t、 基于R中的两组不同因素跨数据帧进行测试

我有一个变量的数据框，记录在两个位置的11种植物。对于每一种物种，我试图使用t检验（或wilcoxon检验）比较两个不同位置的变量平均值

下面是我的数据的前几行

 SPECIES   LOCATION X.COLONIZATION SPORE_DENSITY   pH  NO3  NH4    P Organic_C      K   Cu    Mn   Zn   BD X.Sand
1   C. comosa    Gauteng             90           387 5.40 8.24 1.35 1.10      0.95  94.40 3.36 84.40 4.72 1.45   68.0
2   C. comosa    Gauteng             84           270 5.25 8.36 1.37 1.20      0.99  94.87 3.39 84.87 4.77 1.36   76.0
3   C. comosa    Gauteng             96           404 5.55 8.19 1.32 1.11      0.94  94.01 3.35 84.01 4.68 1.54   78.0
4   C. comosa Mpumalanga             79           382 5.84 4.05 3.46 3.04      1.55 130.40 0.28 25.43 2.00 1.66   73.6
5   C. comosa Mpumalanga             82           383 5.49 4.45 3.48 3.09      1.53 131.36 0.27 25.35 2.12 1.45   76.5
6   C. comosa Mpumalanga             86           371 6.19 4.43 3.44 3.04      1.58 129.95 0.29 25.45 2.14 1.87   74.9
7  C. distans    Gauteng             80           334 5.48 8.88 1.96 3.33      0.99 130.24 0.99 40.01 3.94 1.55   70.0
8  C. distans    Gauteng             75           409 5.29 8.54 1.99 3.28      0.99 130.28 0.95 40.25 3.89 1.48   79.0
9  C. distans    Gauteng             85           259 5.67 8.63 1.93 3.39      1.02 130.30 0.98 40.12 3.97 1.62   79.0
10 C. distans Mpumalanga             65           326 5.61 6.02 2.65 4.45      2.58 163.25 1.79 53.11 6.11 1.68   72.0
11 C. distans Mpumalanga             79           351 5.43 6.58 2.55 4.49      2.59 163.55 1.78 52.89 6.04 1.63   78.0
12 C. distans Mpumalanga             71           251 5.79 6.24 2.59 4.41      2.59 163.27 1.75 53.03 6.19 1.73   75.0
   X.Silt X.Clay
1      12      9
2      16     13
3      14     14
4       9     10
5      11     16
6      13     16
7       8     11
8      12     15
9      10     16
10      8     10
11     15     14
12     16     12

---

例如，对于每个物种，我想比较（检验显著差异）Gauteng和Mpumalanga中孢子密度的平均值。有什么帮助吗？

我们按“物种”分组，然后在数字列上使用

汇总
和
交叉
，将列值子集为“LOCATION”是“Gauteng”或另一个，应用
t.test
并提取pvalue

library(dplyr) #1.0.0
df1 %>%
    group_by(SPECIES) %>%
    summarise(across(where(is.numeric), ~ 
         t.test(.[LOCATION == 'Gauteng'], .[LOCATION == 'Mpumalanga'])$p.value))
# A tibble: 2 x 16
#  SPECIES   X.COLONIZATION SPORE_DENSITY    pH      NO3        NH4        P  Organic_C        K       Cu        Mn       Zn     BD X.Sand X.Silt X.Clay
#  <chr>              <dbl>         <dbl> <dbl>    <dbl>      <dbl>    <dbl>      <dbl>    <dbl>    <dbl>     <dbl>    <dbl>  <dbl>  <dbl>  <dbl>  <dbl>
#1 C. comosa          0.146         0.614 0.149 0.000269    7.27e-8  1.35e-5 0.00000970  2.15e-6  3.12e-7   1.35e-5  7.23e-6 0.219   0.779  0.140  0.474
#2 C. dista…          0.177         0.667 0.438 0.000624    1.94e-4  2.04e-5 0.00000670  4.48e-6  1.22e-6   1.90e-8  2.07e-5 0.0653  0.791  0.363  0.359

library（dplyr）#1.0.0
df1%>%
组别(种类)%>%
总结（跨越（其中（是数字），~
t、 测试（[LOCATION=='Gauteng']，[LOCATION=='Mpumalanga']）$p.value））
#一个tibble:2x16
#物种X.定殖孢子密度pH NO3 NH4 P有机碳K Cu Mn Zn BD X.沙X.粉土X.粘土
#                                                                       
#1 C.科摩萨0.146 0.614 0.149 0.000269 7.27e-8 1.35e-5 0.00000970 2.15e-6 3.12e-7 1.35e-5 7.23e-6 0.219 0.779 0.140 0.474
#2 C区…0.177 0.667 0.438 0.000624 1.94e-4 2.04e-5 0.00000670 4.48e-6 1.22e-6 1.90e-8 2.07e-5 0.0653 0.791 0.363 0.359

数据
df1
df1 <- structure(list(SPECIES = c("C. comosa", "C. comosa", "C. comosa", 
"C. comosa", "C. comosa", "C. comosa", "C. distans", "C. distans", 
"C. distans", "C. distans", "C. distans", "C. distans"), LOCATION = c("Gauteng", 
"Gauteng", "Gauteng", "Mpumalanga", "Mpumalanga", "Mpumalanga", 
"Gauteng", "Gauteng", "Gauteng", "Mpumalanga", "Mpumalanga", 
"Mpumalanga"), X.COLONIZATION = c(90L, 84L, 96L, 79L, 82L, 86L, 
80L, 75L, 85L, 65L, 79L, 71L), SPORE_DENSITY = c(387L, 270L, 
404L, 382L, 383L, 371L, 334L, 409L, 259L, 326L, 351L, 251L), 
    pH = c(5.4, 5.25, 5.55, 5.84, 5.49, 6.19, 5.48, 5.29, 5.67, 
    5.61, 5.43, 5.79), NO3 = c(8.24, 8.36, 8.19, 4.05, 4.45, 
    4.43, 8.88, 8.54, 8.63, 6.02, 6.58, 6.24), NH4 = c(1.35, 
    1.37, 1.32, 3.46, 3.48, 3.44, 1.96, 1.99, 1.93, 2.65, 2.55, 
    2.59), P = c(1.1, 1.2, 1.11, 3.04, 3.09, 3.04, 3.33, 3.28, 
    3.39, 4.45, 4.49, 4.41), Organic_C = c(0.95, 0.99, 0.94, 
    1.55, 1.53, 1.58, 0.99, 0.99, 1.02, 2.58, 2.59, 2.59), K = c(94.4, 
    94.87, 94.01, 130.4, 131.36, 129.95, 130.24, 130.28, 130.3, 
    163.25, 163.55, 163.27), Cu = c(3.36, 3.39, 3.35, 0.28, 0.27, 
    0.29, 0.99, 0.95, 0.98, 1.79, 1.78, 1.75), Mn = c(84.4, 84.87, 
    84.01, 25.43, 25.35, 25.45, 40.01, 40.25, 40.12, 53.11, 52.89, 
    53.03), Zn = c(4.72, 4.77, 4.68, 2, 2.12, 2.14, 3.94, 3.89, 
    3.97, 6.11, 6.04, 6.19), BD = c(1.45, 1.36, 1.54, 1.66, 1.45, 
    1.87, 1.55, 1.48, 1.62, 1.68, 1.63, 1.73), X.Sand = c(68, 
    76, 78, 73.6, 76.5, 74.9, 70, 79, 79, 72, 78, 75), X.Silt = c(12L, 
    16L, 14L, 9L, 11L, 13L, 8L, 12L, 10L, 8L, 15L, 16L), X.Clay = c(9L, 
    13L, 14L, 10L, 16L, 16L, 11L, 15L, 16L, 10L, 14L, 12L)), class = "data.frame", row.names = c("1", 
"2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12"))