Statistical analysis LBH song degradation
## Global model call: uMCMCglmm(fixed = degrad ~ life.span.class + Vegetation.scl +
## dist.scl + Vegetation.scl:dist.scl, random = ~Point.ID, data = xc.snr2,
## nitt = itrns, verbose = FALSE)
## ---
## Model selection table
## (Int) dst.scl lif.spn.cls Vgt.scl dst.scl:Vgt.scl df logLik AICc
## 16 0.2854 0.02235 + 0.03091 0.008550 7 17156.80 -34299.6
## 14 0.2876 0.02241 0.03087 0.008475 6 17155.19 -34298.4
## 8 0.2924 0.02159 + 0.03162 6 17116.34 -34220.7
## 6 0.2940 0.02139 0.03180 5 17114.90 -34219.8
## 7 0.2933 + 0.05337 5 17013.19 -34016.4
## 5 0.2951 0.05336 4 17011.98 -34015.9
## 4 0.2908 0.04637 + 5 16954.28 -33898.6
## 2 0.2920 0.04632 4 16953.04 -33898.1
## 3 0.2911 + 4 15000.89 -29993.8
## 1 0.2925 3 14999.76 -29993.5
## delta weight
## 16 0.00 0.649
## 14 1.23 0.351
## 8 78.92 0.000
## 6 79.81 0.000
## 7 283.22 0.000
## 5 283.65 0.000
## 4 401.04 0.000
## 2 401.52 0.000
## 3 4305.82 0.000
## 1 4306.07 0.000
## Models ranked by AICc(x)
## Random terms (all models):
## '~Point.ID'##
## Iterations = 3001:9991
## Thinning interval = 10
## Sample size = 700
##
## DIC: -34275.69
##
## G-structure: ~Point.ID
##
## post.mean l-95% CI u-95% CI eff.samp
## Point.ID 0.001294 0.000712 0.001995 700
##
## R-structure: ~units
##
## post.mean l-95% CI u-95% CI eff.samp
## units 0.008579 0.008433 0.008793 700
##
## Location effects: degrad ~ life.span.class + Vegetation.scl + dist.scl + Vegetation.scl:dist.scl
##
## post.mean l-95% CI u-95% CI eff.samp pMCMC
## (Intercept) 2.863e-01 2.734e-01 2.987e-01 700 <0.001 **
## life.span.classshort 2.740e-03 6.335e-05 5.311e-03 700 0.0257 *
## Vegetation.scl 3.084e-02 2.810e-02 3.438e-02 700 <0.001 **
## dist.scl 2.248e-02 1.962e-02 2.552e-02 627 <0.001 **
## Vegetation.scl:dist.scl 8.514e-03 6.380e-03 1.021e-02 700 <0.001 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## Global model call: uMCMCglmm(fixed = spl.dff ~ life.span.class + Vegetation.scl +
## dist.scl + Vegetation.scl:dist.scl, random = ~Point.ID, data = xc.snr,
## nitt = itrns, verbose = FALSE)
## ---
## Model selection table
## (Int) dst.scl lif.spn.cls Vgt.scl dst.scl:Vgt.scl df logLik
## 16 -18.46 -3.800 + -1.675 0.2170 7 -46779.45
## 8 -18.26 -3.823 + -1.649 6 -46798.78
## 14 -17.92 -3.807 -1.663 0.2157 6 -46951.64
## 6 -17.69 -3.824 -1.649 5 -46970.42
## 4 -18.19 -5.116 + 5 -47132.97
## 2 -17.66 -5.116 4 -47298.38
## 7 -18.41 + -5.486 5 -48894.73
## 5 -17.88 -5.485 4 -49030.69
## 3 -18.29 + 4 -57336.70
## 1 -17.70 3 -57390.14
## AICc delta weight
## 16 93572.9 0.00 1
## 8 93609.6 36.65 0
## 14 93915.3 342.37 0
## 6 93950.8 377.92 0
## 4 94275.9 703.03 0
## 2 94604.8 1031.85 0
## 7 97799.5 4226.55 0
## 5 98069.4 4496.46 0
## 3 114681.4 21108.49 0
## 1 114786.3 21213.37 0
## Models ranked by AICc(x)
## Random terms (all models):
## '~Point.ID'##
## Iterations = 3001:9991
## Thinning interval = 10
## Sample size = 700
##
## DIC: 93597.05
##
## G-structure: ~Point.ID
##
## post.mean l-95% CI u-95% CI eff.samp
## Point.ID 5.278 2.462 7.852 641.7
##
## R-structure: ~units
##
## post.mean l-95% CI u-95% CI eff.samp
## units 11.58 11.37 11.81 700
##
## Location effects: spl.dff ~ life.span.class + Vegetation.scl + dist.scl + Vegetation.scl:dist.scl
##
## post.mean l-95% CI u-95% CI eff.samp pMCMC
## (Intercept) -18.4408 -19.2765 -17.7074 688.5 <0.001 **
## life.span.classshort 0.9594 0.8583 1.0545 607.0 <0.001 **
## Vegetation.scl -1.6684 -1.7942 -1.5418 793.5 <0.001 **
## dist.scl -3.8027 -3.9228 -3.7007 700.0 <0.001 **
## Vegetation.scl:dist.scl 0.2172 0.1508 0.2822 700.0 <0.001 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
