use the multcomp package to test the contrasts that you are interested in. E.g. only pairwise difference between treatment within the same day. You'll need to specify those contrasts manually. This model uses all available data to estimate the block effect. ir. Thierry Onkelinx Instituut voor natuur- en bosonderzoek / Research Institute for Nature and Forest team Biometrie & Kwaliteitszorg / team Biometrics & Quality Assurance Kliniekstraat 25 1070 Anderlecht Belgium + 32 2 525 02 51 + 32 54 43 61 85 Thierry.Onkelinx at inbo.be www.inbo.be To call in the statistician after the experiment is done may be no more than asking him to perform a post-mortem examination: he may be able to say 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 not ensure that a reasonable answer can be extracted from a given body of data. ~ John Tukey -----Oorspronkelijk bericht----- Van: r-sig-mixed-models-bounces at r-project.org [mailto:r-sig-mixed-models-bounces at r-project.org] Namens Etn Verzonden: zondag 28 september 2014 17:42 Aan: r-sig-mixed-models at r-project.org Onderwerp: [R-sig-ME] individual Linear mixed models Hi all, I would be very grateful if you could please give any advice... I am running a linear mixed model on a complete randomised block experiment blocks = 11 treatments = 5 (A,B,C,D,E) data recorded on days 1, 2, 11 and 18 I'm interested in looking at the difference between treatments on a particular day e.g. difference between treatments on day 1 (I am not interested in the difference between treatments on day 1 versus day 11 etc.) My question is: Is it OK to run linear mixed regression models on each day individually? as I'm not concerned with the changes over time..... (Results for individual days show a difference between treatments on day 1 and day 2, and no difference between treatments on day 11 and 18 - this follows with what would be expected in reality) fit <- lme(y ~ Treatment, random = ~1|block) Following this I run a tukey HSD to find comparison between treatments Is this the correct approach ? any advice is greatly appreciated Aside: I did try a more complicated model: fit <- lme(y ~ Treatment*day, random = ~1|block/day) however none of the treatments were significant and it only showed that day 11 and day 8 were significantly different) Many thanks Etn _______________________________________________ R-sig-mixed-models at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models * * * * * * * * * * * * * D I S C L A I M E R * * * * * * * * * * * * * Dit bericht en eventuele bijlagen geven enkel de visie van de schrijver weer en binden het INBO onder geen enkel beding, zolang dit bericht niet bevestigd is door een geldig ondertekend document. The views expressed in this message and any annex are purely those of the writer and may not be regarded as stating an official position of INBO, as long as the message is not confirmed by a duly signed document.
Thank you very much, your answer is greatly appreciated On Mon, Sep 29, 2014 at 10:26 AM, ONKELINX, Thierry <
Thierry.ONKELINX at inbo.be> wrote:
Another option would be to fit the model lme(y ~ Treatment*Day, random =
~1|block) and then use the multcomp package to test the contrasts that you
are interested in. E.g. only pairwise difference between treatment within
the same day. You'll need to specify those contrasts manually.
This model uses all available data to estimate the block effect.
ir. Thierry Onkelinx
Instituut voor natuur- en bosonderzoek / Research Institute for Nature and
Forest
team Biometrie & Kwaliteitszorg / team Biometrics & Quality Assurance
Kliniekstraat 25
1070 Anderlecht
Belgium
+ 32 2 525 02 51
+ 32 54 43 61 85
Thierry.Onkelinx at inbo.be
www.inbo.be
To call in the statistician after the experiment is done may be no more
than asking him to perform a post-mortem examination: he may be able to say
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 not
ensure that a reasonable answer can be extracted from a given body of data.
~ John Tukey
-----Oorspronkelijk bericht-----
Van: r-sig-mixed-models-bounces at r-project.org [mailto:
r-sig-mixed-models-bounces at r-project.org] Namens Etn
Verzonden: zondag 28 september 2014 17:42
Aan: r-sig-mixed-models at r-project.org
Onderwerp: [R-sig-ME] individual Linear mixed models
Hi all,
I would be very grateful if you could please give any advice...
I am running a linear mixed model on a complete randomised block experiment
blocks = 11
treatments = 5 (A,B,C,D,E)
data recorded on days 1, 2, 11 and 18
I'm interested in looking at the difference between treatments on a
particular day e.g. difference between treatments on day 1 (I am not
interested in the difference between treatments on day 1 versus day 11 etc.)
My question is: Is it OK to run linear mixed regression models on each day
individually? as I'm not concerned with the changes over time.....
(Results for individual days show a difference between treatments on day 1
and day 2, and no difference between treatments on day 11 and 18 - this
follows with what would be expected in reality)
fit <- lme(y ~ Treatment, random = ~1|block)
Following this I run a tukey HSD to find comparison between treatments
Is this the correct approach ? any advice is greatly appreciated
Aside: I did try a more complicated model:
fit <- lme(y ~ Treatment*day, random = ~1|block/day) however none of the
treatments were significant and it only showed that day
11 and day 8 were significantly different)
Many thanks
Etn
[[alternative HTML version deleted]]
_______________________________________________ R-sig-mixed-models at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models * * * * * * * * * * * * * D I S C L A I M E R * * * * * * * * * * * * * Dit bericht en eventuele bijlagen geven enkel de visie van de schrijver weer en binden het INBO onder geen enkel beding, zolang dit bericht niet bevestigd is door een geldig ondertekend document. The views expressed in this message and any annex are purely those of the writer and may not be regarded as stating an official position of INBO, as long as the message is not confirmed by a duly signed document.