Diagrama de ven, cae dentro los RDA

source("forward.r")

getwd()
## [1] "C:/Users/Claudia Gomez/OneDrive - Universidad Nacional de Costa Rica/ecocuantitativa/claudia_gomez"
library(ade4)
library(vegan)
## Loading required package: permute
## Loading required package: lattice
## This is vegan 2.6-4
library(readxl)
biologica <- read_xlsx("./bases_datos/EVALUACION_04.xlsx",
                  sheet = 1,
                  col_names = TRUE)
ambiental <- read_xlsx("./bases_datos/EVALUACION_04.xlsx",
                 sheet = 2,
                 col_names = TRUE)


str(biologica)
## tibble [14 × 44] (S3: tbl_df/tbl/data.frame)
##  $ Sp01: num [1:14] 0 0 4 1 0 0 0 0 0 0 ...
##  $ Sp02: num [1:14] 0 0 0 0 0 2 48 0 0 2 ...
##  $ Sp03: num [1:14] 0 2 2 3 0 0 2 3 16 6 ...
##  $ Sp04: num [1:14] 129 122 143 73 208 12 195 282 27 0 ...
##  $ Sp05: num [1:14] 0 0 0 0 5 0 0 0 0 1 ...
##  $ Sp06: num [1:14] 0 2 2 4 0 0 0 0 0 2 ...
##  $ Sp07: num [1:14] 0 0 0 0 0 0 0 2 0 0 ...
##  $ Sp08: num [1:14] 27 9 11 14 8 0 21 10 23 16 ...
##  $ Sp09: num [1:14] 0 0 0 0 0 0 0 2 0 0 ...
##  $ Sp10: num [1:14] 0 0 0 0 0 0 0 0 0 0 ...
##  $ Sp11: num [1:14] 0 0 0 0 0 0 0 0 0 0 ...
##  $ Sp12: num [1:14] 5 10 6 21 9 0 38 3 0 7 ...
##  $ Sp13: num [1:14] 2 0 0 0 0 0 0 0 0 0 ...
##  $ Sp14: num [1:14] 0 0 0 0 0 0 0 0 0 0 ...
##  $ Sp15: num [1:14] 0 0 0 0 1 0 0 0 0 0 ...
##  $ Sp16: num [1:14] 0 1 3 0 0 0 1 0 0 0 ...
##  $ Sp17: num [1:14] 2 97 172 2 3 1 6 5 1 13 ...
##  $ Sp18: num [1:14] 0 7 0 1 1 0 0 8 1 2 ...
##  $ Sp19: num [1:14] 0 6 0 0 1 0 1 0 0 7 ...
##  $ Sp20: num [1:14] 0 0 0 0 1 0 0 0 0 0 ...
##  $ Sp21: num [1:14] 0 0 0 0 0 0 1 0 0 0 ...
##  $ Sp22: num [1:14] 0 7 0 1 3 0 2 3 0 2 ...
##  $ Sp23: num [1:14] 24 1 87 29 24 9 1 6 14 13 ...
##  $ Sp24: num [1:14] 8 0 0 0 1 0 14 2 0 0 ...
##  $ Sp25: num [1:14] 33 43 10 107 0 29 20 26 11 0 ...
##  $ Sp26: num [1:14] 0 0 0 7 0 0 0 0 0 0 ...
##  $ Sp27: num [1:14] 0 1 1 0 0 0 3 6 0 0 ...
##  $ Sp28: num [1:14] 0 0 1 0 0 0 0 0 0 0 ...
##  $ Sp29: num [1:14] 0 0 0 0 2 0 0 0 0 0 ...
##  $ Sp30: num [1:14] 0 0 0 0 0 0 7 0 0 0 ...
##  $ Sp31: num [1:14] 0 2 0 0 4 0 0 0 0 0 ...
##  $ Sp32: num [1:14] 0 0 0 0 0 0 0 0 0 0 ...
##  $ Sp33: num [1:14] 0 12 12 1 12 1 3 0 0 2 ...
##  $ Sp34: num [1:14] 0 0 0 0 0 0 2 0 0 0 ...
##  $ Sp35: num [1:14] 7 0 35 0 17 0 0 2 3 1 ...
##  $ Sp36: num [1:14] 0 0 0 0 0 0 11 0 0 2 ...
##  $ Sp37: num [1:14] 6 12 28 0 86 0 1 0 0 6 ...
##  $ Sp38: num [1:14] 0 0 0 0 0 0 0 0 0 2 ...
##  $ Sp39: num [1:14] 0 1 0 0 0 0 2 0 0 0 ...
##  $ Sp40: num [1:14] 73 279 292 67 467 1 26 437 22 405 ...
##  $ Sp41: num [1:14] 1 0 0 0 0 0 0 0 0 0 ...
##  $ Sp42: num [1:14] 0 0 0 0 0 0 0 0 0 0 ...
##  $ Sp43: num [1:14] 0 0 0 0 0 0 0 2 0 0 ...
##  $ Sp44: num [1:14] 0 0 0 0 0 0 1 0 0 0 ...
colSums(ambiental)
##  parametro01  parametro02  parametro03  parametro04  parametro05  parametro06 
## 2.621000e+02 4.979000e+01 1.127600e+02 1.384160e+03 1.628330e+03 8.596700e+02 
##  parametro07  parametro08  parametro09  parametro10  parametro11  parametro12 
## 1.103100e+02 3.611940e+03 8.530000e+01 1.664000e+03 6.215000e+02 3.788900e+02 
##  parametro13  parametro14  parametro15  parametro16  parametro17  parametro18 
## 9.208784e-01 1.600800e+00 3.572440e+01 3.779270e+01 1.017870e+02 6.298300e+01 
##  parametro19  parametro20  parametro21  parametro22  parametro23 
## 5.157100e+01 5.178100e+01 1.610600e+02 1.552440e+07 9.141400e+06
rowSums(biologica)
##  [1] 317 614 809 331 853  55 406 799 118 489 229  97 207  34
#transformación

biologica.log<- decostand(biologica[ ,-11,14,32,43], method = "log")
biologica.log
biol.bray<-vegdist(biologica.log, distance = "bray")


env.std <- decostand(ambiental[ ,-11,14,32,43], "standardize")#Seleccionamos la normalización, esto no es una regla.
spe.euc<-vegdist(env.std,method="euclidean")

dca<-decorana(biologica[ ,-11,14,32,43])
## Warning in decorana(biologica[, -11, 14, 32, 43]): some species were removed
## because they were missing in the data
summary(dca)
## 
## Call:
## decorana(veg = biologica[, -11, 14, 32, 43]) 
## 
## Detrended correspondence analysis with 26 segments.
## Rescaling of axes with 4 iterations.
## Total inertia (scaled Chi-square): NaN 
## 
##                        DCA1    DCA2    DCA3    DCA4
## Eigenvalues          0.2899 0.13570 0.11654 0.05839
## Additive Eigenvalues 0.0000 0.00000 0.00000 0.00000
## Decorana values      0.3037 0.09571 0.03354 0.01136
## Axis lengths         1.8033 1.14754 1.42240 0.82382
## Species scores:
## 
##          DCA1     DCA2     DCA3     DCA4 Totals
## Sp01  -0.1896   2.9071  -1.0479  -0.7076      5
## Sp02   2.9163  -0.4018   1.0856  -0.4445     52
## Sp03   0.8959   2.0826   3.0698   0.8618     34
## Sp04   0.8509  -0.3998  -0.2258  -0.1534   1290
## Sp05  -1.5074  -5.0183   0.7318   1.0373      7
## Sp06   0.8313   1.1596  -0.6139  -2.4319     11
## Sp07  -0.2027  -1.0557  -0.3359  -0.2763      2
## Sp08   0.9349   0.7839   1.2857   1.9044    168
## Sp09  -0.2027  -1.0557  -0.3359  -0.2763      2
## Sp10   1.0875  -0.3722   0.3968   1.3415      1
## Sp12   1.6374  -0.2562   0.7144  -0.7544    106
## Sp13   0.6655  -1.3669  -3.8768   4.8448      3
## Sp14   0.1651   0.3883   0.2243   0.0979      0
## Sp15  -1.2995  -7.5303   0.3195  -2.8839      1
## Sp16   0.4031   2.3559  -0.0312  -0.8669      5
## Sp17  -0.7682   2.3398  -0.7056  -1.3542    307
## Sp18  -0.3871   0.3658   1.0569   0.6267     22
## Sp19  -0.9314   0.5367   0.0361  -6.0089     15
## Sp20  -1.2995  -7.5303   0.3195  -2.8839      1
## Sp21   3.0601  -0.9139   1.2742  -0.0614      1
## Sp22   0.0203  -0.6039   0.8169   0.2927     20
## Sp23   0.2936   1.5268  -0.7061   0.3817    230
## Sp24   2.1784  -1.8824  -1.5080  -1.2306     25
## Sp25   1.5523   0.8934  -1.5638   0.1036    307
## Sp26   1.9976   0.4619   0.5280   0.0927      7
## Sp27   1.0186  -0.3019   0.7275   0.7200     16
## Sp28  -1.1687   3.4953  -1.2663  -0.9025      1
## Sp29  -1.2995  -7.5303   0.3195  -2.8839      2
## Sp30   3.0601  -0.9139   1.2742  -0.0614      7
## Sp31  -1.1690  -3.2026   0.8897   1.7286      7
## Sp32   0.1651   0.3883   0.2243   0.0979      0
## Sp33  -0.2952   0.7217  -0.4216  -1.1027     47
## Sp34   3.0601  -0.9139   1.2742  -0.0614      2
## Sp35  -0.8141   1.4340   0.3938   1.9388     76
## Sp36   2.4313  -0.6778   1.1377  -1.4700     14
## Sp37  -1.0495  -2.3625  -0.7747  -2.7238    139
## Sp38  -2.2326   0.3629  -1.1549 -11.1165      2
## Sp39   2.1364   0.2717   1.1492  -0.5639      3
## Sp40  -0.7548  -0.2809   0.3175   0.2678   2411
## Sp41   1.8745  -1.5107  -3.7049  -1.0195      3
## Sp42   0.1651   0.3883   0.2243   0.0979      0
## Sp43  -0.5127   0.2670   1.0969   7.0931      5
## Sp44   3.0601  -0.9139   1.2742  -0.0614      1
## 
## Site scores:
## 
##          DCA1    DCA2    DCA3    DCA4 Totals
##  [1,]  0.4841 -0.0153 -0.1989  0.1682    317
##  [2,] -0.1776  0.2093 -0.0800 -0.2229    614
##  [3,] -0.2810  0.5354 -0.1637 -0.1933    809
##  [4,]  0.7590  0.3615 -0.4247  0.0895    331
##  [5,] -0.3197 -0.4779  0.0522 -0.1324    853
##  [6,]  1.1252  0.6696 -0.9646  0.0276     55
##  [7,]  1.2130 -0.2536  0.1229 -0.2026    406
##  [8,] -0.0384 -0.2295  0.0810  0.1453    799
##  [9,]  0.5067  0.6151  0.4578  0.6010    118
## [10,] -0.5903 -0.1072  0.3165  0.0807    489
## [11,] -0.2355 -0.1682  0.1332  0.1427    229
## [12,]  0.3202  0.0597 -0.0810  0.2491     97
## [13,] -0.4578 -0.0745  0.3401  0.5772    207
## [14,]  0.7987  0.2565 -0.6703  0.0356     34
rda<-rda(biologica.log ~ .,env.std)
rda
## Call: rda(formula = biologica.log ~ parametro01 + parametro02 +
## parametro03 + parametro04 + parametro05 + parametro06 + parametro07 +
## parametro08 + parametro09 + parametro10 + parametro12 + parametro13 +
## parametro14 + parametro15 + parametro16 + parametro17 + parametro18 +
## parametro19 + parametro20 + parametro21 + parametro22 + parametro23,
## data = env.std)
## 
##               Inertia Proportion Rank
## Total           76.37       1.00     
## Constrained     76.37       1.00   13
## Unconstrained    0.00       0.00    0
## Inertia is variance 
## Some constraints or conditions were aliased because they were redundant
## 
## Eigenvalues for constrained axes:
##   RDA1   RDA2   RDA3   RDA4   RDA5   RDA6   RDA7   RDA8   RDA9  RDA10  RDA11 
## 23.432 13.745  9.655  7.492  6.476  5.286  3.284  2.225  1.854  1.185  0.723 
##  RDA12  RDA13 
##  0.573  0.439
(R2<-RsquareAdj(rda)$r.squared)
## [1] 1
(R2adj<-RsquareAdj(rda)$adj.r.squared)
## [1] NA
anova.cca(rda, step=1000)
anova.cca(rda, by="axis", step=1000)
#reconstruccion 
reconstruccion<-rda(biologica.log ~ parametro01 + parametro02 + parametro03 + parametro04 + parametro05 + parametro06 + parametro07,env.std)
reconstruccion
## Call: rda(formula = biologica.log ~ parametro01 + parametro02 +
## parametro03 + parametro04 + parametro05 + parametro06 + parametro07,
## data = env.std)
## 
##               Inertia Proportion Rank
## Total         76.3703     1.0000     
## Constrained   48.4076     0.6339    7
## Unconstrained 27.9627     0.3661    6
## Inertia is variance 
## 
## Eigenvalues for constrained axes:
##   RDA1   RDA2   RDA3   RDA4   RDA5   RDA6   RDA7 
## 17.769  9.103  7.942  5.861  3.897  2.171  1.665 
## 
## Eigenvalues for unconstrained axes:
##    PC1    PC2    PC3    PC4    PC5    PC6 
## 13.092  4.946  3.999  2.739  2.230  0.957
(R2<-RsquareAdj(reconstruccion)$r.squared)
## [1] 0.6338537
(R2adj<-RsquareAdj(reconstruccion)$adj.r.squared)
## [1] 0.2066831
anova.cca(reconstruccion, step=1000)
anova.cca(reconstruccion, by="axis", step=1000)
vif.cca(reconstruccion)
## parametro01 parametro02 parametro03 parametro04 parametro05 parametro06 
##   14.146846   13.078638  152.269808  169.127564    3.476355    1.791923 
## parametro07 
##    4.096341
#Los mejores parametros son el 05, 06 y el 07

reconstruccion2<-rda(biologica.log ~ parametro05 + parametro06 + parametro07,env.std)
reconstruccion2
## Call: rda(formula = biologica.log ~ parametro05 + parametro06 +
## parametro07, data = env.std)
## 
##               Inertia Proportion Rank
## Total         76.3703     1.0000     
## Constrained   16.7935     0.2199    3
## Unconstrained 59.5769     0.7801   10
## Inertia is variance 
## 
## Eigenvalues for constrained axes:
##  RDA1  RDA2  RDA3 
## 8.633 5.522 2.639 
## 
## Eigenvalues for unconstrained axes:
##    PC1    PC2    PC3    PC4    PC5    PC6    PC7    PC8    PC9   PC10 
## 20.592 13.428  8.233  5.397  3.968  2.528  2.356  1.835  0.713  0.527
#Este modelo explica un 16.79% de la composicion biologica