[R-sig-ME] Orthogonal Polynomial contrasts with ordered factors

Wed Dec 16 12:38:13 CET 2015

I'll take a crack at the B questions.  Keep in mind that this is an opinion only.  A significant fourth order by other factor interaction, especially when the lower order polynomial by factor interactions are not significant means that you have probably fit a polynomial to a non-polynomial effect.  Your mention of a plateau tends to support this, at least to me.  Some sort of non-linear effect (sigmoidal, four or five factor logistic) may make more sense from a biological perspective. Steve Denham Director, Biostatistics MPI Research, Inc.

      From: Quentin Schorpp <quentin.schorpp at ti.bund.de>
 To: "r-sig-mixed-models at r-project.org" <r-sig-mixed-models at r-project.org> 
 Sent: Tuesday, December 15, 2015 8:14 AM
 Subject: [R-sig-ME] Orthogonal Polynomial contrasts with ordered factors

Hello,

I would appreciate to get to know more about the use of polynomial 
contrasts in lme4::glmer.
Does anybody could give me an advice for literature about that subject.

In particular
A:  I read, that if a second order polynomial is significant in the 
summary output, then it is supposed to be significant AFTER the first 
order polynomial was                taken into account. Is that right?

B1 : What happens if i use an ordered factor with another factor 
(ordered or not) in an itneraction term? What does a signficant 
interaction of the second                factor (any level) with the 
fourth power polynomial of the first ordered factor tell me?
B2: And waht does it tell me when the lower order polynomials are not 
significant in the interaction?

For more interested readers:

_The data_
My data is abundances of earthworms. I sampled 15 fields, three times 
(samcam) during two years, with 4 pseudoreplicates per field (N=180).
The factor age_class describes the stage of development of the field, it 
has 5 levels ((n = 3 replicates).
However, one of these levels A_Cm has n=6 since i had to switch the 
fields in the second year.
Field.ID is my random factor, to control for the pseudoreplication per 
field and the longitudinal character of the data.  For the sake of less 
complexity samcam stayed non-ordered.

Here is the design

  field.ID\samcam1 2 3 1 4 4 4 2 4 4 4 3 4 4 4 4 4 4 4 5 4 4 4 6 4 4 4 7 4 
4 4 8 4 4 4 9 4 4 4 10 4 4 4 11 4 4 4 _12 4 4 4_ 13 4 0 0 Fields had to 
be switched in the second year 14 4 0 0 15 4 0 0 16 0 4 4 17 0 4 4 18 0 4 4

Other continuous predictor variables were scaled before analysis.

data structure:
  $ abundance      : num  0 0 3 3 2 1 2 5 12 5 ...

  $ ID            : Factor w/ 180 levels "1","2","3","4",..: 1 2 3 4 5 
6 7 8 9 10 ...
  $ field.ID      : Factor w/ 18 levels "1","2","3","4",..: 1 1 1 1 2 2 
2 2 3 3 ...
  $ age_class      : Ord.factor w/ 5 levels "A_Cm"<"B_Sp_young"<..: 5 5 
5 5 5 5 5 5 5 5 ...
  $ samcam        : Factor w/ 3 levels "1","2","3": 1 1 1 1 1 1 1 1 1 1 ...
  $ hole          : Factor w/ 4 levels "1","2","3","4": 1 2 3 4 1 2 3 4 
1 2 ...

  $ scl.pH        : num  -1.553 -1.553 -1.553 -1.553 0.715 ...
  $ scl.mc        : num  -1.072 -1.072 -1.072 -1.072 -0.429 ...
  $ scl.cn        : num  -0.703 -0.703 -0.703 -0.703 -0.474 ...
  $ scl.sand      : num  -0.245 -0.245 -0.245 -0.245 -0.0127 ...
  $ scl.silt      : num  -0.897 -0.897 -0.897 -0.897 -1.529 ...
  $ scl.clay      : num  1.19 1.19 1.19 1.19 1.66 ...
  $ scl.ata1      : num  1.6471 1.6471 1.6471 1.6471 0.0894 ...
  $ scl.atb1      : num  1.6658 1.6658 1.6658 1.6658 0.0659 ...
  $ scl.hum1      : num  -1.378 -1.378 -1.378 -1.378 0.429 ...

_my hyptheses are_
1. abundance increases with increasing age_class
2. If abundance increases over the age classes it will be observed by 
increasing abundance during the period of sampling
(3. Abundance increases during the period of sampling)

_The Model was :_
best.mod <- glmer(abundance~ age_class*samcam + scl.prec1 + 
scl.mc*scl.pH  + (1|field.ID)  ,data=data,family=poisson, 
control=glmerControl(optimizer="bobyqa"))

here is The Model output of one of the best models revealed by 
MuMIn::dredge:

Generalized linear mixed model fit by maximum likelihood (Laplace Approximation) ['glmerMod']
  Family: poisson  ( log )
Formula: anc ~ age_class * samcam + I(scl.ats1^2) + scl.prec1 + (1 | field.ID)
    Data: data
Control: glmerControl(optimizer = "bobyqa")

      AIC      BIC  logLik deviance df.resid
      731      789    -348      695      162

Scaled residuals:
    Min    1Q Median    3Q    Max
-2.181 -0.696 -0.171  0.644  4.178

Random effects:
  Groups  Name        Variance Std.Dev.
  field.ID (Intercept) 0.263    0.513
Number of obs: 180, groups:  field.ID, 18

Fixed effects:
                    Estimate Std. Error z value Pr(>|z|)
(Intercept)          0.6457    0.2079    3.11  0.0019 **
age_class.L          1.9924    0.4416    4.51  6.4e-06 ***
age_class.Q          -0.8644    0.4204  -2.06  0.0398 *
age_class.C          -0.2373    0.4007  -0.59  0.5537
age_class^4          0.7026    0.3591    1.96  0.0504 .
samcam2              0.8549    0.2074    4.12  3.7e-05 ***
samcam3              0.3074    0.1852    1.66  0.0969 .
I(scl.ats1^2)        -0.3328    0.1038  -3.21  0.0013 **
scl.prec1            0.2241    0.0851    2.63  0.0085 **
age_class.L:samcam2  -0.3474    0.5463  -0.64  0.5248
age_class.Q:samcam2  0.1074    0.4766    0.23  0.8216
age_class.C:samcam2  0.8910    0.3644    2.44  0.0145 *
_age_class^4:samcam2 -1.0352 0.2601 -3.98 6.9e-05 *** _  # HERE is the significant interaction of interest!
age_class.L:samcam3  0.1274    0.5125    0.25  0.8038
age_class.Q:samcam3  -0.1801    0.4429  -0.41  0.6842
age_class.C:samcam3  0.5659    0.3615    1.57  0.1174
_age_class^4:samcam3 -0.6489 0.2617 -2.48 0.0131 * ___# HERE is the significant interaction of interest!

_Interpretation:_
I understood, that the relationship was linear in general, as indicated 
by the second line of the output, and this did not change between the 
sampling campaigns. However, during the second and third sampling 
campaign the relationship of abundances in the age_classes was 
characterised by a stronger slope in younger classes and reached a 
plateau afterwards, as indicated by the fourth power.
The missing of the interaction between age_class and samcam1 is very 
hard for me to understand

I'm thankful for any advices!

Quentin

-- 
Quentin Schorpp, M.Sc.
Thünen-Institut für Biodiversität
Bundesallee 50
38116 Braunschweig (Germany)

Tel:  +49 531 596-2524
Fax:  +49 531 596-2599
Mail: quentin.schorpp at ti.bund.de
Web:  http://www.ti.bund.de

Das Johann Heinrich von Thünen-Institut, Bundesforschungsinstitut für Ländliche Räume, Wald und Fischerei – kurz: Thünen-Institut –
besteht aus 15 Fachinstituten, die in den Bereichen Ökonomie, Ökologie und Technologie forschen und die Politik beraten.

Quentin Schorpp, M.Sc.
Thünen Institute of Biodiversity
Bundesallee 50
38116 Braunschweig (Germany)

Tel:  +49 531 596-2524
Fax:  +49 531 596-2599
Mail: quentin.schorpp at ti.bund.de
Web:  http://www.ti.bund.de

The Johann Heinrich von Thünen Institute, Federal Research Institute for Rural Areas, Forestry and Fisheries – Thünen Institute in brief –
consists of 15 specialized institutes that carry out research and provide policy advice in the fields of economy, ecology and technology.

    [[alternative HTML version deleted]]

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

	[[alternative HTML version deleted]]