Birds_Loess_analysis_by_plot
Ron Chen
2023-06-17
## Loading required package: readxl## Loading required package: lubridate##
## Attaching package: 'lubridate'## The following objects are masked from 'package:data.table':
##
## hour, isoweek, mday, minute, month, quarter, second, wday, week,
## yday, year## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union## Loading required package: solartime## - Winter data excluded.
## - The counts of all passing / wintering species (not resident nor breeding in the sampled unit) were set to zero. Abreed_and_non_breed contains the non-breeders as well.Loess covered areas in the northern Negev
Factors are land use (KKL plantings, Bedouine agriculture and natural loess) and time. Total 5 campaigns, one of which is pilot in 2012 which does not contain the bedouin agriculture land use level. 3 levels of land use: KKL plantings: 5 campaigns 2012-2020, 9 plots in each campaign. Bedouin agriculture: 4 campaigns 2014-2020, plot numbers: 9, 11, 12 ,12 respective to years. Loess: 5 campaigns 2012-2020, plot numbers: 15,9,9,9,9 respective to years. Year 2012 had 3 sites that were not repeated: Goral (3 plots), Hatzerim Base (6 plots), Nevatim Base (3 plots). If need to throw out data, best is to throw out Nevatim and the 3 plots named Hatzerim Loess 1,2,3 (have low / outlying counts of biodiversity metrics). 5 sites with 9 plots per site (3 for each land use X proximity combination).
Raw data Total abundance: 6040 Number of observations: 1447 Total richness: 92
Filtered data Total abundance: 2448 Number of observations: 780 Total richness: 41
Model gma, abundance and richness
Richness done with rare species. Abundance and mean abundance done without rare species. Full models include cosine and sine of the time difference from June 21st (in radians).
richness
Explore data.
## [1] "RICHNESS WITH RARE SPECIES"## [1] "data with 2012"## ℹ SHA-1 hash of file is "eef55df1963ba201f57cf44513f566298756fd4f"
## [1] "data without 2012"
## [1] "data with 2012"
## [1] "data without 2012"
| richness | year_ct | site | land_use | td_sc | cos_td_rad | sin_td_rad | h_from_sunrise | cos_hsun | sin_hsun | monitors_name | wind | precipitation | temperature | clouds | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Min. : 1.000 | Min. :0.000 | Sayeret Shaked :30 | Loess :51 | Min. :-1.5653 | Min. :0.02295 | Min. :-0.9997 | Length:140 | Min. :0.1951 | Min. :-0.1642 | Eyal Shochat : 30 | 0 : 0 | 0 : 0 | 0 : 0 | 0 : 0 | |
| 1st Qu.: 3.000 | 1st Qu.:2.000 | Nahal Ashan :24 | Bedouin Agriculture:44 | 1st Qu.:-0.7244 | 1st Qu.:0.34157 | 1st Qu.:-0.9201 | Class :difftime | 1st Qu.:0.8607 | 1st Qu.: 0.1331 | Adi Domer : 0 | 1 : 0 | 3 : 0 | 1 : 0 | 1 : 0 | |
| Median : 4.000 | Median :4.000 | Mishmar Hanegev:23 | KKL Plantings :45 | Median : 0.6826 | Median :0.85208 | Median :-0.5087 | Mode :numeric | Median :0.9542 | Median : 0.2990 | Asaf Mayrose : 0 | 2 : 0 | NA’s:140 | 2 : 0 | 2 : 0 | |
| Mean : 4.593 | Mean :4.214 | Givot Goral :15 | NA | Mean : 0.6387 | Mean :0.67279 | Mean :-0.4482 | NA | Mean :0.8921 | Mean : 0.3286 | Eliraz Dvir : 0 | 3 : 0 | NA | 3 : 0 | 3 : 0 | |
| 3rd Qu.: 6.000 | 3rd Qu.:6.000 | Eshel Hanasi :12 | NA | 3rd Qu.: 1.5220 | 3rd Qu.:0.90882 | 3rd Qu.:-0.1543 | NA | 3rd Qu.:0.9893 | 3rd Qu.: 0.5090 | Eliraz Dvir and Yoav Barak: 0 | NA’s:140 | NA | NA’s:140 | NA’s:140 | |
| Max. :15.000 | Max. :8.000 | Givot Bar :12 | NA | Max. : 4.9558 | Max. :1.00000 | Max. : 0.9845 | NA | Max. :1.0000 | Max. : 0.9808 | (Other) : 0 | NA | NA | NA | NA | |
| NA | NA | (Other) :24 | NA | NA | NA | NA | NA | NA’s :51 | NA’s :51 | NA’s :110 | NA | NA | NA | NA |
no observation for all 4 weather variables. many NAs for sampling time of day variables.exclude from model.
## Warning in cor(P.anal[, lapply(X = .SD, FUN = as.numeric), .SDcols =
## IVs[1:11]], : the standard deviation is zero| richness | year_ct | site | land_use | td_sc | cos_td_rad | sin_td_rad | h_from_sunrise | cos_hsun | sin_hsun | monitors_name | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| richness | 1.0000000 | 0.0358986 | -0.2439373 | 0.3623180 | -0.0031931 | 0.1716892 | -0.0409555 | -0.1092363 | 0.1844295 | -0.0750554 | NA |
| year_ct | 0.0358986 | 1.0000000 | -0.0131923 | 0.0784319 | -0.6891876 | -0.4527528 | -0.6804369 | -0.1097558 | 0.1168999 | -0.1052239 | NA |
| site | -0.2439373 | -0.0131923 | 1.0000000 | -0.1194452 | -0.1113288 | -0.1171673 | -0.0980130 | 0.1422600 | -0.0542126 | 0.1561513 | NA |
| land_use | 0.3623180 | 0.0784319 | -0.1194452 | 1.0000000 | -0.0996863 | 0.0851086 | -0.1008691 | -0.0772346 | 0.1350010 | -0.0453437 | NA |
| td_sc | -0.0031931 | -0.6891876 | -0.1113288 | -0.0996863 | 1.0000000 | 0.5324060 | 0.9841321 | 0.0203523 | -0.1285853 | -0.0237796 | NA |
| cos_td_rad | 0.1716892 | -0.4527528 | -0.1171673 | 0.0851086 | 0.5324060 | 1.0000000 | 0.4312002 | 0.0061055 | -0.1126261 | -0.0359190 | NA |
| sin_td_rad | -0.0409555 | -0.6804369 | -0.0980130 | -0.1008691 | 0.9841321 | 0.4312002 | 1.0000000 | 0.0492202 | -0.1557296 | 0.0031361 | NA |
| h_from_sunrise | -0.1092363 | -0.1097558 | 0.1422600 | -0.0772346 | 0.0203523 | 0.0061055 | 0.0492202 | 1.0000000 | -0.9303548 | 0.9897728 | NA |
| cos_hsun | 0.1844295 | 0.1168999 | -0.0542126 | 0.1350010 | -0.1285853 | -0.1126261 | -0.1557296 | -0.9303548 | 1.0000000 | -0.8708307 | NA |
| sin_hsun | -0.0750554 | -0.1052239 | 0.1561513 | -0.0453437 | -0.0237796 | -0.0359190 | 0.0031361 | 0.9897728 | -0.8708307 | 1.0000000 | NA |
| monitors_name | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA | NA |
Fit Poisson glm, check for existence of overdispersion
## [1] "Estimating overdispersion parameter phi: (Res. Dev.)/(n-p) where n=number of observations; p=number of parameters in the model."## [1] "od = 0.760798125335199"Overdispersion parameter is < 1. Poisson more appropriate. Compare Poisson and negative binomial.
## Warning in theta.ml(Y, mu, sum(w), w, limit = control$maxit, trace =
## control$trace > : iteration limit reached
## Warning in theta.ml(Y, mu, sum(w), w, limit = control$maxit, trace =
## control$trace > : iteration limit reached## df AIC
## m0.po 16 586.8881
## m0.nb 17 588.8897## [1] "poisson"
## [1] "neg bin"
negative binomial did not converge because there is underdispersion and poisson is better.
go with mixed model.
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: poisson ( log )
## Formula: richness ~ land_use * year_ct + cos_td_rad + sin_td_rad + (1 |
## site)
## Data: P.anal
##
## AIC BIC logLik deviance df.resid
## 588.5 615.0 -285.2 570.5 131
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.6859 -0.6177 -0.1608 0.5767 3.6774
##
## Random effects:
## Groups Name Variance Std.Dev.
## site (Intercept) 0.01245 0.1116
## Number of obs: 140, groups: site, 9
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.06782 0.17914 5.961 2.51e-09 ***
## land_useBedouin Agriculture -0.26481 0.23580 -1.123 0.2614
## land_useKKL Plantings 0.32321 0.16197 1.995 0.0460 *
## year_ct -0.01841 0.03094 -0.595 0.5518
## cos_td_rad 0.37660 0.16078 2.342 0.0192 *
## sin_td_rad -0.09158 0.13362 -0.685 0.4931
## land_useBedouin Agriculture:year_ct 0.10169 0.04355 2.335 0.0195 *
## land_useKKL Plantings:year_ct 0.01537 0.03572 0.430 0.6670
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) lnd_BA ln_KKLP yer_ct cs_td_ sn_td_ l_BA:_
## lnd_sBdnAgr -0.222
## lnd_sKKLPln -0.297 0.383
## year_ct -0.492 0.269 0.454
## cos_td_rad -0.730 -0.160 -0.208 0.083
## sin_td_rad 0.147 0.013 0.144 0.403 -0.267
## lnd_sBAgr:_ 0.202 -0.805 -0.321 -0.534 0.123 0.043
## lnd_sKKLP:_ 0.233 -0.259 -0.735 -0.659 0.147 -0.061 0.492perform stepwise model selection of poisson mixed model.
## Single term deletions
##
## Model:
## richness ~ land_use * year_ct + cos_td_rad + sin_td_rad + (1 |
## site)
## npar AIC
## <none> 588.49
## cos_td_rad 1 592.12
## sin_td_rad 1 586.97
## land_use:year_ct 2 590.59remove sine of time of year.
## Single term deletions
##
## Model:
## richness ~ land_use * year_ct + cos_td_rad + (1 | site)
## npar AIC
## <none> 586.97
## cos_td_rad 1 590.14
## land_use:year_ct 2 589.43land_use * year and cosine of time of year remain. Final model:
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: poisson ( log )
## Formula: richness ~ land_use * year_ct + cos_td_rad + (1 | site)
## Data: P.anal
##
## AIC BIC logLik deviance df.resid
## 587.0 610.5 -285.5 571.0 132
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.6438 -0.6020 -0.1577 0.5573 3.6664
##
## Random effects:
## Groups Name Variance Std.Dev.
## site (Intercept) 0.01149 0.1072
## Number of obs: 140, groups: site, 9
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.083714 0.174602 6.207 5.41e-10 ***
## land_useBedouin Agriculture -0.263209 0.234868 -1.121 0.2624
## land_useKKL Plantings 0.339773 0.160606 2.116 0.0344 *
## year_ct -0.009524 0.027935 -0.341 0.7332
## cos_td_rad 0.348352 0.154097 2.261 0.0238 *
## land_useBedouin Agriculture:year_ct 0.102878 0.043278 2.377 0.0174 *
## land_useKKL Plantings:year_ct 0.013666 0.035496 0.385 0.7002
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) lnd_BA ln_KKLP yer_ct cs_td_ l_BA:_
## lnd_sBdnAgr -0.223
## lnd_sKKLPln -0.321 0.389
## year_ct -0.608 0.294 0.438
## cos_td_rad -0.720 -0.173 -0.191 0.203
## lnd_sBAgr:_ 0.196 -0.811 -0.332 -0.602 0.148
## lnd_sKKLP:_ 0.242 -0.265 -0.737 -0.693 0.147 0.494## $site
## (Intercept)
## Eshel Hanasi -0.045137191
## Givot Bar 0.002827638
## Givot Goral 0.106788644
## Hatzerim Base -0.001968742
## Mishmar Hanegev 0.075006970
## Nahal Ashan 0.065199853
## Nevatim Base 0.005947562
## Park Loess -0.093317558
## Sayeret Shaked -0.103992836
##
## with conditional variances for "site"## $site
## Registered S3 methods overwritten by 'broom':
## method from
## tidy.glht jtools
## tidy.summary.glht jtools| Observations | 140 |
| Dependent variable | richness |
| Type | Mixed effects generalized linear model |
| Family | poisson |
| Link | log |
| AIC | 586.971 |
| BIC | 610.504 |
| Pseudo-R² (fixed effects) | 0.187 |
| Pseudo-R² (total) | 0.231 |
| exp(Est.) | S.E. | z val. | p | |
|---|---|---|---|---|
| (Intercept) | 2.956 | 0.175 | 6.207 | 0.000 |
| land_useBedouin Agriculture | 0.769 | 0.235 | -1.121 | 0.262 |
| land_useKKL Plantings | 1.405 | 0.161 | 2.116 | 0.034 |
| year_ct | 0.991 | 0.028 | -0.341 | 0.733 |
| cos_td_rad | 1.417 | 0.154 | 2.261 | 0.024 |
| land_useBedouin Agriculture:year_ct | 1.108 | 0.043 | 2.377 | 0.017 |
| land_useKKL Plantings:year_ct | 1.014 | 0.035 | 0.385 | 0.700 |
| Group | Parameter | Std. Dev. |
|---|---|---|
| site | (Intercept) | 0.107 |
| Group | # groups | ICC |
|---|---|---|
| site | 9 | 0.011 |
Test whether temporal trends are significantly different from zero, using emmeans package, FDR correction for multiple comparisons.
## land_use year_ct.trend SE df z.ratio p.value
## Loess -0.00952 0.0279 Inf -0.341 0.8725
## Bedouin Agriculture 0.09335 0.0346 Inf 2.698 0.0209
## KKL Plantings 0.00414 0.0258 Inf 0.161 0.8725
##
## P value adjustment: fdr method for 3 testsTest for pairwise differences among levels of land use, apply FDR correction for multiple comparisons.
## contrast year_ct estimate SE df z.ratio p.value
## Loess - Bedouin Agriculture 4.21 -0.170 0.138 Inf -1.239 0.2154
## Loess - KKL Plantings 4.21 -0.397 0.113 Inf -3.521 0.0013
## Bedouin Agriculture - KKL Plantings 4.21 -0.227 0.116 Inf -1.959 0.0751
##
## Results are given on the log (not the response) scale.
## P value adjustment: fdr method for 3 testsSignificant increase of 9.7850508% in richness per year on average for Bedouin agriculture, no significant temporal trend for Loess and KKL Plantings.
on average over time, Loess richness (3.589255 species) is significantly lower than KKL (5.340458 species; P=0.001); Bedouin agriculture (4.2558382 species) is not significantly different from both of them.
geometric mean of abundance
Explore data. Exclude time of day because of high number of NAs.
## [1] "GEOMETRIC MEAN ABUNDANCE WITHOUT RARE SPECIES"## [1] "data with 2012"
## [1] "data without 2012"
## [1] "data with 2012"
## [1] "data without 2012"
| gma | year_ct | site | land_use | td_sc | cos_td_rad | sin_td_rad | h_from_sunrise | cos_hsun | sin_hsun | monitors_name | wind | precipitation | temperature | clouds | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Min. : 1.260 | Min. :0.000 | Sayeret Shaked :30 | Loess :51 | Min. :-1.5653 | Min. :0.02295 | Min. :-0.9997 | Length:140 | Min. :0.1951 | Min. :-0.1642 | Eyal Shochat : 30 | 0 : 0 | 0 : 0 | 0 : 0 | 0 : 0 | |
| 1st Qu.: 2.000 | 1st Qu.:2.000 | Nahal Ashan :24 | Bedouin Agriculture:44 | 1st Qu.:-0.7244 | 1st Qu.:0.34157 | 1st Qu.:-0.9201 | Class :difftime | 1st Qu.:0.8607 | 1st Qu.: 0.1331 | Adi Domer : 0 | 1 : 0 | 3 : 0 | 1 : 0 | 1 : 0 | |
| Median : 2.406 | Median :4.000 | Mishmar Hanegev:23 | KKL Plantings :45 | Median : 0.6826 | Median :0.85208 | Median :-0.5087 | Mode :numeric | Median :0.9542 | Median : 0.2990 | Asaf Mayrose : 0 | 2 : 0 | NA’s:140 | 2 : 0 | 2 : 0 | |
| Mean : 2.926 | Mean :4.214 | Givot Goral :15 | NA | Mean : 0.6387 | Mean :0.67279 | Mean :-0.4482 | NA | Mean :0.8921 | Mean : 0.3286 | Eliraz Dvir : 0 | 3 : 0 | NA | 3 : 0 | 3 : 0 | |
| 3rd Qu.: 3.207 | 3rd Qu.:6.000 | Eshel Hanasi :12 | NA | 3rd Qu.: 1.5220 | 3rd Qu.:0.90882 | 3rd Qu.:-0.1543 | NA | 3rd Qu.:0.9893 | 3rd Qu.: 0.5090 | Eliraz Dvir and Yoav Barak: 0 | NA’s:140 | NA | NA’s:140 | NA’s:140 | |
| Max. :10.371 | Max. :8.000 | Givot Bar :12 | NA | Max. : 4.9558 | Max. :1.00000 | Max. : 0.9845 | NA | Max. :1.0000 | Max. : 0.9808 | (Other) : 0 | NA | NA | NA | NA | |
| NA | NA | (Other) :24 | NA | NA | NA | NA | NA | NA’s :51 | NA’s :51 | NA’s :110 | NA | NA | NA | NA |
Fit glm, compare gamma, gaussian (poisson inappropriate because response is not discrete)
Gamma seems better than gaussian. Fit fixed and mixed models.
## Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, :
## Model failed to converge with max|grad| = 0.012328 (tol = 0.002, component 1)Mixed model did not converge, use glm:
##
## Call:
## glm(formula = gma ~ land_use * year_ct + cos_td_rad + sin_td_rad +
## site, family = Gamma, data = P.anal)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.95553 -0.28198 -0.07873 0.15650 1.16860
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.3840219 0.1001764 3.833 0.0002 ***
## land_useBedouin Agriculture -0.0842592 0.0824937 -1.021 0.3091
## land_useKKL Plantings 0.0001899 0.0583558 0.003 0.9974
## year_ct -0.0089596 0.0088011 -1.018 0.3107
## cos_td_rad -0.0206125 0.0613463 -0.336 0.7374
## sin_td_rad 0.0954936 0.0531921 1.795 0.0750 .
## siteGivot Bar -0.0780948 0.0546019 -1.430 0.1552
## siteGivot Goral 0.0075556 0.0627164 0.120 0.9043
## siteHatzerim Base -0.0337372 0.0918198 -0.367 0.7139
## siteMishmar Hanegev -0.0260323 0.0584789 -0.445 0.6570
## siteNahal Ashan 0.0940335 0.0822483 1.143 0.2551
## siteNevatim Base 0.0066576 0.1716479 0.039 0.9691
## sitePark Loess 0.0131366 0.0860731 0.153 0.8789
## siteSayeret Shaked 0.0386733 0.0779441 0.496 0.6207
## land_useBedouin Agriculture:year_ct 0.0276513 0.0126212 2.191 0.0303 *
## land_useKKL Plantings:year_ct 0.0285655 0.0124291 2.298 0.0232 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for Gamma family taken to be 0.1956952)
##
## Null deviance: 28.575 on 139 degrees of freedom
## Residual deviance: 21.703 on 124 degrees of freedom
## AIC: 445.98
##
## Number of Fisher Scoring iterations: 5perform stepwise model selection of Gaussian model.
## Start: AIC=445.98
## gma ~ land_use * year_ct + cos_td_rad + sin_td_rad + site
##
## Df Deviance AIC
## - site 8 23.307 438.18
## - cos_td_rad 1 21.725 444.09
## <none> 21.703 445.98
## - sin_td_rad 1 22.370 447.39
## - land_use:year_ct 2 23.147 449.36
##
## Step: AIC=440.23
## gma ~ land_use + year_ct + cos_td_rad + sin_td_rad + land_use:year_ct
##
## Df Deviance AIC
## - cos_td_rad 1 23.479 439.08
## <none> 23.307 440.23
## - sin_td_rad 1 24.148 442.36
## - land_use:year_ct 2 24.632 442.74
##
## Step: AIC=439.29
## gma ~ land_use + year_ct + sin_td_rad + land_use:year_ct
##
## Df Deviance AIC
## <none> 23.479 439.29
## - sin_td_rad 1 24.167 440.64
## - land_use:year_ct 2 24.952 442.45keep removing terms, because \(\Delta AIC<2\). remove sine.
## Single term deletions
##
## Model:
## gma ~ land_use * year_ct
## Df Deviance AIC
## <none> 24.167 441.45
## land_use:year_ct 2 25.657 444.51year X land use remain. This is the final model:
##
## Call:
## glm(formula = gma ~ land_use * year_ct, family = Gamma, data = P.anal)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.9292 -0.3539 -0.1036 0.1449 1.2127
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.380616 0.036636 10.389 <2e-16 ***
## land_useBedouin Agriculture -0.137185 0.062042 -2.211 0.0287 *
## land_useKKL Plantings -0.013240 0.058533 -0.226 0.8214
## year_ct -0.013438 0.007054 -1.905 0.0589 .
## land_useBedouin Agriculture:year_ct 0.024062 0.011716 2.054 0.0419 *
## land_useKKL Plantings:year_ct 0.028566 0.012488 2.288 0.0237 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for Gamma family taken to be 0.2111039)
##
## Null deviance: 28.575 on 139 degrees of freedom
## Residual deviance: 24.167 on 134 degrees of freedom
## AIC: 441.45
##
## Number of Fisher Scoring iterations: 5
| Observations | 140 |
| Dependent variable | gma |
| Type | Generalized linear model |
| Family | Gamma |
| Link | inverse |
| χ²(5) | 4.408 |
| Pseudo-R² (Cragg-Uhler) | 0.165 |
| Pseudo-R² (McFadden) | 0.054 |
| AIC | 441.450 |
| BIC | 462.041 |
| Est. | S.E. | t val. | p | |
|---|---|---|---|---|
| (Intercept) | 0.381 | 0.037 | 10.389 | 0.000 |
| land_useBedouin Agriculture | -0.137 | 0.062 | -2.211 | 0.029 |
| land_useKKL Plantings | -0.013 | 0.059 | -0.226 | 0.821 |
| year_ct | -0.013 | 0.007 | -1.905 | 0.059 |
| land_useBedouin Agriculture:year_ct | 0.024 | 0.012 | 2.054 | 0.042 |
| land_useKKL Plantings:year_ct | 0.029 | 0.012 | 2.288 | 0.024 |
| Standard errors: MLE |
According to the model, no significant temporal trend for Loess, but interaction of year and land use is significant. Test whether temporal trends are significantly different from zero, using emmeans package, FDR correction for multiple comparisons.
## land_use year_ct.trend SE df t.ratio p.value
## Loess -0.0134 0.00705 134 -1.905 0.1768
## Bedouin Agriculture 0.0106 0.00935 134 1.136 0.2581
## KKL Plantings 0.0151 0.01030 134 1.468 0.2166
##
## P value adjustment: fdr method for 3 testsNo significant temporal trend detected for all three land uses. In view of this, re-fit model without interaction term.
## Start: AIC=446.07
## gma ~ land_use + year_ct
##
## Df Deviance AIC
## - year_ct 1 25.657 444.07
## <none> 25.657 446.07
## - land_use 2 28.526 454.73
##
## Step: AIC=444.07
## gma ~ land_use
##
## Df Deviance AIC
## <none> 25.657 444.07
## - land_use 2 28.575 453.04only land use remains.
##
## Call:
## glm(formula = gma ~ land_use, family = Gamma, data = P.anal)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.8448 -0.3748 -0.1082 0.1509 1.3829
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.32831 0.02181 15.056 <2e-16 ***
## land_useBedouin Agriculture -0.03117 0.03045 -1.024 0.3078
## land_useKKL Plantings 0.09527 0.03705 2.571 0.0112 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for Gamma family taken to be 0.2249982)
##
## Null deviance: 28.575 on 139 degrees of freedom
## Residual deviance: 25.657 on 137 degrees of freedom
## AIC: 444.07
##
## Number of Fisher Scoring iterations: 5
| Observations | 140 |
| Dependent variable | gma |
| Type | Generalized linear model |
| Family | Gamma |
| Link | inverse |
| χ²(2) | 2.918 |
| Pseudo-R² (Cragg-Uhler) | 0.110 |
| Pseudo-R² (McFadden) | 0.034 |
| AIC | 444.071 |
| BIC | 455.837 |
| Est. | S.E. | t val. | p | |
|---|---|---|---|---|
| (Intercept) | 0.328 | 0.022 | 15.056 | 0.000 |
| land_useBedouin Agriculture | -0.031 | 0.030 | -1.024 | 0.308 |
| land_useKKL Plantings | 0.095 | 0.037 | 2.571 | 0.011 |
| Standard errors: MLE |
Test for pairwise differences among levels of land use, apply FDR correction for multiple comparisons.
## contrast estimate SE df t.ratio p.value
## Loess - Bedouin Agriculture 0.0312 0.0304 137 1.024 0.3078
## Loess - KKL Plantings -0.0953 0.0370 137 -2.571 0.0168
## Bedouin Agriculture - KKL Plantings -0.1264 0.0367 137 -3.443 0.0023
##
## Note: contrasts are still on the inverse scale
## P value adjustment: fdr method for 3 testsNo significant difference in GMA between Loess (3.0458883) and Bedouin agriculture (3.3653697). KKL Plantings (2.3608274) significantly lower than Loess (P=0.017) and Bedouin agriculture (P=0.002).
No significant temporal trend detected for all three land uses.
abundance
Explore data
## [1] "ABUNDANCE WITHOUT RARE SPECIES"## [1] "data with 2012"
## [1] "data without 2012"
## [1] "data with 2012"
## [1] "data without 2012"
| abundance | year_ct | site | land_use | td_sc | cos_td_rad | sin_td_rad | |
|---|---|---|---|---|---|---|---|
| Min. : 2.00 | Min. :0.000 | Sayeret Shaked :30 | Loess :51 | Min. :-1.5653 | Min. :0.02295 | Min. :-0.9997 | |
| 1st Qu.: 7.00 | 1st Qu.:2.000 | Nahal Ashan :24 | Bedouin Agriculture:44 | 1st Qu.:-0.7244 | 1st Qu.:0.34157 | 1st Qu.:-0.9201 | |
| Median : 10.00 | Median :4.000 | Mishmar Hanegev:23 | KKL Plantings :45 | Median : 0.6826 | Median :0.85208 | Median :-0.5087 | |
| Mean : 16.34 | Mean :4.214 | Givot Goral :15 | NA | Mean : 0.6387 | Mean :0.67279 | Mean :-0.4482 | |
| 3rd Qu.: 17.25 | 3rd Qu.:6.000 | Eshel Hanasi :12 | NA | 3rd Qu.: 1.5220 | 3rd Qu.:0.90882 | 3rd Qu.:-0.1543 | |
| Max. :125.00 | Max. :8.000 | Givot Bar :12 | NA | Max. : 4.9558 | Max. :1.00000 | Max. : 0.9845 | |
| NA | NA | (Other) :24 | NA | NA | NA | NA |
outlier in loess with total abundance >30. outlier in bedouin agriculture with total abundance >120. Examine:
## unit subunit site year year_ct
## 1: Loess Covered Areas in the Northern Negev <NA> Nahal Ashan 2020 8
## settlements agriculture habitat dunes land_use point_name
## 1: <NA> <NA> <NA> <NA> Loess Nahal Ashan Loess 2
## date datetime td_sc td_rad cos_td_rad
## 1: 2020-03-25 02:00:00 2020-03-25 09:25:40 -1.48902 -1.513416 0.0573492
## sin_td_rad timediff_Jun21 monitors_name wind precipitation temperature
## 1: -0.9983542 -87.91667 days Eyal Shochat <NA> <NA> <NA>
## clouds h_from_sunrise cos_hsun sin_hsun pilot richness abundance gma
## 1: <NA> 1.7 hours 0.9025853 0.4305111 FALSE 5 38 4.967254## unit subunit site year year_ct
## 1: Loess Covered Areas in the Northern Negev <NA> Givot Bar 2018 6
## settlements agriculture habitat dunes land_use
## 1: <NA> <NA> <NA> <NA> Bedouin Agriculture
## point_name date datetime td_sc
## 1: Givot Bar Bedouin Agriculture 2 2018-05-22 2018-05-22 05:21:00 0.6825762
## td_rad cos_td_rad sin_td_rad timediff_Jun21 monitors_name wind
## 1: -0.5336404 0.860961 -0.5086709 -31 days <NA> <NA>
## precipitation temperature clouds h_from_sunrise cos_hsun sin_hsun pilot
## 1: <NA> <NA> <NA> -0.42 hours 0.993961 -0.1097343 FALSE
## richness abundance gma
## 1: 7 125 5.011216PHI>1, hence choose negative binomial. Fit fixed and mixed models. Choose mixed model if possible, otherwise choose a model with fixed-effects only.
mixed model converged.
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: Negative Binomial(3.4767) ( log )
## Formula: abundance ~ land_use * year_ct + cos_td_rad + sin_td_rad + (1 |
## site)
## Data: P.anal
##
## AIC BIC logLik deviance df.resid
## 988.2 1017.7 -484.1 968.2 130
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.5959 -0.6310 -0.2227 0.3360 4.2385
##
## Random effects:
## Groups Name Variance Std.Dev.
## site (Intercept) 0.09997 0.3162
## Number of obs: 140, groups: site, 9
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.65536 0.25985 6.370 1.89e-10 ***
## land_useBedouin Agriculture 0.33579 0.33255 1.010 0.312618
## land_useKKL Plantings 0.89990 0.22217 4.051 5.11e-05 ***
## year_ct 0.04737 0.03845 1.232 0.217957
## cos_td_rad 0.54866 0.21422 2.561 0.010432 *
## sin_td_rad -0.35334 0.18317 -1.929 0.053730 .
## land_useBedouin Agriculture:year_ct 0.03225 0.05364 0.601 0.547673
## land_useKKL Plantings:year_ct -0.15429 0.04505 -3.425 0.000615 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) lnd_BA ln_KKLP yer_ct cs_td_ sn_td_ l_BA:_
## lnd_sBdnAgr -0.318
## lnd_sKKLPln -0.290 0.402
## year_ct -0.489 0.250 0.416
## cos_td_rad -0.679 -0.082 -0.176 0.155
## sin_td_rad 0.117 0.046 0.157 0.389 -0.281
## lnd_sBAgr:_ 0.225 -0.728 -0.281 -0.504 0.053 0.068
## lnd_sKKLP:_ 0.198 -0.202 -0.737 -0.575 0.119 -0.065 0.408## $site
## (Intercept)
## Eshel Hanasi -0.045137191
## Givot Bar 0.002827638
## Givot Goral 0.106788644
## Hatzerim Base -0.001968742
## Mishmar Hanegev 0.075006970
## Nahal Ashan 0.065199853
## Nevatim Base 0.005947562
## Park Loess -0.093317558
## Sayeret Shaked -0.103992836
##
## with conditional variances for "site"## $site
Perform stepwise model selection of mixed model.
## Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, :
## Model failed to converge with max|grad| = 0.00226083 (tol = 0.002, component 1)## Single term deletions
##
## Model:
## abundance ~ land_use * year_ct + cos_td_rad + sin_td_rad + (1 |
## site)
## npar AIC
## <none> 988.24
## cos_td_rad 1 992.69
## sin_td_rad 1 989.96
## land_use:year_ct 2 1000.85drop sine of time of year because \(\Delta AIC<2\)
## Warning in checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, :
## Model failed to converge with max|grad| = 0.00233194 (tol = 0.002, component 1)## Single term deletions
##
## Model:
## abundance ~ land_use * year_ct + cos_td_rad + (1 | site)
## npar AIC
## <none> 989.89
## cos_td_rad 1 992.00
## land_use:year_ct 2 1003.97land use * year and sampling time of year remain. The final model:
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: Negative Binomial(3.3486) ( log )
## Formula: abundance ~ land_use * year_ct + cos_td_rad + (1 | site)
## Data: P.anal
##
## AIC BIC logLik deviance df.resid
## 989.9 1016.4 -485.9 971.9 131
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.5846 -0.6191 -0.2535 0.3014 4.1904
##
## Random effects:
## Groups Name Variance Std.Dev.
## site (Intercept) 0.09622 0.3102
## Number of obs: 140, groups: site, 9
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.72151 0.26502 6.496 8.26e-11 ***
## land_useBedouin Agriculture 0.36259 0.34336 1.056 0.290957
## land_useKKL Plantings 0.96686 0.22215 4.352 1.35e-05 ***
## year_ct 0.07640 0.03586 2.131 0.033124 *
## cos_td_rad 0.42973 0.21112 2.035 0.041805 *
## land_useBedouin Agriculture:year_ct 0.03816 0.05468 0.698 0.485223
## land_useKKL Plantings:year_ct -0.16047 0.04539 -3.536 0.000407 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) lnd_BA ln_KKLP yer_ct cs_td_ l_BA:_
## lnd_sBdnAgr -0.349
## lnd_sKKLPln -0.324 0.402
## year_ct -0.608 0.286 0.399
## cos_td_rad -0.696 -0.034 -0.117 0.320
## lnd_sBAgr:_ 0.234 -0.751 -0.300 -0.572 0.058
## lnd_sKKLP:_ 0.209 -0.202 -0.738 -0.590 0.100 0.407## $site
## (Intercept)
## Eshel Hanasi -0.22869398
## Givot Bar 0.56150117
## Givot Goral 0.08251180
## Hatzerim Base -0.16121909
## Mishmar Hanegev 0.33649321
## Nahal Ashan -0.00925356
## Nevatim Base -0.06818663
## Park Loess -0.20895200
## Sayeret Shaked -0.28722925
##
## with conditional variances for "site"## $site
Not the greatest fit in the world. Take into account when stressing the strength of the results.
Interpretation of abundance model:
| Observations | 140 |
| Dependent variable | abundance |
| Type | Mixed effects generalized linear model |
| Family | Negative Binomial(3.3486) |
| Link | log |
| AIC | 989.895 |
| BIC | 1016.369 |
| Pseudo-R² (fixed effects) | 0.486 |
| Pseudo-R² (total) | 0.782 |
| Est. | S.E. | z val. | p | |
|---|---|---|---|---|
| (Intercept) | 1.722 | 0.265 | 6.496 | 0.000 |
| land_useBedouin Agriculture | 0.363 | 0.343 | 1.056 | 0.291 |
| land_useKKL Plantings | 0.967 | 0.222 | 4.352 | 0.000 |
| year_ct | 0.076 | 0.036 | 2.131 | 0.033 |
| cos_td_rad | 0.430 | 0.211 | 2.035 | 0.042 |
| land_useBedouin Agriculture:year_ct | 0.038 | 0.055 | 0.698 | 0.485 |
| land_useKKL Plantings:year_ct | -0.160 | 0.045 | -3.536 | 0.000 |
| Group | Parameter | Std. Dev. |
|---|---|---|
| site | (Intercept) | 0.310 |
| Group | # groups | ICC |
|---|---|---|
| site | 9 | 0.168 |
all model effects are significant. Test for difference of temporal trend from zero for each land use.
## land_use year_ct.trend SE df z.ratio p.value
## Loess 0.0764 0.0359 Inf 2.131 0.0331
## Bedouin Agriculture 0.1146 0.0451 Inf 2.542 0.0331
## KKL Plantings -0.0841 0.0378 Inf -2.226 0.0331
##
## P value adjustment: fdr method for 3 testsAll trends are significantly different from zero.
Test for pairwise differences in average abundance among levels of land use, apply FDR correction for multiple comparisons.
## contrast year_ct estimate SE df z.ratio p.value
## Loess - Bedouin Agriculture 4.21 -0.523 0.228 Inf -2.292 0.0657
## Loess - KKL Plantings 4.21 -0.291 0.152 Inf -1.907 0.0849
## Bedouin Agriculture - KKL Plantings 4.21 0.233 0.188 Inf 1.238 0.2155
##
## Results are given on the log (not the response) scale.
## P value adjustment: fdr method for 3 testsNo significant difference in average abundance among the three land uses - Loess (10.3047081), Bedouin agriculture (17.3922753) and KKL Plantings (13.7794718).
All trends are significantly different from zero (P=0.033 for all three). The rates are as follows: KKL plantings decreases 8.0635856% per year; Loess and Bedouin agriculture increase 7.939393% and 12.1383509% per year, respectively.
community analysis using package MVabund
Explore single species observations, including mean-variance plot. There is a strong mean-var relationship, indicating that employing GLMs is the proper way to analyze, rather than OLS (assumption of homogeneity is violated).
## Overlapping points were shifted along the y-axis to make them visible.##
## PIPING TO 2nd MVFACTOR## Only the variables Galerida.cristata, Passer.domesticus, Columba.livia, Streptopelia.decaocto, Prinia.gracilis, Lanius.excubitor, Corvus.cornix, Burhinus.oedicnemus, Chloris.chloris, Spilopelia.senegalensis, Acridotheres.tristis, Falco.tinnunculus were included in the plot
## (the variables with highest total abundance).
## [1] "abundance observations, aggregated into plots and species (i.e., several observations from the same species in the same plot are aggregated):"
## [1] "these are the actual observations, before aggregation into plots:"
## [1] "zoom in on high abundance observations:"
start model specification:
## nb po
## 227.5317 318.7130## [1] "POISSON"
## [1] "NEGATIVE BINOMIAL"
negative binomial model is better than poisson according to residuals and AIC comparison.
## nb po nb1
## 227.5317 318.7130 227.6228The addition of the explanatory variable ‘site’ is not improving the AIC of the model. stepwise selection of model:
## Single term deletions
##
## Model:
## spp_no_rare ~ land_use * year_ct + cos_td_rad + sin_td_rad
## Df AIC
## <none> 3868.0
## cos_td_rad 17 3913.9
## sin_td_rad 17 3871.3
## land_use:year_ct 34 3892.2close call for sine. when included in the final model comes out borderline, P=0.05. remove.
## Single term deletions
##
## Model:
## spp_no_rare ~ land_use * year_ct + cos_td_rad
## Df AIC
## <none> 3871.3
## cos_td_rad 17 3897.0
## land_use:year_ct 34 3891.6final model includes land use * year, sampling time of year.
##
## Test statistics:
## wald value Pr(>wald)
## (Intercept) 11.318 0.001 ***
## land_useBedouin Agriculture 5.697 0.001 ***
## land_useKKL Plantings 8.128 0.001 ***
## year_ct 6.616 0.001 ***
## cos_td_rad 7.148 0.001 ***
## land_useBedouin Agriculture:year_ct 3.231 0.365
## land_useKKL Plantings:year_ct 6.670 0.001 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Test statistic: 16.33, p-value: 0.001
## Arguments:
## Test statistics calculated assuming response assumed to be uncorrelated
## P-value calculated using 999 resampling iterations via pit.trap resampling (to account for correlation in testing).## Analysis of Deviance Table
##
## Model: spp_no_rare ~ land_use * year_ct + cos_td_rad
##
## Multivariate test:
## Res.Df Df.diff Dev Pr(>Dev)
## (Intercept) 139
## land_use 137 2 246.61 0.01 **
## year_ct 136 1 48.13 0.01 **
## cos_td_rad 135 1 47.55 0.01 **
## land_use:year_ct 133 2 88.35 0.01 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Univariate Tests:
## Acridotheres.tristis Burhinus.oedicnemus
## Dev Pr(>Dev) Dev Pr(>Dev)
## (Intercept)
## land_use 5.752 0.33 6.596 0.23
## year_ct 12.957 0.01 0.219 1.00
## cos_td_rad 0 1.00 15.536 0.02
## land_use:year_ct 2.76 0.90 14.101 0.03
## Chloris.chloris Columba.livia Corvus.cornix
## Dev Pr(>Dev) Dev Pr(>Dev) Dev
## (Intercept)
## land_use 4.174 0.44 13.207 0.03 5.238
## year_ct 0.414 1.00 0.354 1.00 0.331
## cos_td_rad 0.219 1.00 0.078 1.00 0.113
## land_use:year_ct 2.824 0.90 15.761 0.02 1.046
## Falco.tinnunculus Galerida.cristata
## Pr(>Dev) Dev Pr(>Dev) Dev Pr(>Dev)
## (Intercept)
## land_use 0.33 1.984 0.72 12.595 0.03
## year_ct 1.00 3.545 0.69 2.399 0.87
## cos_td_rad 1.00 3.665 0.60 4.986 0.39
## land_use:year_ct 0.97 0.695 0.97 3.698 0.76
## Iduna.pallida Lanius.excubitor
## Dev Pr(>Dev) Dev Pr(>Dev)
## (Intercept)
## land_use 27.694 0.01 34.644 0.01
## year_ct 0.014 1.00 0.015 1.00
## cos_td_rad 1.292 0.98 0.283 1.00
## land_use:year_ct 0 0.97 3.911 0.71
## Passer.domesticus Prinia.gracilis
## Dev Pr(>Dev) Dev Pr(>Dev)
## (Intercept)
## land_use 29.549 0.01 1.698 0.72
## year_ct 2.472 0.87 1.002 0.99
## cos_td_rad 3.581 0.62 0.35 1.00
## land_use:year_ct 17.406 0.02 4.83 0.62
## Pycnonotus.xanthopygos Spilopelia.senegalensis
## Dev Pr(>Dev) Dev
## (Intercept)
## land_use 13.186 0.03 20.893
## year_ct 0.091 1.00 0.113
## cos_td_rad 0.619 1.00 3.265
## land_use:year_ct 7.731 0.26 0.214
## Streptopelia.decaocto Streptopelia.turtur
## Pr(>Dev) Dev Pr(>Dev) Dev
## (Intercept)
## land_use 0.01 40.218 0.01 0.511
## year_ct 1.00 13.932 0.01 6.625
## cos_td_rad 0.69 0.583 1.00 5.012
## land_use:year_ct 0.97 2.149 0.90 5.806
## Upupa.epops Vanellus.spinosus
## Pr(>Dev) Dev Pr(>Dev) Dev Pr(>Dev)
## (Intercept)
## land_use 0.84 10.642 0.03 18.028 0.01
## year_ct 0.17 1.411 0.97 2.235 0.87
## cos_td_rad 0.39 0.279 1.00 7.688 0.18
## land_use:year_ct 0.54 1.122 0.96 4.293 0.68
## Arguments:
## Test statistics calculated assuming uncorrelated response (for faster computation)
## P-value calculated using 99 iterations via PIT-trap resampling.All factors (land_use, year, land_use:year, time of year) have a statistically significant effect on community composition.
The interaction land use * year is significantly different from Loess only for KKL plantings, not for Bedouin agriculture. In addition, this term is only significant for 3 species: stone curlew, rock pigeon and house sparrow. Therefore, plot species - level model for these 3 species which includes the interaction, and re-run manyglm without interaction to simplify interpretation.
## Resampling begins for test 1.
## Resampling run 0 finished. Time elapsed: 0.00 minutes...
## Resampling begins for test 2.
## Resampling run 0 finished. Time elapsed: 0.00 minutes...
## Resampling begins for test 3.
## Resampling run 0 finished. Time elapsed: 0.00 minutes...
## Time elapsed: 0 hr 0 min 9 sec##
## Test statistics:
## wald value Pr(>wald)
## (Intercept) 11.726 0.001 ***
## land_useBedouin Agriculture 9.586 0.001 ***
## land_useKKL Plantings 10.209 0.001 ***
## year_ct 7.001 0.001 ***
## cos_td_rad 6.012 0.024 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Test statistic: 15.03, p-value: 0.001
## Arguments:
## Test statistics calculated assuming response assumed to be uncorrelated
## P-value calculated using 999 resampling iterations via pit.trap resampling (to account for correlation in testing).## Analysis of Deviance Table
##
## Model: spp_no_rare ~ land_use + year_ct + cos_td_rad
##
## Multivariate test:
## Res.Df Df.diff Dev Pr(>Dev)
## (Intercept) 139
## land_use 137 2 246.61 0.01 **
## year_ct 136 1 48.13 0.01 **
## cos_td_rad 135 1 47.55 0.01 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Univariate Tests:
## Acridotheres.tristis Burhinus.oedicnemus
## Dev Pr(>Dev) Dev Pr(>Dev)
## (Intercept)
## land_use 5.752 0.32 6.596 0.22
## year_ct 12.957 0.01 0.219 1.00
## cos_td_rad 0 1.00 15.536 0.01
## Chloris.chloris Columba.livia Corvus.cornix
## Dev Pr(>Dev) Dev Pr(>Dev) Dev
## (Intercept)
## land_use 4.174 0.40 13.207 0.03 5.238
## year_ct 0.414 0.99 0.354 1.00 0.331
## cos_td_rad 0.219 1.00 0.078 1.00 0.113
## Falco.tinnunculus Galerida.cristata
## Pr(>Dev) Dev Pr(>Dev) Dev Pr(>Dev)
## (Intercept)
## land_use 0.33 1.984 0.70 12.595 0.03
## year_ct 1.00 3.545 0.63 2.399 0.83
## cos_td_rad 1.00 3.665 0.76 4.986 0.50
## Iduna.pallida Lanius.excubitor Passer.domesticus
## Dev Pr(>Dev) Dev Pr(>Dev) Dev
## (Intercept)
## land_use 27.694 0.01 34.644 0.01 29.549
## year_ct 0.014 1.00 0.015 1.00 2.472
## cos_td_rad 1.292 0.98 0.283 1.00 3.581
## Prinia.gracilis Pycnonotus.xanthopygos
## Pr(>Dev) Dev Pr(>Dev) Dev Pr(>Dev)
## (Intercept)
## land_use 0.01 1.698 0.70 13.186 0.03
## year_ct 0.83 1.002 0.98 0.091 1.00
## cos_td_rad 0.76 0.35 1.00 0.619 1.00
## Spilopelia.senegalensis Streptopelia.decaocto
## Dev Pr(>Dev) Dev Pr(>Dev)
## (Intercept)
## land_use 20.893 0.01 40.218 0.01
## year_ct 0.113 1.00 13.932 0.01
## cos_td_rad 3.265 0.76 0.583 1.00
## Streptopelia.turtur Upupa.epops Vanellus.spinosus
## Dev Pr(>Dev) Dev Pr(>Dev) Dev
## (Intercept)
## land_use 0.511 0.79 10.642 0.03 18.028
## year_ct 6.625 0.18 1.411 0.94 2.235
## cos_td_rad 5.012 0.49 0.279 1.00 7.688
##
## Pr(>Dev)
## (Intercept)
## land_use 0.01
## year_ct 0.83
## cos_td_rad 0.16
## Arguments:
## Test statistics calculated assuming uncorrelated response (for faster computation)
## P-value calculated using 99 iterations via PIT-trap resampling.## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## [[1]]
##
## [[2]]
##
## [[3]]
## [[1]]
##
## [[2]]
Significant negative temporal effect on house sparrow and positive effect on common myna. Significant effect land use: most species do not prefer natural loess over the other two habitats. Nonetheless, batha specialist species are not detected in our survey: is it possible they have disappeared?
check general trend in species that were filtered due to rareness in dataset.
Of the 24 species that did not make the rare species cutoff, 9 (38%) appeared only in the natural loess vs. only 3 (12%) in KKL plantings and 2 (8%) in the Bedouin agriculture. Of these 9 species, 9 are defined as batha specialists, vs. 1 and 0 in Bedouin agriculture, respectively. Moreover, of the 9 species unique to the natural loess, 7 are endangered vs. 0 in KKL plantings and 0 in Bedouin agriculture, respectively.
