Script Article TCC
Arthur Barros, Rodrigo Carmo e Felipe Melo
11/01/2022
Dado
Seed_rain_origins<-read_csv("base_geral.csv", locale = locale(decimal_mark = ","))
Seed_rain_origins %>%
drop_na() %>%
mutate(id_real=as.factor(id_real),
id=NULL,
site_plot = paste(site, plot),
yr=as.factor(yr),
site=as.factor(site),
frag_cat=as.factor(frag_cat),
disp_mode=as.factor(disp_mode),
origen=as.factor(origen)) %>%
filter(habit!=c("liana","shrub") & origen!="x")-> Seed_rain_origins
str(Seed_rain_origins)
## tibble [934 x 12] (S3: tbl_df/tbl/data.frame)
## $ frag_cat : Factor w/ 4 levels "Control","Large",..: 4 4 4 4 4 4 4 4 4 4 ...
## $ area : num [1:934] 2.9 2.9 2.9 2.9 2.9 2.9 2.9 2.9 2.9 2.9 ...
## $ site : Factor w/ 8 levels "C1","C2","G1",..: 7 7 7 7 7 7 7 7 7 7 ...
## $ plot : chr [1:934] "Q1" "Q1" "Q1" "Q1" ...
## $ disp_mode : Factor w/ 2 levels "abio","zoo": 2 2 1 2 1 2 2 2 2 2 ...
## $ seed_size_cat: chr [1:934] "M" "P" "P" "G" ...
## $ habit : chr [1:934] "tree" "und-tree" "tree" "tree" ...
## $ origen : Factor w/ 3 levels "d","nd","x": 2 2 2 2 1 2 2 2 2 1 ...
## $ id_real : Factor w/ 43 levels "1","5","6","7",..: 32 30 26 10 15 7 18 37 39 22 ...
## $ abund : num [1:934] 40 1 38 5 20 0 5 1 114 0 ...
## $ yr : Factor w/ 2 levels "2006","2007": 1 1 1 1 1 1 1 1 1 1 ...
## $ site_plot : chr [1:934] "P1 Q1" "P1 Q1" "P1 Q1" "P1 Q1" ...
paged_table(Seed_rain_origins)Calculando a diversidade interpolada no inext
Seed_rain_origins %>%
select(yr, frag_cat, disp_mode, origen, id_real, abund) %>%
#str()
mutate(all_variables=as.factor(paste(yr, frag_cat, disp_mode, origen))) %>%
#str()
select(all_variables, id_real, abund) %>%
pivot_wider(names_from = all_variables, values_from =abund, values_fn = sum) %>%
replace(is.na(.),0)-> inext_data
#inext_data %>%
# colnames()
l_06_small_zoo_d <- c(43, sort(inext_data$`2006 Small zoo d`[inext_data$`2006 Small zoo d`>0],
decreasing = TRUE))
l_06_small_zoo_nd <- c(43, sort(inext_data$`2006 Small zoo nd`[inext_data$`2006 Small zoo nd`>0],
decreasing = TRUE))
l_06_small_abio_d <- c(43, sort(inext_data$`2006 Small abio d`[inext_data$`2006 Small abio d`>0],
decreasing = TRUE))
l_06_small_abio_nd <- c(43, sort(inext_data$`2006 Small abio nd`[inext_data$`2006 Small abio nd`>0],
decreasing = TRUE))
l_06_medium_zoo_d <- c(43, sort(inext_data$`2006 Medium zoo d`[inext_data$`2006 Medium zoo d`>0],
decreasing = TRUE))
l_06_medium_zoo_nd <- c(43, sort(inext_data$`2006 Medium zoo nd`[inext_data$`2006 Medium zoo nd`>0],
decreasing = TRUE))
l_06_medium_abio_d <- c(43, sort(inext_data$`2006 Medium abio d`[inext_data$`2006 Medium abio d`>0],
decreasing = TRUE))
l_06_medium_abio_nd <- c(43, sort(inext_data$`2006 Medium abio nd`[inext_data$`2006 Medium abio nd`>0],
decreasing = TRUE))
l_06_large_zoo_d <- c(43, sort(inext_data$`2006 Large zoo d`[inext_data$`2006 Large zoo d`>0],
decreasing = TRUE))
l_06_large_zoo_nd <- c(43, sort(inext_data$`2006 Large zoo nd`[inext_data$`2006 Large zoo nd`>0],
decreasing = TRUE))
l_06_large_abio_d <- c(43, sort(inext_data$`2006 Large abio d`[inext_data$`2006 Large abio d`>0],
decreasing = TRUE))
l_06_large_abio_nd <- c(43, sort(inext_data$`2006 Large abio nd`[inext_data$`2006 Large abio nd`>0],
decreasing = TRUE))
l_06_control_zoo_d <- c(43, sort(inext_data$`2006 Control zoo d`[inext_data$`2006 Control zoo d`>0],
decreasing = TRUE))
l_06_control_zoo_nd <- c(43, sort(inext_data$`2006 Control zoo nd`[inext_data$`2006 Control zoo nd`>0],
decreasing = TRUE))
l_06_control_abio_d <- c(43, sort(inext_data$`2006 Control abio d`[inext_data$`2006 Control abio d`>0],
decreasing = TRUE))
l_06_control_abio_nd <- c(43, sort(inext_data$`2006 Control abio nd`[inext_data$`2006 Control abio nd`>0],
decreasing = TRUE))
#####
#Ano 07
l_07_small_zoo_d <- c(43, sort(inext_data$`2007 Small zoo d`[inext_data$`2007 Small zoo d`>0],
decreasing = TRUE))
l_07_small_zoo_nd <- c(43, sort(inext_data$`2007 Small zoo nd`[inext_data$`2007 Small zoo nd`>0],
decreasing = TRUE))
l_07_small_abio_d <- c(43, sort(inext_data$`2007 Small abio d`[inext_data$`2007 Small abio d`>0],
decreasing = TRUE))
l_07_small_abio_nd <- c(43, sort(inext_data$`2007 Small abio nd`[inext_data$`2007 Small abio nd`>0],
decreasing = TRUE))
l_07_medium_zoo_d <- c(43, sort(inext_data$`2007 Medium zoo d`[inext_data$`2007 Medium zoo d`>0],
decreasing = TRUE))
l_07_medium_zoo_nd <- c(43, sort(inext_data$`2007 Medium zoo nd`[inext_data$`2007 Medium zoo nd`>0],
decreasing = TRUE))
l_07_medium_abio_d <- c(43, sort(inext_data$`2007 Medium abio d`[inext_data$`2007 Medium abio d`>0],
decreasing = TRUE))
l_07_medium_abio_nd <- c(43, sort(inext_data$`2007 Medium abio nd`[inext_data$`2007 Medium abio nd`>0],
decreasing = TRUE))
l_07_large_zoo_d <- c(43, sort(inext_data$`2007 Large zoo d`[inext_data$`2007 Large zoo d`>0],
decreasing = TRUE))
l_07_large_zoo_nd <- c(43, sort(inext_data$`2007 Large zoo nd`[inext_data$`2007 Large zoo nd`>0],
decreasing = TRUE))
l_07_large_abio_d <- c(43, sort(inext_data$`2007 Large abio d`[inext_data$`2007 Large abio d`>0],
decreasing = TRUE))
l_07_large_abio_nd <- c(43, sort(inext_data$`2007 Large abio nd`[inext_data$`2007 Large abio nd`>0],
decreasing = TRUE))
l_07_control_zoo_d <- c(43, sort(inext_data$`2007 Control zoo d`[inext_data$`2007 Control zoo d`>0],
decreasing = TRUE))
l_07_control_zoo_nd <- c(43, sort(inext_data$`2007 Control zoo nd`[inext_data$`2007 Control zoo nd`>0],
decreasing = TRUE))
l_07_control_abio_d <- c(43, sort(inext_data$`2007 Control abio d`[inext_data$`2007 Control abio d`>0],
decreasing = TRUE))
l_07_control_abio_nd <- c(43, sort(inext_data$`2007 Control abio nd`[inext_data$`2007 Control abio nd`>0],
decreasing = TRUE))
#####
# continue
inext_list_data <- list(
l_06_small_zoo_d = l_06_small_zoo_d,
l_06_small_zoo_nd = l_06_small_zoo_nd,
l_06_small_abio_d = l_06_small_abio_d,
l_06_small_abio_nd = l_06_small_abio_nd,
l_06_medium_zoo_d = l_06_medium_zoo_d,
l_06_medium_zoo_nd = l_06_medium_zoo_nd,
l_06_medium_abio_d = l_06_medium_abio_d,
l_06_medium_abio_nd = l_06_medium_abio_nd,
l_06_large_zoo_d = l_06_large_zoo_d,
l_06_large_zoo_nd = l_06_large_zoo_nd,
l_06_large_abio_d = l_06_large_abio_d,
l_06_large_abio_nd = l_06_large_abio_nd,
l_06_control_zoo_d = l_06_control_zoo_d,
l_06_control_zoo_nd = l_06_control_zoo_nd,
l_06_control_abio_d = l_06_control_abio_d,
l_06_control_abio_nd = l_06_control_abio_nd,
l_07_small_zoo_d = l_07_small_zoo_d,
l_07_small_zoo_nd = l_07_small_zoo_nd,
l_07_small_abio_d = l_07_small_abio_d,
l_07_small_abio_nd = l_07_small_abio_nd,
l_07_medium_zoo_d = l_07_medium_zoo_d,
l_07_medium_zoo_nd = l_07_medium_zoo_nd,
l_07_medium_abio_d = l_07_medium_abio_d,
l_07_medium_abio_nd = l_07_medium_abio_nd,
l_07_large_zoo_d = l_07_large_zoo_d,
l_07_large_zoo_nd = l_07_large_zoo_nd,
l_07_large_abio_d = l_07_large_abio_d,
l_07_large_abio_nd = l_07_large_abio_nd,
l_07_control_zoo_d = l_07_control_zoo_d,
l_07_control_zoo_nd = l_07_control_zoo_nd,
l_07_control_abio_d = l_07_control_abio_d,
l_07_control_abio_nd = l_07_control_abio_nd
)
iNEXT(x=inext_list_data, q=c(0, 1, 2), datatype="abundance")->inext_result
#####
# juntanto tudo - Ano 06
inext_result[["iNextEst"]][["l_06_small_zoo_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("small", 57),
disp_mode=rep("zoo", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_small_zoo_d
inext_result[["iNextEst"]][["l_06_small_zoo_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("small", 57),
disp_mode=rep("zoo", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_small_zoo_nd
inext_result[["iNextEst"]][["l_06_small_abio_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("small", 57),
disp_mode=rep("abio", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_small_abio_d
inext_result[["iNextEst"]][["l_06_small_abio_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("small", 57),
disp_mode=rep("abio", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_small_abio_nd
#medium
inext_result[["iNextEst"]][["l_06_medium_zoo_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("medium", 57),
disp_mode=rep("zoo", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_medium_zoo_d
inext_result[["iNextEst"]][["l_06_medium_zoo_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("medium", 57),
disp_mode=rep("zoo", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_medium_zoo_nd
inext_result[["iNextEst"]][["l_06_medium_abio_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("medium", 57),
disp_mode=rep("abio", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_medium_abio_d
inext_result[["iNextEst"]][["l_06_medium_abio_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("medium", 57),
disp_mode=rep("abio", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_medium_abio_nd
### Large
inext_result[["iNextEst"]][["l_06_large_zoo_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("large", 57),
disp_mode=rep("zoo", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_large_zoo_d
inext_result[["iNextEst"]][["l_06_large_zoo_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("large", 57),
disp_mode=rep("zoo", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_large_zoo_nd
inext_result[["iNextEst"]][["l_06_large_abio_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("large", 57),
disp_mode=rep("abio", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_large_abio_d
inext_result[["iNextEst"]][["l_06_large_abio_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("large", 57),
disp_mode=rep("abio", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_large_abio_nd
### Control
inext_result[["iNextEst"]][["l_06_control_zoo_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("control", 57),
disp_mode=rep("zoo", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_control_zoo_d
inext_result[["iNextEst"]][["l_06_control_zoo_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("control", 57),
disp_mode=rep("zoo", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_control_zoo_nd
inext_result[["iNextEst"]][["l_06_control_abio_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("control", 57),
disp_mode=rep("abio", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_control_abio_d
inext_result[["iNextEst"]][["l_06_control_abio_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2006", 57),
frag_cat=rep("control", 57),
disp_mode=rep("abio", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_06_control_abio_nd
#####
# Agora pro ano de 2007
inext_result[["iNextEst"]][["l_07_small_zoo_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("small", 57),
disp_mode=rep("zoo", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_small_zoo_d
inext_result[["iNextEst"]][["l_07_small_zoo_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("small", 57),
disp_mode=rep("zoo", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_small_zoo_nd
inext_result[["iNextEst"]][["l_07_small_abio_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("small", 57),
disp_mode=rep("abio", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_small_abio_d
inext_result[["iNextEst"]][["l_07_small_abio_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("small", 57),
disp_mode=rep("abio", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_small_abio_nd
#medium
inext_result[["iNextEst"]][["l_07_medium_zoo_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("medium", 57),
disp_mode=rep("zoo", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_medium_zoo_d
inext_result[["iNextEst"]][["l_07_medium_zoo_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("medium", 57),
disp_mode=rep("zoo", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_medium_zoo_nd
inext_result[["iNextEst"]][["l_07_medium_abio_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("medium", 57),
disp_mode=rep("abio", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_medium_abio_d
inext_result[["iNextEst"]][["l_07_medium_abio_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("medium", 57),
disp_mode=rep("abio", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_medium_abio_nd
### Large
inext_result[["iNextEst"]][["l_07_large_zoo_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("large", 57),
disp_mode=rep("zoo", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_large_zoo_d
inext_result[["iNextEst"]][["l_07_large_zoo_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("large", 57),
disp_mode=rep("zoo", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_large_zoo_nd
inext_result[["iNextEst"]][["l_07_large_abio_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("large", 57),
disp_mode=rep("abio", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_large_abio_d
inext_result[["iNextEst"]][["l_07_large_abio_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("large", 57),
disp_mode=rep("abio", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_large_abio_nd
### Control
inext_result[["iNextEst"]][["l_07_control_zoo_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("control", 57),
disp_mode=rep("zoo", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_control_zoo_d
inext_result[["iNextEst"]][["l_07_control_zoo_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("control", 57),
disp_mode=rep("zoo", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_control_zoo_nd
inext_result[["iNextEst"]][["l_07_control_abio_d"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("control", 57),
disp_mode=rep("abio", 57),
origen=rep("d", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_control_abio_d
inext_result[["iNextEst"]][["l_07_control_abio_nd"]] %>%
filter(method=="interpolated") %>%
mutate(
yr=rep("2007", 57),
frag_cat=rep("control", 57),
disp_mode=rep("abio", 57),
origen=rep("nd", 57)) %>%
select(yr, frag_cat, disp_mode, origen, order, qD)-> data_07_control_abio_nd
#####
# juntanto tudo em um data_frame
full_join(data_06_small_zoo_d, data_06_small_zoo_nd) %>%
full_join(data_06_small_abio_d) %>%
full_join(data_06_small_abio_nd) %>%
full_join(data_06_medium_zoo_d) %>%
full_join(data_06_medium_zoo_nd) %>%
full_join(data_06_medium_abio_d) %>%
full_join(data_06_medium_abio_nd) %>%
full_join(data_06_large_zoo_d) %>%
full_join(data_06_large_zoo_nd) %>%
full_join(data_06_large_abio_d) %>%
full_join(data_06_large_abio_nd) %>%
full_join(data_06_control_zoo_d) %>%
full_join(data_06_control_zoo_nd) %>%
full_join(data_06_control_abio_d) %>%
full_join(data_06_control_abio_nd) %>%
full_join(data_07_small_zoo_d) %>%
full_join(data_07_small_zoo_nd) %>%
full_join(data_07_small_abio_d) %>%
full_join(data_07_small_abio_nd) %>%
full_join(data_07_medium_zoo_d) %>%
full_join(data_07_medium_zoo_nd) %>%
full_join(data_07_medium_abio_d) %>%
full_join(data_07_medium_abio_nd) %>%
full_join(data_07_large_zoo_d) %>%
full_join(data_07_large_zoo_nd) %>%
full_join(data_07_large_abio_d) %>%
full_join(data_07_large_abio_nd) %>%
full_join(data_07_control_zoo_d) %>%
full_join(data_07_control_zoo_nd) %>%
full_join(data_07_control_abio_d) %>%
full_join(data_07_control_abio_nd) %>%
pivot_wider(names_from = order, values_from =qD) %>%
unnest() %>%
rename("div0"=`0`,"div1"=`1`,"div2"=`2`)->div_data_geral
div_data_geral %>%
mutate(yr=as.factor(yr),
frag_cat=as.factor(frag_cat),
disp_mode=as.factor(disp_mode),
origen=as.factor(origen))->div_data_geral
paged_table(div_data_geral)AnĆ”lises exploratĆ³rias bem bĆ”sicas
Vou ajeitar as escalas ainda, galera. Isso aqui Ć© sĆ³ o bĆ”sico mesmo!
library(ggplot2)
div_data_geral %>%
ggplot(aes(x=yr , y=div0, fill=frag_cat, color=frag_cat))+
geom_boxplot(alpha=0.5)+
facet_grid(disp_mode ~ origen)+
scale_color_manual(values = c("#FFCCCC", "#FFCC99", "#FFCC66", "#FF9966")) +
scale_fill_manual(values = c("#FFCCCC", "#FFCC99", "#FFCC66", "#FF9966")) +
theme_classic()
div_data_geral %>%
ggplot(aes(x=yr , y=div1, fill=frag_cat, color=frag_cat))+
geom_boxplot(alpha=0.5)+
facet_grid(disp_mode ~ origen)+
scale_color_manual(values = c("#FFCCCC", "#FFCC99", "#FFCC66", "#FF9966")) +
scale_fill_manual(values = c("#FFCCCC", "#FFCC99", "#FFCC66", "#FF9966")) +
theme_classic()
div_data_geral %>%
ggplot(aes(x=yr , y=div2, fill=frag_cat, color=frag_cat))+
geom_boxplot(alpha=0.5)+
facet_grid(disp_mode ~ origen)+
scale_color_manual(values = c("#FFCCCC", "#FFCC99", "#FFCC66", "#FF9966")) +
scale_fill_manual(values = c("#FFCCCC", "#FFCC99", "#FFCC66", "#FF9966")) +
theme_classic()
div_data_geral %>%
ggplot(mapping = aes(x=frag_cat , y=div0, fill=yr, color=yr, group=yr))+
geom_jitter(alpha=0.6) +
geom_smooth(method =lm, se=T)+
facet_grid(disp_mode ~ origen)+
scale_color_manual(values = c("#FFCCCC", "#FF9966")) +
scale_fill_manual(values = c("#FFCCCC", "#FF9966")) +
theme_classic()
div_data_geral %>%
ggplot(mapping = aes(x=frag_cat , y=div1, fill=yr, color=yr, group=yr))+
geom_jitter(alpha=0.6) +
geom_smooth(method =lm, se=T)+
facet_grid(disp_mode ~ origen)+
scale_color_manual(values = c("#FFCCCC", "#FF9966")) +
scale_fill_manual(values = c("#FFCCCC", "#FF9966")) +
theme_classic()
div_data_geral %>%
ggplot(mapping = aes(x=frag_cat , y=div2, fill=yr, color=yr, group=yr))+
geom_jitter(alpha=0.6) +
geom_smooth(method =lm, se=T)+
facet_grid(disp_mode ~ origen)+
scale_color_manual(values = c("#FFCCCC", "#FF9966")) +
scale_fill_manual(values = c("#FFCCCC", "#FF9966")) +
theme_classic() 
Modelos
library(performance)
library(see)
library(MuMIn)
histogram(~div0, data = div_data_geral)
histogram(~div1, data = div_data_geral)
histogram(~div2, data = div_data_geral)
# testando modelos
# modelo cheio, sem interaĆ§Ć£o
model_div0<-glm(div0~yr+frag_cat+origen+disp_mode, data = div_data_geral, family = "gaussian",
na.action = "na.fail")
summary(model_div0)
##
## Call:
## glm(formula = div0 ~ yr + frag_cat + origen + disp_mode, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -11.6823 -0.8370 0.0563 1.1128 8.3017
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.9342 0.2740 18.009 < 2e-16 ***
## yr2007 -2.5415 0.2071 -12.271 < 2e-16 ***
## frag_catlarge -0.9892 0.2929 -3.377 0.00078 ***
## frag_catmedium 0.8026 0.2929 2.740 0.00632 **
## frag_catsmall -0.2731 0.2929 -0.932 0.35155
## origennd -0.2553 0.2071 -1.233 0.21818
## disp_modezoo 6.9455 0.2071 33.535 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 6.520047)
##
## Null deviance: 12492.7 on 607 degrees of freedom
## Residual deviance: 3918.5 on 601 degrees of freedom
## AIC: 2874.3
##
## Number of Fisher Scoring iterations: 2
dredge(model_div0, evaluate = TRUE, rank = "AICc", fixed = NULL, trace = TRUE)
## 0 : glm(formula = div0 ~ 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 1 : glm(formula = div0 ~ disp_mode + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 2 : glm(formula = div0 ~ frag_cat + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 3 : glm(formula = div0 ~ disp_mode + frag_cat + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 4 : glm(formula = div0 ~ origen + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 5 : glm(formula = div0 ~ disp_mode + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 6 : glm(formula = div0 ~ frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 7 : glm(formula = div0 ~ disp_mode + frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 8 : glm(formula = div0 ~ yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 9 : glm(formula = div0 ~ disp_mode + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 10 : glm(formula = div0 ~ frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 11 : glm(formula = div0 ~ disp_mode + frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 12 : glm(formula = div0 ~ origen + yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 13 : glm(formula = div0 ~ disp_mode + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 14 : glm(formula = div0 ~ frag_cat + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 15 : glm(formula = div0 ~ disp_mode + frag_cat + origen + yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## Global model call: glm(formula = div0 ~ yr + frag_cat + origen + disp_mode, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## ---
## Model selection table
## (Int) dsp_mod frg_cat org yr df logLik AICc delta weight
## 12 4.807 + + + 7 -1429.926 2874.0 0.00 0.564
## 16 4.934 + + + + 8 -1429.158 2874.6 0.52 0.436
## 10 4.692 + + 4 -1448.677 2905.4 31.38 0.000
## 14 4.819 + + + 5 -1447.956 2906.0 31.97 0.000
## 4 3.536 + + 6 -1497.742 3007.6 133.59 0.000
## 8 3.663 + + + 7 -1497.128 3008.4 134.40 0.000
## 2 3.421 + 3 -1512.835 3031.7 157.67 0.000
## 6 3.549 + + 4 -1512.251 3032.6 158.53 0.000
## 11 8.279 + + 6 -1750.067 3512.3 638.24 0.000
## 15 8.407 + + + 7 -1749.800 3513.8 639.75 0.000
## 9 8.164 + 3 -1756.741 3519.5 645.48 0.000
## 13 8.292 + + 4 -1756.479 3521.0 646.99 0.000
## 3 7.009 + 5 -1775.479 3561.1 687.02 0.000
## 7 7.136 + + 6 -1775.233 3562.6 688.57 0.000
## 1 6.894 2 -1781.623 3567.3 693.23 0.000
## 5 7.021 + 3 -1781.382 3568.8 694.77 0.000
## Models ranked by AICc(x)
# modelo cheio com interaĆ§Ć£o entre o ano e as demais variĆ”veis
model_int_div0<-glm(div0~yr*frag_cat+yr*origen+yr*disp_mode, data = div_data_geral, family = "gaussian",
na.action = "na.fail")
summary(model_int_div0)
##
## Call:
## glm(formula = div0 ~ yr * frag_cat + yr * origen + yr * disp_mode,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -13.4163 -0.7086 0.2031 1.2873 6.5677
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.3561 0.3360 12.965 < 2e-16 ***
## yr2007 -1.3853 0.4752 -2.915 0.00369 **
## frag_catlarge -0.6535 0.3880 -1.684 0.09263 .
## frag_catmedium 2.0521 0.3880 5.289 1.73e-07 ***
## frag_catsmall 0.6045 0.3880 1.558 0.11973
## origennd -1.3931 0.2743 -5.078 5.11e-07 ***
## disp_modezoo 8.0082 0.2743 29.191 < 2e-16 ***
## yr2007:frag_catlarge -0.6714 0.5487 -1.224 0.22159
## yr2007:frag_catmedium -2.4989 0.5487 -4.554 6.37e-06 ***
## yr2007:frag_catsmall -1.7552 0.5487 -3.199 0.00145 **
## yr2007:origennd 2.2756 0.3880 5.865 7.44e-09 ***
## yr2007:disp_modezoo -2.1253 0.3880 -5.478 6.36e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 5.719991)
##
## Null deviance: 12492.7 on 607 degrees of freedom
## Residual deviance: 3409.1 on 596 degrees of freedom
## AIC: 2799.6
##
## Number of Fisher Scoring iterations: 2
dredge(model_int_div0, evaluate = TRUE, rank = "AICc", fixed = NULL, trace = TRUE)
## 0 : glm(formula = div0 ~ 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 1 : glm(formula = div0 ~ disp_mode + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 2 : glm(formula = div0 ~ frag_cat + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 3 : glm(formula = div0 ~ disp_mode + frag_cat + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 4 : glm(formula = div0 ~ origen + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 5 : glm(formula = div0 ~ disp_mode + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 6 : glm(formula = div0 ~ frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 7 : glm(formula = div0 ~ disp_mode + frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 8 : glm(formula = div0 ~ yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 9 : glm(formula = div0 ~ disp_mode + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 10 : glm(formula = div0 ~ frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 11 : glm(formula = div0 ~ disp_mode + frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 12 : glm(formula = div0 ~ origen + yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 13 : glm(formula = div0 ~ disp_mode + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 14 : glm(formula = div0 ~ frag_cat + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 15 : glm(formula = div0 ~ disp_mode + frag_cat + origen + yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 25 : glm(formula = div0 ~ disp_mode + yr + disp_mode:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 27 : glm(formula = div0 ~ disp_mode + frag_cat + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 29 : glm(formula = div0 ~ disp_mode + origen + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 31 : glm(formula = div0 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 42 : glm(formula = div0 ~ frag_cat + yr + frag_cat:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 43 : glm(formula = div0 ~ disp_mode + frag_cat + yr + frag_cat:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 46 : glm(formula = div0 ~ frag_cat + origen + yr + frag_cat:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 47 : glm(formula = div0 ~ disp_mode + frag_cat + origen + yr + frag_cat:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 59 : glm(formula = div0 ~ disp_mode + frag_cat + yr + disp_mode:yr +
## frag_cat:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 63 : glm(formula = div0 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## frag_cat:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 76 : glm(formula = div0 ~ origen + yr + origen:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 77 : glm(formula = div0 ~ disp_mode + origen + yr + origen:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 78 : glm(formula = div0 ~ frag_cat + origen + yr + origen:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 79 : glm(formula = div0 ~ disp_mode + frag_cat + origen + yr + origen:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 93 : glm(formula = div0 ~ disp_mode + origen + yr + disp_mode:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 95 : glm(formula = div0 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 110 : glm(formula = div0 ~ frag_cat + origen + yr + frag_cat:yr + origen:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 111 : glm(formula = div0 ~ disp_mode + frag_cat + origen + yr + frag_cat:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 127 : glm(formula = div0 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## frag_cat:yr + origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## Global model call: glm(formula = div0 ~ yr * frag_cat + yr * origen + yr * disp_mode,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## ---
## Model selection table
## (Int) dsp_mod frg_cat org yr dsp_mod:yr frg_cat:yr org:yr df logLik
## 128 4.356 + + + + + + + 13 -1386.821
## 96 4.972 + + + + + + 10 -1399.143
## 112 4.887 + + + + + + 12 -1401.753
## 60 3.660 + + + + + 11 -1404.714
## 64 3.787 + + + + + + 12 -1403.880
## 80 5.503 + + + + + 9 -1413.496
## 28 4.275 + + + + 8 -1416.345
## 32 4.403 + + + + + 9 -1415.542
## 94 4.857 + + + + + 7 -1419.826
## 44 4.191 + + + + 10 -1418.813
## 48 4.319 + + + + + 11 -1418.016
## 12 4.807 + + + 7 -1429.926
## 16 4.934 + + + + 8 -1429.158
## 78 5.388 + + + + 6 -1433.255
## 26 4.160 + + + 5 -1435.926
## 30 4.288 + + + + 6 -1435.173
## 10 4.692 + + 4 -1448.677
## 14 4.819 + + + 5 -1447.956
## 4 3.536 + + 6 -1497.742
## 8 3.663 + + + 7 -1497.128
## 2 3.421 + 3 -1512.835
## 6 3.549 + + 4 -1512.251
## 111 8.360 + + + + + 11 -1740.533
## 79 8.976 + + + + 8 -1744.436
## 43 7.664 + + + 9 -1746.236
## 11 8.279 + + 6 -1750.067
## 47 7.791 + + + + 10 -1745.965
## 77 8.861 + + + 5 -1751.233
## 15 8.407 + + + 7 -1749.800
## 9 8.164 + 3 -1756.741
## 13 8.292 + + 4 -1756.479
## 3 7.009 + 5 -1775.479
## 7 7.136 + + 6 -1775.233
## 1 6.894 2 -1781.623
## 5 7.021 + 3 -1781.382
## AICc delta weight
## 128 2800.3 0.00 1
## 96 2818.7 18.40 0
## 112 2828.0 27.78 0
## 60 2831.9 31.62 0
## 64 2832.3 32.03 0
## 80 2845.3 45.04 0
## 28 2848.9 48.68 0
## 32 2849.4 49.13 0
## 94 2853.8 53.58 0
## 44 2858.0 57.74 0
## 48 2858.5 58.22 0
## 12 2874.0 73.78 0
## 16 2874.6 74.30 0
## 78 2878.7 78.40 0
## 26 2882.0 81.70 0
## 30 2882.5 82.23 0
## 10 2905.4 105.17 0
## 14 2906.0 105.76 0
## 4 3007.6 207.37 0
## 8 3008.4 208.19 0
## 2 3031.7 231.46 0
## 6 3032.6 232.31 0
## 111 3503.5 703.25 0
## 79 3505.1 704.86 0
## 43 3510.8 710.52 0
## 11 3512.3 712.02 0
## 47 3512.3 712.04 0
## 77 3512.6 712.31 0
## 15 3513.8 713.53 0
## 9 3519.5 719.27 0
## 13 3521.0 720.77 0
## 3 3561.1 760.80 0
## 7 3562.6 762.35 0
## 1 3567.3 767.01 0
## 5 3568.8 768.55 0
## Models ranked by AICc(x)
# modelo sem interaĆ§Ć£o com o ano como variĆ”vel aleatĆ³ria
model_lmer_div0<-lmer(div0~frag_cat+origen+disp_mode+(1|yr), data = div_data_geral,
na.action = "na.fail")
summary(model_lmer_div0)
## Linear mixed model fit by REML ['lmerMod']
## Formula: div0 ~ frag_cat + origen + disp_mode + (1 | yr)
## Data: div_data_geral
##
## REML criterion at convergence: 2872.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.5718 -0.3300 0.0251 0.4391 3.2545
##
## Random effects:
## Groups Name Variance Std.Dev.
## yr (Intercept) 3.208 1.791
## Residual 6.520 2.553
## Number of obs: 608, groups: yr, 2
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 3.6635 1.2917 2.836
## frag_catlarge -0.9892 0.2929 -3.377
## frag_catmedium 0.8026 0.2929 2.740
## frag_catsmall -0.2731 0.2929 -0.932
## origennd -0.2553 0.2071 -1.233
## disp_modezoo 6.9455 0.2071 33.535
##
## Correlation of Fixed Effects:
## (Intr) frg_ctl frg_ctm frg_cts orgnnd
## frag_catlrg -0.113
## frag_catmdm -0.113 0.500
## frag_ctsmll -0.113 0.500 0.500
## origennd -0.080 0.000 0.000 0.000
## disp_modezo -0.080 0.000 0.000 0.000 0.000
dredge(model_lmer_div0, evaluate = TRUE, rank = "AICc", fixed = NULL, trace = TRUE)
## 0 : lmer(formula = div0 ~ (1 | yr), data = div_data_geral, na.action = "na.fail")
## 1 : lmer(formula = div0 ~ disp_mode + (1 | yr), data = div_data_geral,
## na.action = "na.fail")
## 2 : lmer(formula = div0 ~ frag_cat + (1 | yr), data = div_data_geral,
## na.action = "na.fail")
## 3 : lmer(formula = div0 ~ disp_mode + frag_cat + (1 | yr), data = div_data_geral,
## na.action = "na.fail")
## 4 : lmer(formula = div0 ~ origen + (1 | yr), data = div_data_geral,
## na.action = "na.fail")
## 5 : lmer(formula = div0 ~ disp_mode + origen + (1 | yr), data = div_data_geral,
## na.action = "na.fail")
## 6 : lmer(formula = div0 ~ frag_cat + origen + (1 | yr), data = div_data_geral,
## na.action = "na.fail")
## 7 : lmer(formula = div0 ~ disp_mode + frag_cat + origen + (1 | yr),
## data = div_data_geral, na.action = "na.fail")
## Global model call: lmer(formula = div0 ~ frag_cat + origen + disp_mode + (1 | yr),
## data = div_data_geral, na.action = "na.fail")
## ---
## Model selection table
## (Int) dsp_mod frg_cat org df logLik AICc delta weight
## 4 3.536 + + 7 -1436.223 2886.6 0.00 0.716
## 8 3.663 + + + 8 -1436.119 2888.5 1.85 0.284
## 2 3.421 + 4 -1453.606 2915.3 28.65 0.000
## 6 3.549 + + 5 -1453.515 2917.1 30.50 0.000
## 3 7.009 + 6 -1753.076 3518.3 631.66 0.000
## 7 7.136 + + 7 -1752.940 3520.1 633.43 0.000
## 1 6.894 3 -1760.029 3526.1 639.46 0.000
## 5 7.021 + 4 -1759.889 3527.8 641.21 0.000
## Models ranked by AICc(x)
## Random terms (all models):
## 1 | yr
# modelo com interaĆ§Ć£o com o ano como variĆ”vel aleatĆ³ria
model_int_lmer_div0<-lmer(div0~frag_cat*origen*disp_mode+(1|yr), data = div_data_geral,
na.action = "na.fail")
summary(model_int_lmer_div0)
## Linear mixed model fit by REML ['lmerMod']
## Formula: div0 ~ frag_cat * origen * disp_mode + (1 | yr)
## Data: div_data_geral
##
## REML criterion at convergence: 2823.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -5.2377 -0.2809 0.0234 0.4267 2.7897
##
## Random effects:
## Groups Name Variance Std.Dev.
## yr (Intercept) 3.209 1.791
## Residual 6.198 2.489
## Number of obs: 608, groups: yr, 2
##
## Fixed effects:
## Estimate Std. Error t value
## (Intercept) 3.0001 1.3295 2.256
## frag_catlarge -0.2068 0.5711 -0.362
## frag_catmedium 0.8571 0.5711 1.501
## frag_catsmall 1.2292 0.5711 2.152
## origennd 1.5693 0.5711 2.748
## disp_modezoo 6.8163 0.5711 11.935
## frag_catlarge:origennd -2.0250 0.8077 -2.507
## frag_catmedium:origennd -1.2359 0.8077 -1.530
## frag_catsmall:origennd -3.4092 0.8077 -4.221
## frag_catlarge:disp_modezoo -0.2851 0.8077 -0.353
## frag_catmedium:disp_modezoo 2.1030 0.8077 2.604
## frag_catsmall:disp_modezoo -0.6724 0.8077 -0.833
## origennd:disp_modezoo -0.7373 0.8077 -0.913
## frag_catlarge:origennd:disp_modezoo 1.4907 1.1423 1.305
## frag_catmedium:origennd:disp_modezoo -1.9524 1.1423 -1.709
## frag_catsmall:origennd:disp_modezoo 2.1540 1.1423 1.886
dredge(model_int_lmer_div0, evaluate = TRUE, rank = "AICc", fixed = NULL, trace = TRUE)
## 0 : lmer(formula = div0 ~ (1 | yr), data = div_data_geral, na.action = "na.fail")
## 1 : lmer(formula = div0 ~ disp_mode + (1 | yr), data = div_data_geral,
## na.action = "na.fail")
## 2 : lmer(formula = div0 ~ frag_cat + (1 | yr), data = div_data_geral,
## na.action = "na.fail")
## 3 : lmer(formula = div0 ~ disp_mode + frag_cat + (1 | yr), data = div_data_geral,
## na.action = "na.fail")
## 4 : lmer(formula = div0 ~ origen + (1 | yr), data = div_data_geral,
## na.action = "na.fail")
## 5 : lmer(formula = div0 ~ disp_mode + origen + (1 | yr), data = div_data_geral,
## na.action = "na.fail")
## 6 : lmer(formula = div0 ~ frag_cat + origen + (1 | yr), data = div_data_geral,
## na.action = "na.fail")
## 7 : lmer(formula = div0 ~ disp_mode + frag_cat + origen + (1 | yr),
## data = div_data_geral, na.action = "na.fail")
## 11 : lmer(formula = div0 ~ disp_mode + frag_cat + (1 | yr) + disp_mode:frag_cat,
## data = div_data_geral, na.action = "na.fail")
## 15 : lmer(formula = div0 ~ disp_mode + frag_cat + origen + (1 | yr) +
## disp_mode:frag_cat, data = div_data_geral, na.action = "na.fail")
## 21 : lmer(formula = div0 ~ disp_mode + origen + (1 | yr) + disp_mode:origen,
## data = div_data_geral, na.action = "na.fail")
## 23 : lmer(formula = div0 ~ disp_mode + frag_cat + origen + (1 | yr) +
## disp_mode:origen, data = div_data_geral, na.action = "na.fail")
## 31 : lmer(formula = div0 ~ disp_mode + frag_cat + origen + (1 | yr) +
## disp_mode:frag_cat + disp_mode:origen, data = div_data_geral,
## na.action = "na.fail")
## 38 : lmer(formula = div0 ~ frag_cat + origen + (1 | yr) + frag_cat:origen,
## data = div_data_geral, na.action = "na.fail")
## 39 : lmer(formula = div0 ~ disp_mode + frag_cat + origen + (1 | yr) +
## frag_cat:origen, data = div_data_geral, na.action = "na.fail")
## 47 : lmer(formula = div0 ~ disp_mode + frag_cat + origen + (1 | yr) +
## disp_mode:frag_cat + frag_cat:origen, data = div_data_geral,
## na.action = "na.fail")
## 55 : lmer(formula = div0 ~ disp_mode + frag_cat + origen + (1 | yr) +
## disp_mode:origen + frag_cat:origen, data = div_data_geral,
## na.action = "na.fail")
## 63 : lmer(formula = div0 ~ disp_mode + frag_cat + origen + (1 | yr) +
## disp_mode:frag_cat + disp_mode:origen + frag_cat:origen,
## data = div_data_geral, na.action = "na.fail")
## 127 : lmer(formula = div0 ~ disp_mode + frag_cat + origen + (1 | yr) +
## disp_mode:frag_cat + disp_mode:origen + frag_cat:origen +
## disp_mode:frag_cat:origen, data = div_data_geral, na.action = "na.fail")
## Global model call: lmer(formula = div0 ~ frag_cat * origen * disp_mode + (1 | yr),
## data = div_data_geral, na.action = "na.fail")
## ---
## Model selection table
## (Int) dsp_mod frg_cat org dsp_mod:frg_cat dsp_mod:org frg_cat:org
## 128 3.000 + + + + + +
## 40 2.935 + + + +
## 48 3.184 + + + + +
## 56 2.857 + + + + +
## 64 3.106 + + + + + +
## 4 3.536 + +
## 12 3.785 + + +
## 8 3.663 + + +
## 16 3.912 + + + +
## 24 3.585 + + + +
## 32 3.834 + + + + +
## 2 3.421 +
## 6 3.549 + +
## 22 3.470 + + +
## 39 6.408 + + +
## 3 7.009 +
## 7 7.136 + +
## 1 6.894
## 5 7.021 +
## dsp_mod:frg_cat:org df logLik AICc delta weight
## 128 + 18 -1411.593 2860.3 0.00 0.994
## 40 11 -1425.014 2872.5 12.12 0.002
## 48 14 -1422.290 2873.3 12.94 0.002
## 56 12 -1424.695 2873.9 13.57 0.001
## 64 15 -1421.971 2874.8 14.41 0.001
## 4 7 -1436.223 2886.6 26.29 0.000
## 12 10 -1433.513 2887.4 27.05 0.000
## 8 8 -1436.119 2888.5 28.13 0.000
## 16 11 -1433.409 2889.3 28.91 0.000
## 24 9 -1435.794 2889.9 29.54 0.000
## 32 12 -1433.083 2890.7 30.34 0.000
## 2 4 -1453.606 2915.3 54.93 0.000
## 6 5 -1453.515 2917.1 56.78 0.000
## 22 6 -1453.178 2918.5 58.15 0.000
## 39 10 -1746.999 3514.4 654.02 0.000
## 3 6 -1753.076 3518.3 657.95 0.000
## 7 7 -1752.940 3520.1 659.72 0.000
## 1 3 -1760.029 3526.1 665.75 0.000
## 5 4 -1759.889 3527.8 667.50 0.000
## Models ranked by AICc(x)
## Random terms (all models):
## 1 | yr
# teestando o modelo comm interaƧƵes do ano para a diverisdade 1 e 2
model_int_div1<-glm(div1~yr*frag_cat+yr*origen+yr*disp_mode, data = div_data_geral, family = "gaussian",
na.action = "na.fail")
summary(model_int_div1)
##
## Call:
## glm(formula = div1 ~ yr * frag_cat + yr * origen + yr * disp_mode,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.9631 -0.7119 0.0186 0.8403 3.1909
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.6169 0.1883 19.205 < 2e-16 ***
## yr2007 -1.6935 0.2663 -6.359 4.06e-10 ***
## frag_catlarge -1.0913 0.2175 -5.018 6.89e-07 ***
## frag_catmedium -0.6966 0.2175 -3.203 0.001432 **
## frag_catsmall 0.4605 0.2175 2.117 0.034635 *
## origennd -2.1987 0.1538 -14.299 < 2e-16 ***
## disp_modezoo 3.8858 0.1538 25.270 < 2e-16 ***
## yr2007:frag_catlarge 1.1695 0.3075 3.803 0.000158 ***
## yr2007:frag_catmedium 0.2055 0.3075 0.668 0.504292
## yr2007:frag_catsmall -0.5719 0.3075 -1.860 0.063434 .
## yr2007:origennd 2.3934 0.2175 11.006 < 2e-16 ***
## yr2007:disp_modezoo -1.3482 0.2175 -6.199 1.06e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 1.797072)
##
## Null deviance: 3345.9 on 607 degrees of freedom
## Residual deviance: 1071.1 on 596 degrees of freedom
## AIC: 2095.7
##
## Number of Fisher Scoring iterations: 2
dredge(model_int_div1, evaluate = TRUE, rank = "AICc", fixed = NULL, trace = TRUE)
## 0 : glm(formula = div1 ~ 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 1 : glm(formula = div1 ~ disp_mode + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 2 : glm(formula = div1 ~ frag_cat + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 3 : glm(formula = div1 ~ disp_mode + frag_cat + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 4 : glm(formula = div1 ~ origen + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 5 : glm(formula = div1 ~ disp_mode + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 6 : glm(formula = div1 ~ frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 7 : glm(formula = div1 ~ disp_mode + frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 8 : glm(formula = div1 ~ yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 9 : glm(formula = div1 ~ disp_mode + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 10 : glm(formula = div1 ~ frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 11 : glm(formula = div1 ~ disp_mode + frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 12 : glm(formula = div1 ~ origen + yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 13 : glm(formula = div1 ~ disp_mode + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 14 : glm(formula = div1 ~ frag_cat + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 15 : glm(formula = div1 ~ disp_mode + frag_cat + origen + yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 25 : glm(formula = div1 ~ disp_mode + yr + disp_mode:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 27 : glm(formula = div1 ~ disp_mode + frag_cat + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 29 : glm(formula = div1 ~ disp_mode + origen + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 31 : glm(formula = div1 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 42 : glm(formula = div1 ~ frag_cat + yr + frag_cat:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 43 : glm(formula = div1 ~ disp_mode + frag_cat + yr + frag_cat:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 46 : glm(formula = div1 ~ frag_cat + origen + yr + frag_cat:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 47 : glm(formula = div1 ~ disp_mode + frag_cat + origen + yr + frag_cat:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 59 : glm(formula = div1 ~ disp_mode + frag_cat + yr + disp_mode:yr +
## frag_cat:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 63 : glm(formula = div1 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## frag_cat:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 76 : glm(formula = div1 ~ origen + yr + origen:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 77 : glm(formula = div1 ~ disp_mode + origen + yr + origen:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 78 : glm(formula = div1 ~ frag_cat + origen + yr + origen:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 79 : glm(formula = div1 ~ disp_mode + frag_cat + origen + yr + origen:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 93 : glm(formula = div1 ~ disp_mode + origen + yr + disp_mode:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 95 : glm(formula = div1 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 110 : glm(formula = div1 ~ frag_cat + origen + yr + frag_cat:yr + origen:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 111 : glm(formula = div1 ~ disp_mode + frag_cat + origen + yr + frag_cat:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 127 : glm(formula = div1 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## frag_cat:yr + origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## Global model call: glm(formula = div1 ~ yr * frag_cat + yr * origen + yr * disp_mode,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## ---
## Model selection table
## (Int) dsp_mod frg_cat org yr dsp_mod:yr frg_cat:yr org:yr df logLik
## 128 3.617 + + + + + + + 13 -1034.847
## 96 3.516 + + + + + + 10 -1051.384
## 112 3.954 + + + + + + 12 -1053.844
## 94 3.285 + + + + + 7 -1068.287
## 80 3.854 + + + + + 9 -1069.405
## 78 3.622 + + + + 6 -1085.359
## 64 3.018 + + + + + + 12 -1091.093
## 32 2.918 + + + + + 9 -1104.899
## 48 3.356 + + + + + 11 -1106.963
## 30 2.687 + + + + 6 -1119.136
## 16 3.255 + + + + 8 -1120.082
## 60 2.518 + + + + + 11 -1125.114
## 14 3.024 + + + 5 -1133.641
## 28 2.417 + + + + 8 -1137.488
## 44 2.855 + + + + 10 -1139.343
## 26 2.186 + + + 5 -1150.308
## 8 2.770 + + + 7 -1149.307
## 12 2.754 + + + 7 -1151.162
## 6 2.539 + + 4 -1161.648
## 10 2.523 + + 4 -1163.429
## 4 2.269 + + 6 -1177.667
## 2 2.038 + 3 -1188.928
## 111 5.560 + + + + + 11 -1316.828
## 79 5.459 + + + + 8 -1323.477
## 77 5.228 + + + 5 -1330.497
## 47 4.961 + + + + 10 -1340.333
## 15 4.861 + + + 7 -1346.492
## 13 4.630 + + 4 -1353.005
## 43 4.460 + + + 9 -1355.790
## 7 4.376 + + 6 -1360.720
## 11 4.360 + + 6 -1361.646
## 5 4.144 + 3 -1366.939
## 9 4.129 + 3 -1367.846
## 3 3.875 + 5 -1375.198
## 1 3.643 2 -1381.130
## AICc delta weight
## 128 2096.3 0.00 1
## 96 2123.1 26.83 0
## 112 2132.2 35.91 0
## 94 2150.8 54.45 0
## 80 2157.1 60.80 0
## 78 2182.9 86.55 0
## 64 2206.7 110.40 0
## 32 2228.1 131.79 0
## 48 2236.4 140.06 0
## 30 2250.4 154.11 0
## 16 2256.4 160.10 0
## 60 2272.7 176.36 0
## 14 2277.4 181.08 0
## 28 2291.2 194.91 0
## 44 2299.1 202.75 0
## 26 2310.7 214.41 0
## 8 2312.8 216.49 0
## 12 2316.5 220.20 0
## 6 2331.4 235.06 0
## 10 2334.9 238.62 0
## 4 2367.5 271.17 0
## 2 2383.9 287.59 0
## 111 2656.1 559.79 0
## 79 2663.2 566.89 0
## 77 2671.1 574.79 0
## 47 2701.0 604.73 0
## 15 2707.2 610.86 0
## 13 2714.1 617.77 0
## 43 2729.9 633.57 0
## 7 2733.6 637.27 0
## 11 2735.4 639.13 0
## 5 2739.9 643.61 0
## 9 2741.7 645.43 0
## 3 2760.5 664.19 0
## 1 2766.3 669.97 0
## Models ranked by AICc(x)
model_int_div2<-glm(div2~yr*frag_cat+yr*origen+yr*disp_mode, data = div_data_geral, family = "gaussian",
na.action = "na.fail")
summary(model_int_div2)
##
## Call:
## glm(formula = div2 ~ yr * frag_cat + yr * origen + yr * disp_mode,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.0881 -0.7358 -0.0311 0.6638 3.4569
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.0408 0.1485 20.473 < 2e-16 ***
## yr2007 -1.4865 0.2100 -7.077 4.15e-12 ***
## frag_catlarge -0.8351 0.1715 -4.870 1.43e-06 ***
## frag_catmedium -1.0828 0.1715 -6.314 5.32e-10 ***
## frag_catsmall 0.3703 0.1715 2.159 0.03122 *
## origennd -1.7240 0.1213 -14.216 < 2e-16 ***
## disp_modezoo 2.6770 0.1213 22.074 < 2e-16 ***
## yr2007:frag_catlarge 1.1317 0.2425 4.666 3.80e-06 ***
## yr2007:frag_catmedium 0.6808 0.2425 2.807 0.00516 **
## yr2007:frag_catsmall -0.3592 0.2425 -1.481 0.13910
## yr2007:origennd 1.9864 0.1715 11.582 < 2e-16 ***
## yr2007:disp_modezoo -0.9942 0.1715 -5.797 1.10e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 1.117698)
##
## Null deviance: 1842.72 on 607 degrees of freedom
## Residual deviance: 666.15 on 596 degrees of freedom
## AIC: 1807
##
## Number of Fisher Scoring iterations: 2
dredge(model_int_div2, evaluate = TRUE, rank = "AICc", fixed = NULL, trace = TRUE)
## 0 : glm(formula = div2 ~ 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 1 : glm(formula = div2 ~ disp_mode + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 2 : glm(formula = div2 ~ frag_cat + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 3 : glm(formula = div2 ~ disp_mode + frag_cat + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 4 : glm(formula = div2 ~ origen + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 5 : glm(formula = div2 ~ disp_mode + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 6 : glm(formula = div2 ~ frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 7 : glm(formula = div2 ~ disp_mode + frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 8 : glm(formula = div2 ~ yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 9 : glm(formula = div2 ~ disp_mode + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 10 : glm(formula = div2 ~ frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 11 : glm(formula = div2 ~ disp_mode + frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 12 : glm(formula = div2 ~ origen + yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 13 : glm(formula = div2 ~ disp_mode + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 14 : glm(formula = div2 ~ frag_cat + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 15 : glm(formula = div2 ~ disp_mode + frag_cat + origen + yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 25 : glm(formula = div2 ~ disp_mode + yr + disp_mode:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 27 : glm(formula = div2 ~ disp_mode + frag_cat + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 29 : glm(formula = div2 ~ disp_mode + origen + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 31 : glm(formula = div2 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 42 : glm(formula = div2 ~ frag_cat + yr + frag_cat:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 43 : glm(formula = div2 ~ disp_mode + frag_cat + yr + frag_cat:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 46 : glm(formula = div2 ~ frag_cat + origen + yr + frag_cat:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 47 : glm(formula = div2 ~ disp_mode + frag_cat + origen + yr + frag_cat:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 59 : glm(formula = div2 ~ disp_mode + frag_cat + yr + disp_mode:yr +
## frag_cat:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 63 : glm(formula = div2 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## frag_cat:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 76 : glm(formula = div2 ~ origen + yr + origen:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 77 : glm(formula = div2 ~ disp_mode + origen + yr + origen:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 78 : glm(formula = div2 ~ frag_cat + origen + yr + origen:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 79 : glm(formula = div2 ~ disp_mode + frag_cat + origen + yr + origen:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 93 : glm(formula = div2 ~ disp_mode + origen + yr + disp_mode:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 95 : glm(formula = div2 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 110 : glm(formula = div2 ~ frag_cat + origen + yr + frag_cat:yr + origen:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 111 : glm(formula = div2 ~ disp_mode + frag_cat + origen + yr + frag_cat:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 127 : glm(formula = div2 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## frag_cat:yr + origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## Global model call: glm(formula = div2 ~ yr * frag_cat + yr * origen + yr * disp_mode,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## ---
## Model selection table
## (Int) dsp_mod frg_cat org yr dsp_mod:yr frg_cat:yr org:yr df logLik
## 128 3.041 + + + + + + + 13 -890.481
## 112 3.289 + + + + + + 12 -907.156
## 96 2.859 + + + + + + 10 -912.958
## 80 3.108 + + + + + 9 -928.474
## 94 2.654 + + + + + 7 -943.084
## 78 2.902 + + + + 6 -957.169
## 64 2.544 + + + + + + 12 -952.195
## 48 2.793 + + + + + 11 -965.874
## 32 2.363 + + + + + 9 -970.664
## 16 2.611 + + + + 8 -983.554
## 60 2.179 + + + + + 11 -981.024
## 30 2.157 + + + + 6 -995.791
## 44 2.427 + + + + 10 -993.491
## 28 1.997 + + + + 8 -997.868
## 8 2.298 + + + 7 -1003.003
## 14 2.406 + + + 5 -1007.677
## 12 2.246 + + + 7 -1009.676
## 26 1.792 + + + 5 -1020.923
## 6 2.092 + + 4 -1025.685
## 4 1.932 + + 6 -1027.569
## 10 2.040 + + 4 -1031.884
## 2 1.727 + 3 -1048.550
## 111 4.379 + + + + + 11 -1121.859
## 79 4.198 + + + + 8 -1132.566
## 77 3.992 + + + 5 -1147.568
## 47 3.883 + + + + 10 -1152.252
## 15 3.701 + + + 7 -1161.956
## 43 3.517 + + + 9 -1167.522
## 7 3.387 + + 6 -1172.924
## 13 3.496 + + 4 -1175.606
## 11 3.336 + + 6 -1176.758
## 5 3.182 + 3 -1186.101
## 3 3.022 + 5 -1187.214
## 9 3.130 + 3 -1189.773
## 1 2.817 2 -1199.798
## AICc delta weight
## 128 1807.6 0.00 1
## 112 1838.8 31.26 0
## 96 1846.3 38.71 0
## 80 1875.2 67.67 0
## 94 1900.4 92.78 0
## 78 1926.5 118.90 0
## 64 1928.9 121.34 0
## 48 1954.2 146.62 0
## 32 1959.6 152.05 0
## 16 1983.3 175.77 0
## 60 1984.5 176.92 0
## 30 2003.7 196.15 0
## 44 2007.4 199.77 0
## 28 2012.0 204.40 0
## 8 2020.2 212.62 0
## 14 2025.5 217.88 0
## 12 2033.5 225.96 0
## 26 2051.9 244.37 0
## 6 2059.4 251.86 0
## 4 2067.3 259.70 0
## 10 2071.8 264.26 0
## 2 2103.1 295.57 0
## 111 2266.2 458.59 0
## 79 2281.4 473.80 0
## 77 2305.2 497.66 0
## 47 2324.9 517.30 0
## 15 2338.1 530.52 0
## 43 2353.3 545.77 0
## 7 2358.0 550.41 0
## 13 2359.3 551.70 0
## 11 2365.7 558.08 0
## 5 2378.2 570.67 0
## 3 2384.5 576.95 0
## 9 2385.6 578.01 0
## 1 2403.6 596.04 0
## Models ranked by AICc(x)
#checando os modelos
check_distribution(model_int_div0)
## # Distribution of Model Family
##
## Predicted Distribution of Residuals
##
## Distribution Probability
## normal 69%
## tweedie 22%
## weibull 9%
##
## Predicted Distribution of Response
##
## Distribution Probability
## tweedie 41%
## chi 31%
## weibull 22%
check_distribution(model_int_div1)
## # Distribution of Model Family
##
## Predicted Distribution of Residuals
##
## Distribution Probability
## normal 69%
## tweedie 25%
## weibull 6%
##
## Predicted Distribution of Response
##
## Distribution Probability
## tweedie 47%
## chi 16%
## gamma 12%
check_distribution(model_int_div2)
## # Distribution of Model Family
##
## Predicted Distribution of Residuals
##
## Distribution Probability
## normal 69%
## tweedie 19%
## weibull 9%
##
## Predicted Distribution of Response
##
## Distribution Probability
## tweedie 50%
## weibull 12%
## exponential 9%
check_model(model_int_div0) # autaorrelaĆ§Ć£o entre ano e plot indica realmente um efeito conjunto dos dois
check_model(model_int_div1)
check_model(model_int_div2)
# autaorrelaĆ§Ć£o entre ano e plot indica realmente um efeito conjunto dos dois
# modelos finais (resultado)
fin_mod_int_div0<-glm(div0~yr+frag_cat+yr*origen+yr*disp_mode, data = div_data_geral, family = "gaussian",
na.action = "na.fail")
summary(fin_mod_int_div0)
##
## Call:
## glm(formula = div0 ~ yr + frag_cat + yr * origen + yr * disp_mode,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -12.7825 -0.7744 0.0221 1.4063 7.2015
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.9718 0.2962 16.785 < 2e-16 ***
## yr2007 -2.6166 0.3420 -7.651 8.02e-14 ***
## frag_catlarge -0.9892 0.2793 -3.542 0.000428 ***
## frag_catmedium 0.8026 0.2793 2.874 0.004197 **
## frag_catsmall -0.2731 0.2793 -0.978 0.328540
## origennd -1.3931 0.2793 -4.989 7.98e-07 ***
## disp_modezoo 8.0082 0.2793 28.677 < 2e-16 ***
## yr2007:origennd 2.2756 0.3949 5.762 1.33e-08 ***
## yr2007:disp_modezoo -2.1253 0.3949 -5.381 1.06e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 5.926767)
##
## Null deviance: 12492.7 on 607 degrees of freedom
## Residual deviance: 3550.1 on 599 degrees of freedom
## AIC: 2818.3
##
## Number of Fisher Scoring iterations: 2
dredge(fin_mod_int_div0, evaluate = TRUE, rank = "AICc", fixed = NULL, trace = TRUE)
## 0 : glm(formula = div0 ~ 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 1 : glm(formula = div0 ~ disp_mode + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 2 : glm(formula = div0 ~ frag_cat + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 3 : glm(formula = div0 ~ disp_mode + frag_cat + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 4 : glm(formula = div0 ~ origen + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 5 : glm(formula = div0 ~ disp_mode + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 6 : glm(formula = div0 ~ frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 7 : glm(formula = div0 ~ disp_mode + frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 8 : glm(formula = div0 ~ yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 9 : glm(formula = div0 ~ disp_mode + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 10 : glm(formula = div0 ~ frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 11 : glm(formula = div0 ~ disp_mode + frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 12 : glm(formula = div0 ~ origen + yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 13 : glm(formula = div0 ~ disp_mode + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 14 : glm(formula = div0 ~ frag_cat + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 15 : glm(formula = div0 ~ disp_mode + frag_cat + origen + yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 25 : glm(formula = div0 ~ disp_mode + yr + disp_mode:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 27 : glm(formula = div0 ~ disp_mode + frag_cat + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 29 : glm(formula = div0 ~ disp_mode + origen + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 31 : glm(formula = div0 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 44 : glm(formula = div0 ~ origen + yr + origen:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 45 : glm(formula = div0 ~ disp_mode + origen + yr + origen:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 46 : glm(formula = div0 ~ frag_cat + origen + yr + origen:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 47 : glm(formula = div0 ~ disp_mode + frag_cat + origen + yr + origen:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 61 : glm(formula = div0 ~ disp_mode + origen + yr + disp_mode:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 63 : glm(formula = div0 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## Global model call: glm(formula = div0 ~ yr + frag_cat + yr * origen + yr * disp_mode,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## ---
## Model selection table
## (Int) dsp_mod frg_cat org yr dsp_mod:yr org:yr df logLik AICc delta
## 64 4.972 + + + + + + 10 -1399.143 2818.7 0.00
## 48 5.503 + + + + + 9 -1413.496 2845.3 26.64
## 28 4.275 + + + + 8 -1416.345 2848.9 30.28
## 32 4.403 + + + + + 9 -1415.542 2849.4 30.73
## 62 4.857 + + + + + 7 -1419.826 2853.8 35.18
## 12 4.807 + + + 7 -1429.926 2874.0 55.38
## 16 4.934 + + + + 8 -1429.158 2874.6 55.90
## 46 5.388 + + + + 6 -1433.255 2878.7 60.00
## 26 4.160 + + + 5 -1435.926 2882.0 63.30
## 30 4.288 + + + + 6 -1435.173 2882.5 63.83
## 10 4.692 + + 4 -1448.677 2905.4 86.77
## 14 4.819 + + + 5 -1447.956 2906.0 87.36
## 4 3.536 + + 6 -1497.742 3007.6 188.97
## 8 3.663 + + + 7 -1497.128 3008.4 189.79
## 2 3.421 + 3 -1512.835 3031.7 213.06
## 6 3.549 + + 4 -1512.251 3032.6 213.92
## 47 8.976 + + + + 8 -1744.436 3505.1 686.46
## 11 8.279 + + 6 -1750.067 3512.3 693.62
## 45 8.861 + + + 5 -1751.233 3512.6 693.91
## 15 8.407 + + + 7 -1749.800 3513.8 695.13
## 9 8.164 + 3 -1756.741 3519.5 700.87
## 13 8.292 + + 4 -1756.479 3521.0 702.37
## 3 7.009 + 5 -1775.479 3561.1 742.40
## 7 7.136 + + 6 -1775.233 3562.6 743.95
## 1 6.894 2 -1781.623 3567.3 748.61
## 5 7.021 + 3 -1781.382 3568.8 750.15
## weight
## 64 1
## 48 0
## 28 0
## 32 0
## 62 0
## 12 0
## 16 0
## 46 0
## 26 0
## 30 0
## 10 0
## 14 0
## 4 0
## 8 0
## 2 0
## 6 0
## 47 0
## 11 0
## 45 0
## 15 0
## 9 0
## 13 0
## 3 0
## 7 0
## 1 0
## 5 0
## Models ranked by AICc(x)
fin_mod_int_div1<-glm(div1~yr+frag_cat+yr*origen+yr*disp_mode, data = div_data_geral, family = "gaussian",
na.action = "na.fail")
summary(fin_mod_int_div1)
##
## Call:
## glm(formula = div1 ~ yr + frag_cat + yr * origen + yr * disp_mode,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.5768 -0.7534 0.0568 0.8437 3.5772
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.5165 0.1672 21.035 < 2e-16 ***
## yr2007 -1.4928 0.1930 -7.733 4.47e-14 ***
## frag_catlarge -0.5066 0.1576 -3.214 0.001379 **
## frag_catmedium -0.5938 0.1576 -3.768 0.000181 ***
## frag_catsmall 0.1745 0.1576 1.107 0.268630
## origennd -2.1987 0.1576 -13.950 < 2e-16 ***
## disp_modezoo 3.8858 0.1576 24.654 < 2e-16 ***
## yr2007:origennd 2.3934 0.2229 10.738 < 2e-16 ***
## yr2007:disp_modezoo -1.3482 0.2229 -6.048 2.58e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 1.888037)
##
## Null deviance: 3345.9 on 607 degrees of freedom
## Residual deviance: 1130.9 on 599 degrees of freedom
## AIC: 2122.8
##
## Number of Fisher Scoring iterations: 2
dredge(fin_mod_int_div1, evaluate = TRUE, rank = "AICc", fixed = NULL, trace = TRUE)
## 0 : glm(formula = div1 ~ 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 1 : glm(formula = div1 ~ disp_mode + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 2 : glm(formula = div1 ~ frag_cat + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 3 : glm(formula = div1 ~ disp_mode + frag_cat + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 4 : glm(formula = div1 ~ origen + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 5 : glm(formula = div1 ~ disp_mode + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 6 : glm(formula = div1 ~ frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 7 : glm(formula = div1 ~ disp_mode + frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 8 : glm(formula = div1 ~ yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 9 : glm(formula = div1 ~ disp_mode + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 10 : glm(formula = div1 ~ frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 11 : glm(formula = div1 ~ disp_mode + frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 12 : glm(formula = div1 ~ origen + yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 13 : glm(formula = div1 ~ disp_mode + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 14 : glm(formula = div1 ~ frag_cat + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 15 : glm(formula = div1 ~ disp_mode + frag_cat + origen + yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 25 : glm(formula = div1 ~ disp_mode + yr + disp_mode:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 27 : glm(formula = div1 ~ disp_mode + frag_cat + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 29 : glm(formula = div1 ~ disp_mode + origen + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 31 : glm(formula = div1 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 44 : glm(formula = div1 ~ origen + yr + origen:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 45 : glm(formula = div1 ~ disp_mode + origen + yr + origen:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 46 : glm(formula = div1 ~ frag_cat + origen + yr + origen:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 47 : glm(formula = div1 ~ disp_mode + frag_cat + origen + yr + origen:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 61 : glm(formula = div1 ~ disp_mode + origen + yr + disp_mode:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 63 : glm(formula = div1 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## Global model call: glm(formula = div1 ~ yr + frag_cat + yr * origen + yr * disp_mode,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## ---
## Model selection table
## (Int) dsp_mod frg_cat org yr dsp_mod:yr org:yr df logLik AICc delta
## 64 3.516 + + + + + + 10 -1051.384 2123.1 0.00
## 62 3.285 + + + + + 7 -1068.287 2150.8 27.62
## 48 3.854 + + + + + 9 -1069.405 2157.1 33.97
## 46 3.622 + + + + 6 -1085.359 2182.9 59.72
## 32 2.918 + + + + + 9 -1104.899 2228.1 104.96
## 30 2.687 + + + + 6 -1119.136 2250.4 127.28
## 16 3.255 + + + + 8 -1120.082 2256.4 133.27
## 14 3.024 + + + 5 -1133.641 2277.4 154.24
## 28 2.417 + + + + 8 -1137.488 2291.2 168.08
## 26 2.186 + + + 5 -1150.308 2310.7 187.58
## 8 2.770 + + + 7 -1149.307 2312.8 189.66
## 12 2.754 + + + 7 -1151.162 2316.5 193.37
## 6 2.539 + + 4 -1161.648 2331.4 208.22
## 10 2.523 + + 4 -1163.429 2334.9 211.79
## 4 2.269 + + 6 -1177.667 2367.5 244.34
## 2 2.038 + 3 -1188.928 2383.9 260.76
## 47 5.459 + + + + 8 -1323.477 2663.2 540.06
## 45 5.228 + + + 5 -1330.497 2671.1 547.96
## 15 4.861 + + + 7 -1346.492 2707.2 584.03
## 13 4.630 + + 4 -1353.005 2714.1 590.94
## 7 4.376 + + 6 -1360.720 2733.6 610.44
## 11 4.360 + + 6 -1361.646 2735.4 612.30
## 5 4.144 + 3 -1366.939 2739.9 616.78
## 9 4.129 + 3 -1367.846 2741.7 618.60
## 3 3.875 + 5 -1375.198 2760.5 637.36
## 1 3.643 2 -1381.130 2766.3 643.14
## weight
## 64 1
## 62 0
## 48 0
## 46 0
## 32 0
## 30 0
## 16 0
## 14 0
## 28 0
## 26 0
## 8 0
## 12 0
## 6 0
## 10 0
## 4 0
## 2 0
## 47 0
## 45 0
## 15 0
## 13 0
## 7 0
## 11 0
## 5 0
## 9 0
## 3 0
## 1 0
## Models ranked by AICc(x)
fin_mod_int_div2<-glm(div2~yr+frag_cat+yr*origen+yr*disp_mode, data = div_data_geral, family = "gaussian",
na.action = "na.fail")
summary(fin_mod_int_div2)
##
## Call:
## glm(formula = div2 ~ yr + frag_cat + yr * origen + yr * disp_mode,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.7268 -0.6805 0.0862 0.6573 3.8182
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.8591 0.1331 21.475 < 2e-16 ***
## yr2007 -1.1232 0.1537 -7.306 8.82e-13 ***
## frag_catlarge -0.2693 0.1255 -2.146 0.0323 *
## frag_catmedium -0.7424 0.1255 -5.915 5.59e-09 ***
## frag_catsmall 0.1907 0.1255 1.519 0.1292
## origennd -1.7240 0.1255 -13.735 < 2e-16 ***
## disp_modezoo 2.6770 0.1255 21.327 < 2e-16 ***
## yr2007:origennd 1.9864 0.1775 11.190 < 2e-16 ***
## yr2007:disp_modezoo -0.9942 0.1775 -5.601 3.26e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 1.197441)
##
## Null deviance: 1842.72 on 607 degrees of freedom
## Residual deviance: 717.27 on 599 degrees of freedom
## AIC: 1845.9
##
## Number of Fisher Scoring iterations: 2
dredge(fin_mod_int_div2, evaluate = TRUE, rank = "AICc", fixed = NULL, trace = TRUE)
## 0 : glm(formula = div2 ~ 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 1 : glm(formula = div2 ~ disp_mode + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 2 : glm(formula = div2 ~ frag_cat + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 3 : glm(formula = div2 ~ disp_mode + frag_cat + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 4 : glm(formula = div2 ~ origen + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 5 : glm(formula = div2 ~ disp_mode + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 6 : glm(formula = div2 ~ frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 7 : glm(formula = div2 ~ disp_mode + frag_cat + origen + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 8 : glm(formula = div2 ~ yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 9 : glm(formula = div2 ~ disp_mode + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 10 : glm(formula = div2 ~ frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 11 : glm(formula = div2 ~ disp_mode + frag_cat + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 12 : glm(formula = div2 ~ origen + yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 13 : glm(formula = div2 ~ disp_mode + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 14 : glm(formula = div2 ~ frag_cat + origen + yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 15 : glm(formula = div2 ~ disp_mode + frag_cat + origen + yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 25 : glm(formula = div2 ~ disp_mode + yr + disp_mode:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 27 : glm(formula = div2 ~ disp_mode + frag_cat + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 29 : glm(formula = div2 ~ disp_mode + origen + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 31 : glm(formula = div2 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 44 : glm(formula = div2 ~ origen + yr + origen:yr + 1, family = "gaussian",
## data = div_data_geral, na.action = "na.fail")
## 45 : glm(formula = div2 ~ disp_mode + origen + yr + origen:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 46 : glm(formula = div2 ~ frag_cat + origen + yr + origen:yr + 1,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 47 : glm(formula = div2 ~ disp_mode + frag_cat + origen + yr + origen:yr +
## 1, family = "gaussian", data = div_data_geral, na.action = "na.fail")
## 61 : glm(formula = div2 ~ disp_mode + origen + yr + disp_mode:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## 63 : glm(formula = div2 ~ disp_mode + frag_cat + origen + yr + disp_mode:yr +
## origen:yr + 1, family = "gaussian", data = div_data_geral,
## na.action = "na.fail")
## Global model call: glm(formula = div2 ~ yr + frag_cat + yr * origen + yr * disp_mode,
## family = "gaussian", data = div_data_geral, na.action = "na.fail")
## ---
## Model selection table
## (Int) dsp_mod frg_cat org yr dsp_mod:yr org:yr df logLik AICc delta
## 64 2.859 + + + + + + 10 -912.958 1846.3 0.00
## 48 3.108 + + + + + 9 -928.474 1875.2 28.96
## 62 2.654 + + + + + 7 -943.084 1900.4 54.07
## 46 2.902 + + + + 6 -957.169 1926.5 80.19
## 32 2.363 + + + + + 9 -970.664 1959.6 113.35
## 16 2.611 + + + + 8 -983.554 1983.3 137.06
## 30 2.157 + + + + 6 -995.791 2003.7 157.44
## 28 1.997 + + + + 8 -997.868 2012.0 165.69
## 8 2.298 + + + 7 -1003.003 2020.2 173.91
## 14 2.406 + + + 5 -1007.677 2025.5 179.17
## 12 2.246 + + + 7 -1009.676 2033.5 187.25
## 26 1.792 + + + 5 -1020.923 2051.9 205.66
## 6 2.092 + + 4 -1025.685 2059.4 213.15
## 4 1.932 + + 6 -1027.569 2067.3 220.99
## 10 2.040 + + 4 -1031.884 2071.8 225.55
## 2 1.727 + 3 -1048.550 2103.1 256.86
## 47 4.198 + + + + 8 -1132.566 2281.4 435.09
## 45 3.992 + + + 5 -1147.568 2305.2 458.95
## 15 3.701 + + + 7 -1161.956 2338.1 491.82
## 7 3.387 + + 6 -1172.924 2358.0 511.70
## 13 3.496 + + 4 -1175.606 2359.3 512.99
## 11 3.336 + + 6 -1176.758 2365.7 519.37
## 5 3.182 + 3 -1186.101 2378.2 531.96
## 3 3.022 + 5 -1187.214 2384.5 538.24
## 9 3.130 + 3 -1189.773 2385.6 539.30
## 1 2.817 2 -1199.798 2403.6 557.33
## weight
## 64 1
## 48 0
## 62 0
## 46 0
## 32 0
## 16 0
## 30 0
## 28 0
## 8 0
## 14 0
## 12 0
## 26 0
## 6 0
## 4 0
## 10 0
## 2 0
## 47 0
## 45 0
## 15 0
## 7 0
## 13 0
## 11 0
## 5 0
## 3 0
## 9 0
## 1 0
## Models ranked by AICc(x)