library(ordinal)
## Warning: package 'ordinal' was built under R version 4.1.3
library(MASS)
## Warning: package 'MASS' was built under R version 4.1.3
library(brant)
## Warning: package 'brant' was built under R version 4.1.3
library(AER)
## Warning: package 'AER' was built under R version 4.1.3
## Loading required package: car
## Warning: package 'car' was built under R version 4.1.3
## Loading required package: carData
## Loading required package: lmtest
## Warning: package 'lmtest' was built under R version 4.1.3
## Loading required package: zoo
## Warning: package 'zoo' was built under R version 4.1.3
## 
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric
## Loading required package: sandwich
## Warning: package 'sandwich' was built under R version 4.1.3
## Loading required package: survival
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.1.3
library(aod)
## Warning: package 'aod' was built under R version 4.1.3
## 
## Attaching package: 'aod'
## The following object is masked from 'package:survival':
## 
##     rats
library(gt)
## Warning: package 'gt' was built under R version 4.1.3
library(jmv)
## Warning: package 'jmv' was built under R version 4.1.3
library(rcompanion)
## Warning: package 'rcompanion' was built under R version 4.1.3
library(apaTables)
## Warning: package 'apaTables' was built under R version 4.1.3
library(apaText)
## Warning: package 'apaText' was built under R version 4.1.3
library(readr)
## Warning: package 'readr' was built under R version 4.1.3

Read in Mosquito data

Msqt <- read_csv("BCH_MSQT_7_27_22.csv", col_types = cols(BCH_ID = col_factor(levels = c("1", 
    "2", "21", "33", "51", "53", "59", "66", 
    "68", "77", "88", "91", "188", "246", 
    "267", "270", "313", "329", "360", "371", 
    "429", "456", "493", "565", "571", "587", 
    "596", "651", "671", "872", "909", "932", 
    "937", "949", "955", "968", "971", "972", 
    "985", "1017", "1092", "1190", "1204")), 
    Jul_Date = col_number(), Dt_2020 = col_number(), 
    Dt_2021 = col_number(), CmbCrt = col_factor(levels = c("none", 
        "silv", "gopl")), none = col_number(), 
    silv = col_number(), pc1 = col_factor(levels = c("exurban", 
        "suburban", "urban")), Exurban = col_number(), 
    Suburban = col_number(), Ae_albopictus = col_number(), 
    Cx_childesteri = col_number(), Cx_erraticus = col_number(), 
    Cx_pipiens = col_number(), Cx_po = col_number(), 
    Oc._c_canadensis = col_number(), `Oc_c_ mathesoni` = col_number(), 
    Oc_increpitus = col_number(), Oc_zoosophus = col_number(), 
    Tx_r_rutilus = col_number(), Ae_japanicus = col_number(), 
    Oc_sollicitans = col_number(), Cx_restuans = col_number(), 
    Abun = col_number()))
View(Msqt)

Read in Mosquito data with “none” level certified home removed

Msqt_NoNo <- read_csv("Msqt_NoNo.csv", col_types = cols(BCH_ID = col_factor(levels = c("1", 
    "2", "21", "33", "51", "53", "59", "66", 
    "68", "77", "88", "91", "188", "246", 
    "267", "270", "313", "329", "360", "371", 
    "429", "456", "493", "565", "571", "587", 
    "596", "651", "671", "872", "909", "932", 
    "937", "949", "955", "968", "971", "972", 
    "985", "1017", "1092", "1190", "1204")), 
    Jul_Date = col_number(), Dt_2020 = col_number(), 
    Dt_2021 = col_number(), CmbCrt = col_factor(levels = c("none", 
        "silv", "gopl")), none = col_number(), 
    silv = col_number(), pc1 = col_factor(levels = c("exurban", 
        "suburban", "urban")), Exurban = col_number(), 
    Suburban = col_number(), Ae_albopictus = col_number(), 
    Cx_childesteri = col_number(), Cx_erraticus = col_number(), 
    Cx_pipiens = col_number(), Cx_po = col_number(), 
    Oc._c_canadensis = col_number(), `Oc_c_ mathesoni` = col_number(), 
    Oc_increpitus = col_number(), Oc_zoosophus = col_number(), 
    Tx_r_rutilus = col_number(), Ae_japanicus = col_number(), 
    Oc_sollicitans = col_number(), Cx_restuans = col_number(), 
    Abun = col_number()))
View(Msqt_NoNo)

Ordinal Logistic Regression

## BCH Cert Level OLM
## SR

polrSR <- polr(formula = CmbCrt~EstSR+Jul_Date+Dt_2020+pc1+Abun,data = Msqt, Hess = TRUE)

brant(polrSR)
## -------------------------------------------- 
## Test for X2  df  probability 
## -------------------------------------------- 
## Omnibus      3.29    6   0.77
## EstSR        0.06    1   0.8
## Jul_Date 0.01    1   0.91
## Dt_2020      0   1   0.95
## pc1suburban  0.35    1   0.56
## pc1urban 0.01    1   0.91
## Abun     2.71    1   0.1
## -------------------------------------------- 
## 
## H0: Parallel Regression Assumption holds
summary(polrSR)
## Warning in sqrt(diag(vc)): NaNs produced
## Call:
## polr(formula = CmbCrt ~ EstSR + Jul_Date + Dt_2020 + pc1 + Abun, 
##     data = Msqt, Hess = TRUE)
## 
## Coefficients:
##                Value Std. Error  t value
## EstSR       0.241689   0.039425   6.1303
## Jul_Date    0.003392        NaN      NaN
## Dt_2020     3.336195   0.011371 293.3841
## pc1suburban 0.001364   0.009169   0.1488
## pc1urban    0.008458   0.006999   1.2084
## Abun        0.005061   0.004185   1.2092
## 
## Intercepts:
##           Value     Std. Error t value  
## none|silv   71.7957    0.0227  3159.5168
## silv|gopl   73.2305    0.1528   479.3456
## 
## Residual Deviance: 353.7708 
## AIC: 369.7708
coeftest(polrSR)
## Warning in sqrt(diag(vc)): NaNs produced
## 
## z test of coefficients:
## 
##               Estimate Std. Error   z value  Pr(>|z|)    
## EstSR        0.2416895  0.0394253    6.1303  8.77e-10 ***
## Jul_Date     0.0033923        NaN       NaN       NaN    
## Dt_2020      3.3361951  0.0113714  293.3841 < 2.2e-16 ***
## pc1suburban  0.0013642  0.0091686    0.1488    0.8817    
## pc1urban     0.0084582  0.0069995    1.2084    0.2269    
## Abun         0.0050606  0.0041852    1.2092    0.2266    
## none|silv   71.7956835  0.0227236 3159.5168 < 2.2e-16 ***
## silv|gopl   73.2304743  0.1527718  479.3456 < 2.2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
exp(coeftest(polrSR))
## Warning in sqrt(diag(vc)): NaNs produced
## 
## z test of coefficients:
## 
##               Estimate Std. Error     z value Pr(>|z|)
## EstSR       1.2734e+00 1.0402e+00  4.5958e+02    1.000
## Jul_Date    1.0034e+00        NaN         NaN      NaN
## Dt_2020     2.8112e+01 1.0114e+00 2.6008e+127    1.000
## pc1suburban 1.0014e+00 1.0092e+00  1.1604e+00    2.415
## pc1urban    1.0085e+00 1.0070e+00  3.3481e+00    1.255
## Abun        1.0051e+00 1.0042e+00  3.3507e+00    1.254
## none|silv   1.5152e+31 1.0230e+00         Inf    1.000
## silv|gopl   6.3620e+31 1.1651e+00 1.5036e+208    1.000
## Shan H

polrSh <- polr(formula = CmbCrt~EstShan+Jul_Date+Dt_2020+pc1+Abun,data = Msqt, Hess = TRUE)

brant(polrSh)
## -------------------------------------------- 
## Test for X2  df  probability 
## -------------------------------------------- 
## Omnibus      3.3 6   0.77
## EstShan      0.01    1   0.93
## Jul_Date 0.01    1   0.92
## Dt_2020      0   1   0.97
## pc1suburban  0.38    1   0.54
## pc1urban 0.02    1   0.89
## Abun     2.59    1   0.11
## -------------------------------------------- 
## 
## H0: Parallel Regression Assumption holds
summary(polrSh)
## Warning in sqrt(diag(vc)): NaNs produced
## Call:
## polr(formula = CmbCrt ~ EstShan + Jul_Date + Dt_2020 + pc1 + 
##     Abun, data = Msqt, Hess = TRUE)
## 
## Coefficients:
##                 Value Std. Error t value
## EstShan      0.487319   0.039406  12.367
## Jul_Date     0.002745        NaN     NaN
## Dt_2020      2.595959   0.014742 176.092
## pc1suburban -0.082131   0.012736  -6.448
## pc1urban     0.015350   0.010657   1.440
## Abun         0.005481   0.004085   1.342
## 
## Intercepts:
##           Value     Std. Error t value  
## none|silv   58.1943    0.0319  1824.8491
## silv|gopl   59.6515    0.1486   401.5051
## 
## Residual Deviance: 350.4478 
## AIC: 366.4478
coeftest(polrSh)
## Warning in sqrt(diag(vc)): NaNs produced
## 
## z test of coefficients:
## 
##               Estimate Std. Error   z value  Pr(>|z|)    
## EstShan      0.4873187  0.0394056   12.3668 < 2.2e-16 ***
## Jul_Date     0.0027449        NaN       NaN       NaN    
## Dt_2020      2.5959589  0.0147421  176.0921 < 2.2e-16 ***
## pc1suburban -0.0821311  0.0127365   -6.4485  1.13e-10 ***
## pc1urban     0.0153500  0.0106572    1.4403    0.1498    
## Abun         0.0054807  0.0040854    1.3415    0.1797    
## none|silv   58.1943199  0.0318899 1824.8491 < 2.2e-16 ***
## silv|gopl   59.6514943  0.1485697  401.5051 < 2.2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
exp(coeftest(polrSh))
## Warning in sqrt(diag(vc)): NaNs produced
## 
## z test of coefficients:
## 
##               Estimate Std. Error     z value Pr(>|z|)
## EstShan     1.6280e+00 1.0402e+00  2.3486e+05    1.000
## Jul_Date    1.0028e+00        NaN         NaN      NaN
## Dt_2020     1.3409e+01 1.0149e+00  2.9911e+76    1.000
## pc1suburban 9.2115e-01 1.0128e+00  1.6000e-03    1.000
## pc1urban    1.0155e+00 1.0107e+00  4.2222e+00    1.162
## Abun        1.0055e+00 1.0041e+00  3.8249e+00    1.197
## none|silv   1.8770e+25 1.0324e+00         Inf    1.000
## silv|gopl   8.0596e+25 1.1602e+00 2.3520e+174    1.000
## Simpson

polrSi <- polr(formula = CmbCrt~EstSimp+Jul_Date+Dt_2020+pc1+Abun,data = Msqt, Hess = TRUE)

brant(polrSi)
## -------------------------------------------- 
## Test for X2  df  probability 
## -------------------------------------------- 
## Omnibus      3.5 6   0.74
## EstSimp      0.31    1   0.57
## Jul_Date 0.03    1   0.87
## Dt_2020      0.01    1   0.91
## pc1suburban  0.45    1   0.5
## pc1urban 0.02    1   0.9
## Abun     2.67    1   0.1
## -------------------------------------------- 
## 
## H0: Parallel Regression Assumption holds
summary(polrSi)
## Warning in sqrt(diag(vc)): NaNs produced
## Call:
## polr(formula = CmbCrt ~ EstSimp + Jul_Date + Dt_2020 + pc1 + 
##     Abun, data = Msqt, Hess = TRUE)
## 
## Coefficients:
##                 Value Std. Error t value
## EstSimp      0.694222   0.037332  18.596
## Jul_Date     0.002950        NaN     NaN
## Dt_2020      2.733747   0.016492 165.758
## pc1suburban -0.077035   0.013729  -5.611
## pc1urban     0.014285   0.013041   1.095
## Abun         0.005106   0.004138   1.234
## 
## Intercepts:
##           Value     Std. Error t value  
## none|silv   62.6710    0.0365  1714.9343
## silv|gopl   64.1364    0.1455   440.8219
## 
## Residual Deviance: 349.1876 
## AIC: 365.1876
coeftest(polrSi)
## Warning in sqrt(diag(vc)): NaNs produced
## 
## z test of coefficients:
## 
##               Estimate Std. Error   z value  Pr(>|z|)    
## EstSimp      0.6942224  0.0373315   18.5961 < 2.2e-16 ***
## Jul_Date     0.0029499        NaN       NaN       NaN    
## Dt_2020      2.7337468  0.0164924  165.7579 < 2.2e-16 ***
## pc1suburban -0.0770352  0.0137285   -5.6113 2.008e-08 ***
## pc1urban     0.0142848  0.0130415    1.0953    0.2734    
## Abun         0.0051058  0.0041383    1.2338    0.2173    
## none|silv   62.6709896  0.0365443 1714.9343 < 2.2e-16 ***
## silv|gopl   64.1364361  0.1454929  440.8219 < 2.2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
exp(coeftest(polrSi))
## Warning in sqrt(diag(vc)): NaNs produced
## 
## z test of coefficients:
## 
##               Estimate Std. Error     z value Pr(>|z|)
## EstSimp     2.0021e+00 1.0380e+00  1.1918e+08    1.000
## Jul_Date    1.0030e+00        NaN         NaN      NaN
## Dt_2020     1.5390e+01 1.0166e+00  9.7221e+71    1.000
## pc1suburban 9.2586e-01 1.0138e+00  3.7000e-03    1.000
## pc1urban    1.0144e+00 1.0131e+00  2.9902e+00    1.314
## Abun        1.0051e+00 1.0042e+00  3.4343e+00    1.243
## none|silv   1.6507e+27 1.0372e+00         Inf    1.000
## silv|gopl   7.1466e+27 1.1566e+00 2.7958e+191    1.000

Abunudance glm

## SR
glmSR.ab <- glm(formula = Abun~EstSR+Jul_Date+Dt_2020+none+silv+Exurban+Suburban,family = gaussian, data = Msqt)

summary(glmSR.ab)
## 
## Call:
## glm(formula = Abun ~ EstSR + Jul_Date + Dt_2020 + none + silv + 
##     Exurban + Suburban, family = gaussian, data = Msqt)
## 
## Deviance Residuals: 
##     Min       1Q   Median       3Q      Max  
## -53.198  -18.112   -5.018    8.304  150.583  
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)   
## (Intercept) 2697.3033  2171.6121   1.242  0.21609   
## EstSR         10.0579     3.6910   2.725  0.00717 **
## Jul_Date      -0.1270     0.1024  -1.240  0.21675   
## Dt_2020      -99.8743   105.5770  -0.946  0.34563   
## none          -6.6855     6.0541  -1.104  0.27118   
## silv           4.7702     6.0494   0.789  0.43159   
## Exurban      -12.0391     6.0696  -1.984  0.04908 * 
## Suburban      -8.1002     5.9080  -1.371  0.17234   
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for gaussian family taken to be 971.2978)
## 
##     Null deviance: 221705  on 162  degrees of freedom
## Residual deviance: 150551  on 155  degrees of freedom
## AIC: 1593.6
## 
## Number of Fisher Scoring iterations: 2
exp(coeftest(glmSR.ab))
## 
## z test of coefficients:
## 
##               Estimate Std. Error z value Pr(>|z|)
## (Intercept)        Inf        Inf  3.4628    1.239
## EstSR       2.3339e+04 4.0086e+01 15.2557    1.006
## Jul_Date    8.8076e-01 1.1078e+00  0.2893    1.240
## Dt_2020     4.2182e-44 7.1041e+45  0.3883    1.411
## none        1.2489e-03 4.2587e+02  0.3314    1.309
## silv        1.1794e+02 4.2387e+02  2.2002    1.538
## Exurban     5.9084e-06 4.3252e+02  0.1376    1.048
## Suburban    3.0347e-04 3.6795e+02  0.2538    1.186
exp(confint(glmSR.ab))
## Waiting for profiling to be done...
##                     2.5 %       97.5 %
## (Intercept)  0.000000e+00          Inf
## EstSR        1.683743e+01 3.235228e+07
## Jul_Date     7.206341e-01 1.076462e+00
## Dt_2020     5.725687e-134 3.107649e+46
## none         8.774907e-09 1.777598e+02
## silv         8.363247e-04 1.663191e+07
## Exurban      4.027087e-11 8.668490e-01
## Suburban     2.839605e-09 3.243253e+01
## Shannon H

glmSh.ab <- glm(formula = Abun~EstShan+Jul_Date+Dt_2020+none+silv+Exurban+Suburban,family = gaussian, data = Msqt)

summary(glmSh.ab)
## 
## Call:
## glm(formula = Abun ~ EstShan + Jul_Date + Dt_2020 + none + silv + 
##     Exurban + Suburban, family = gaussian, data = Msqt)
## 
## Deviance Residuals: 
##     Min       1Q   Median       3Q      Max  
## -50.938  -17.140   -5.767    7.819  166.313  
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)  
## (Intercept) 1696.15308 2184.92654   0.776   0.4388  
## EstShan        4.15146    4.05232   1.024   0.3072  
## Jul_Date      -0.07944    0.10299  -0.771   0.4417  
## Dt_2020      -45.90042  105.90497  -0.433   0.6653  
## none          -7.21260    6.23748  -1.156   0.2493  
## silv           4.53013    6.19221   0.732   0.4655  
## Exurban      -11.08365    6.18085  -1.793   0.0749 .
## Suburban      -6.38407    6.07157  -1.051   0.2947  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for gaussian family taken to be 1010.983)
## 
##     Null deviance: 221705  on 162  degrees of freedom
## Residual deviance: 156702  on 155  degrees of freedom
## AIC: 1600.1
## 
## Number of Fisher Scoring iterations: 2
exp(coeftest(glmSh.ab))
## 
## z test of coefficients:
## 
##               Estimate Std. Error z value Pr(>|z|)
## (Intercept)        Inf        Inf  2.1734    1.549
## EstShan     6.3527e+01 5.7531e+01  2.7856    1.357
## Jul_Date    9.2364e-01 1.1085e+00  0.4624    1.553
## Dt_2020     1.1633e-20 9.8616e+45  0.6483    1.944
## none        7.3723e-04 5.1157e+02  0.3146    1.281
## silv        9.2771e+01 4.8893e+02  2.0784    1.591
## Exurban     1.5361e-05 4.8340e+02  0.1664    1.076
## Suburban    1.6882e-03 4.3336e+02  0.3494    1.341
exp(confint(glmSh.ab))
## Waiting for profiling to be done...
##                     2.5 %       97.5 %
## (Intercept)  0.000000e+00          Inf
## EstShan      2.257421e-02 1.787731e+05
## Jul_Date     7.548123e-01 1.130218e+00
## Dt_2020     8.302795e-111 1.629966e+70
## none         3.616232e-09 1.502985e+02
## silv         4.972693e-04 1.730732e+07
## Exurban      8.419528e-11 2.802710e+00
## Suburban     1.146319e-08 2.486349e+02
glmSi.ab <- glm(formula = Abun~EstSimp+Jul_Date+Dt_2020+none+silv+Exurban+Suburban,family = gaussian, data = Msqt)

summary(glmSi.ab)
## 
## Call:
## glm(formula = Abun ~ EstSimp + Jul_Date + Dt_2020 + none + silv + 
##     Exurban + Suburban, family = gaussian, data = Msqt)
## 
## Deviance Residuals: 
##     Min       1Q   Median       3Q      Max  
## -51.561  -17.044   -5.021    9.371  165.169  
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)  
## (Intercept) 1776.62194 2172.94196   0.818   0.4148  
## EstSimp        6.90235    4.93682   1.398   0.1641  
## Jul_Date      -0.08334    0.10242  -0.814   0.4171  
## Dt_2020      -51.13534  105.34752  -0.485   0.6281  
## none          -6.64003    6.24279  -1.064   0.2891  
## silv           5.02037    6.19589   0.810   0.4190  
## Exurban      -10.99681    6.15905  -1.785   0.0761 .
## Suburban      -6.63509    6.01450  -1.103   0.2717  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for gaussian family taken to be 1005.152)
## 
##     Null deviance: 221705  on 162  degrees of freedom
## Residual deviance: 155799  on 155  degrees of freedom
## AIC: 1599.2
## 
## Number of Fisher Scoring iterations: 2
exp(coeftest(glmSi.ab))
## 
## z test of coefficients:
## 
##               Estimate Std. Error z value Pr(>|z|)
## (Intercept)        Inf        Inf  2.2651    1.512
## EstSimp     9.9461e+02 1.3933e+02  4.0476    1.176
## Jul_Date    9.2004e-01 1.1079e+00  0.4432    1.516
## Dt_2020     6.1973e-23 5.6474e+45  0.6155    1.873
## none        1.3070e-03 5.1429e+02  0.3452    1.333
## silv        1.5147e+02 4.9073e+02  2.2485    1.519
## Exurban     1.6755e-05 4.7298e+02  0.1677    1.077
## Suburban    1.3135e-03 4.0932e+02  0.3318    1.310
exp(confint(glmSi.ab))
## Waiting for profiling to be done...
##                     2.5 %       97.5 %
## (Intercept)  0.000000e+00          Inf
## EstSimp      6.243388e-02 1.584477e+07
## Jul_Date     7.527059e-01 1.124578e+00
## Dt_2020     1.318969e-112 2.911900e+67
## none         6.344551e-09 2.692397e+02
## silv         8.060541e-04 2.846256e+07
## Exurban      9.584103e-11 2.929144e+00
## Suburban     9.973844e-09 1.729707e+02

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.

Density graph of iNext estimates of Species Richness for the ’20 & ’21 season, grouped by BCH certification Level

Msqt.DenPlt <- ggplot(Msqt,aes(EstSR))
Msqt.DenPlt+geom_density(aes(fill=factor(CmbCrt)), alpha=0.8) +
  labs(title="Density plot", 
       subtitle="iNext estimates of Species Richness grouped by BCH certification Level",
       caption="Source: iNEXT",
       x="Species Richness",
       fill="certification Level")

Msqt_NN.DenPlt <- ggplot(Msqt_NoNo,aes(EstSR))
Msqt_NN.DenPlt+geom_density(aes(fill=factor(CmbCrt)), alpha=0.8)+
  labs(title="Density plot",
       subtitle="iNext estimates of Species Richness grouped by BCH certification Level with none certificated removed ",
       caption="Source: iNEXT",
       x="Species Richness",
       fill="certification Level")

Density graph of iNext estimates of Species Abundance for the ’20 & ’21 season, grouped by Species Abundance

Msqt.DenPlt <- ggplot(Msqt,aes(Abun))
Msqt.DenPlt+geom_density(aes(fill=factor(CmbCrt)), alpha=0.8) +
  labs(title="Density plot", 
       subtitle="iNext estimates of Species Abundance by BCH certification Level",
       caption="Source: iNEXT",
       x="Species Abundance",
       fill="certification Level")

Msqt_NN.DenPlt <- ggplot(Msqt_NoNo,aes(Abun))
Msqt_NN.DenPlt+geom_density(aes(fill=factor(CmbCrt)), alpha=0.8)+
  labs(title="Density plot",
       subtitle="iNext estimates of Species Abundance by BCH certification Level, with none certificated removed ",
       caption="Source: iNEXT",
       x="Species Abundance",
       fill="certification Level")