G * t(hat) 中的错误：不一致的数组

Question

尝试在 R 中使用 adonis 执行 PERMANOVA。添加到我的数据表和因子中，但是，我不断收到示例错误 - G * t(hat) 中的错误：不合格数组

没有 N/A 数据，它适用于现成的数据矩阵和我自己的数据表的子集。

无效的样本数据；

subset<-matrix(c(0,0.000666667,0.001333333,0.000333333,0.000333333,0.019833333,0.007666667,0.014666667,0.0005,0.022833333,0.016833333,0.018166667,0.000666667,0.009666667,0.008833333,0.009166667,0.001333333,0.018666667,0.0295,0.031833333),ncol=4)

test_groups<-c(1,1,2,2)
adonis(subset~test_groups)

G * t(hat) 中的错误：不一致的数组

有效的测试数据；

test<-matrix(data=c(0.1,0.1,0.3,0.1,0.2,0.3,0.1,0,0.3,0.1,0.2,0.3,0.1,0.2,0.3,0.1),ncol=4)

为什么它不起作用？

Answer 1

test_groups 向量的长度为 4，而subset 的行数为 5。
下面我将subset 的行数设置为5，adonis 命令运行良好。

library(vegan) 
subset <- matrix(c(0,0.000666667,0.001333333,0.000333333,0.000333333,0.019833333,0.007666667,0.014666667,0.0005,0.022833333,0.016833333,0.018166667,0.000666667,0.009666667,0.008833333,0.009166667,0.001333333,0.018666667,0.0295,0.031833333),ncol=5)
test_groups <- c(1,1,2,2)     
adonis(subset~test_groups)

这是结果。

'nperm' >= set of all permutations: complete enumeration.
Set of permutations < 'minperm'. Generating entire set.

Call:
adonis(formula = subset ~ test_groups) 

Permutation: free
Number of permutations: 23

Terms added sequentially (first to last)

            Df SumsOfSqs MeanSqs F.Model      R2 Pr(>F)
test_groups  1   0.22804 0.22804  1.0592 0.34624 0.3333
Residuals    2   0.43059 0.21530         0.65376       
Total        3   0.65864                 1.00000