Error in R t_test , not enough "x" observations

Question

I am trying to conduct group-wise t-test , but the code i am using returnign an error. It has worked alright for me previously and on other data frame but for this data frame its giving this error

Error in t.test.default(x = 0.0268, y = 0.0223, paired = FALSE, var.equal = FALSE, : not enough 'x' observations

My Code is

stat.test.BACI5 <- Flaov %>%
  group_by(`Treatment`) %>%
  t_test(`Observed` ~  Control,  detailed = TRUE) %>%
  adjust_pvalue(method = "bonferroni") %>%
  add_significance()  

Here is the data structure

structure(list(Treatment = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L
), .Label = c("Phase1", "Phase2"), class = "factor"), Group = structure(c(3L, 
4L, 2L, 3L, 2L, 4L, 1L, 2L, 4L, 3L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 
1L, 2L, 1L, 1L, 1L, 4L, 2L, 3L, 2L, 4L, 3L, 1L, 2L, 4L, 1L, 3L, 
1L, 1L, 1L, 2L, 1L, 3L, 2L, 1L, 2L, 3L, 1L, 1L, 1L, 2L, 2L, 2L, 
4L, 2L, 1L, 1L, 1L, 4L, 1L, 3L, 1L, 3L, 4L, 2L, 1L, 1L, 2L, 4L, 
2L, 3L, 1L, 1L, 2L), .Label = c("Group A ", "Group B", "Group C ", 
"Group D"), class = "factor"), Observed = c(0.1057, 0.151, 0.0576, 
0.1267, 0.0941, 0.1554, 0.0247, 0.0832, 0.2807, 0.1137, 0.0325, 
0.0777, 0.0362, 0.0637, 0.0303, 0.0223, 0.0932, 0.0363, 0.0641, 
0.0453, 0.0359, 0.0334, 0.2006, 0.0538, 0.1114, 0.0661, 0.2452, 
0.1043, 0.0489, 0.0663, 0.1967, 0.0321, 0.1042, 0.0268, 0.0313, 
0.0255, 0.0787, 0.038, 0.1212, 0.0839, 0.0446, 0.0986, 0.1364, 
0.0335, 0.0409, 0.0407, 0.0871, 0.0584, 0.0875, 0.1961, 0.0711, 
0.0191, 0.0363, 0.0474, 0.1608, 0.0349, 0.1099, 0.0399, 0.1095, 
0.2011, 0.057, 0.0418, 0.0394, 0.054, 0.2033, 0.0631, 0.1089, 
0.0441, 0.0261, 0.0686), Control = c(0.1061, 0.154, 0.0585, 0.1289, 
0.1076, 0.15856, 0.02997, 0.1022, 0.2849, 0.1193, 0.03292, 0.0888, 
0.04628, 0.06454, 0.03341, 0.0239, 0.1013, 0.0364, 0.0883, 0.06363, 
0.0566, 0.04036, 0.20641, 0.06206, 0.1158, 0.0687, 0.2457, 0.12643, 
0.05126, 0.05705, 0.1987, 0.04719, 0.08199, 0.02312, 0.0317, 
0.07045, 0.06395, 0.06043, 0.1251, 0.0912, 0.04575, 0.1018, 0.1379, 
0.03834, 0.048, 0.04131, 0.0926, 0.06242, 0.0965, 0.1972, 0.0742, 
0.0211, 0.04318, 0.05741, 0.1616, 0.06552, 0.1104, 0.04814, 0.11015, 
0.2081, 0.06341, 0.04329, 0.04486, 0.06179, 0.2114, 0.05545, 
0.1127, 0.04327, 0.03355, 0.07189), factors = structure(c(1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L), .Label = c("Phase1", "Phase2"), class = "factor")), row.names = c(NA, 
70L), class = "data.frame")

Answer 1

If you are doing a t test between observed and control in the different treatment groups, the formula is wrong, the left hand side of the formula should be the response variable and right hand side should be grouping variable.

In your case, you need to pivot the data long to get something like this:

library(tidyr)
Flaov[,c("Treatment","Observed","Control")] %>% 
pivot_longer(-c(Treatment)) %>% group_by(Treatment)
# A tibble: 140 x 3
# Groups:   Treatment [2]
   Treatment name      value
   <fct>     <chr>     <dbl>
 1 Phase1    Observed 0.106 
 2 Phase1    Control  0.106 
 3 Phase1    Observed 0.151 
 4 Phase1    Control  0.154 
 5 Phase1    Observed 0.0576
 6 Phase1    Control  0.0585
 7 Phase1    Observed 0.127 
 8 Phase1    Control  0.129 
 9 Phase1    Observed 0.0941
10 Phase1    Control  0.108 
# … with 130 more rows

Then we further pipe it to test:

Flaov[,c("Treatment","Observed","Control")] %>% 
pivot_longer(-c(Treatment)) %>% 
group_by(Treatment) %>% 
t_test(value ~ name)

# A tibble: 2 x 9
  Treatment .y.   group1  group2      n1    n2 statistic    df     p
* <fct>     <chr> <chr>   <chr>    <int> <int>     <dbl> <dbl> <dbl>
1 Phase1    value Control Observed    46    46     0.482  90.0 0.631
2 Phase2    value Control Observed    24    24     0.323  46.0 0.748