画一个带统计检验的PcOA分析结果 （再进一步，配对比较）

前期回顾

方差分析基本概念：方差分析中的“元”和“因素”是什么？

PERMANOVA原理解释：这个统计检验可用于判断PCA/PCoA等的分群效果是否显著！

实战1：画一个带统计检验的PCoA分析结果

在检验完某个因素对物种组成有显著影响后，如果关注该因素不同水平对物种的构成是否存在显著影响，就需要逐一对每两对水平进行检验了。

配对Adonis确定不同管理方式两两之间对物种组成差异的影响

adonis分析可以检验某个因素整体对物种组成差异的影响，但不能比较这个因素的多个水平之间两两是否差异显著，如Management中的BF与HM两种方式是否对物种组成差异有显著影响？

这时就需要pairwise.adonis来进行配对检验了。

# devtools::install_github("pmartinezarbizu/pairwiseAdonis/pairwiseAdonis")
library(pairwiseAdonis)

# This is a wrapper function for multilevel pairwise comparison 
# using adonis() from package 'vegan'. 
# The function returns adjusted p-values using p.adjust().
dune.pairwise.adonis <- pairwise.adonis(x=dune, factors=dune.env$Management, sim.function = "vegdist",
  sim.method = "bray",
  p.adjust.m = "BH",
  reduce = NULL,
  perm = 999)

dune.pairwise.adonis

##      pairs Df SumsOfSqs  F.Model        R2 p.value p.adjusted sig
## 1 SF vs BF  1 0.4016624 2.514890 0.2643110   0.055     0.0825    
## 2 SF vs HF  1 0.2828804 1.857489 0.1710790   0.117     0.1404    
## 3 SF vs NM  1 0.7575728 3.425694 0.2551595   0.008     0.0480   .
## 4 BF vs HF  1 0.1617135 1.567531 0.2071390   0.197     0.1970    
## 5 BF vs NM  1 0.5662456 2.715242 0.2794827   0.017     0.0510    
## 6 HF vs NM  1 0.6513088 3.423068 0.2755413   0.031     0.0620

拼一起画个图

library(ggpubr)
library(patchwork)
tab2 <- ggtexttable(dune.pairwise.adonis[,c("pairs","R2","p.value","p.adjusted")], rows = NULL, 
                    theme = ttheme("blank")) %>% 
  tab_add_hline(at.row = 1:2, row.side = "top", linewidth = 1)  %>% 
  tab_add_hline(at.row = nrow(dune.pairwise.adonis)+1, row.side = "bottom", linewidth = 1)  

p2 = p + tab2 
p2

p2 + plot_layout(design=c(area(1,1), area(2,1)))
# p / tab2
# 调布局

ANOSIM和PERMANOVA的pairwise analysis声明：“Pairwise tests are not possible in vegan. My understanding is that the non-R software with such tests makes separate pairwise tests using subsets of data with only two levels of a factor in one test. We don’t provide that in vegan and have no plans to provide this in the future.” (cited by Jari Oksanen, author of anosim and Adonis{vegan} in R)https://stat.ethz.ch/pipermail/r-sig-ecology/2013-June/003865.html

参考

1. https://www.scribbr.com/frequently-asked-questions/one-way-vs-two-way-anova/
2. MANOVA的前提假设 https://www.real-statistics.com/multivariate-statistics/multivariate-analysis-of-variance-manova/manova-assumptions/ https://www.statology.org/manova-assumptions/
3. https://statistics.laerd.com/statistical-guides/one-way-anova-statistical-guide.php
4. https://chrischizinski.github.io/rstats/vegan-ggplot2/
5. https://chrischizinski.github.io/rstats/adonis/
6. https://chrischizinski.github.io/rstats/ordisurf/
7. https://www.rdocumentation.org/packages/vegan/versions/1.11-0/topics/adonis
8. https://stats.stackexchange.com/questions/312302/adonis-in-vegan-order-of-variables-non-nested-with-one-degree-of-freedom-for
9. https://stats.stackexchange.com/questions/188519/adonis-in-vegan-order-of-variables-or-use-of-strata?noredirect=1
10. https://github.com/vegandevs/vegan/issues/229
11. https://stats.stackexchange.com/questions/476256/adonis-vs-adonis2
12. 清晰解释Type I, Type II, Type III https://mcfromnz.wordpress.com/2011/03/02/anova-type-iiiiii-ss-explained/
13. 清晰解释Type I, Type II, Type III https://stats.stackexchange.com/questions/60362/choice-between-type-i-type-ii-or-type-iii-anova
14. https://thebiobucket.blogspot.com/2011/08/two-way-permanova-adonis-with-custom.html#more
15. adonis的前提条件 https://thebiobucket.blogspot.com/2011/04/assumptions-for-permanova-with-adonis.html#more
16. 作者的论文 https://static1.squarespace.com/static/580e3c475016e191c523a0e2/t/5813ba8b5016e1a5b61f454a/1477687949842/Anderson_et_al-2013-ANOSIM+vs.+PERMANOVA.pdf