Open Ren01230 opened 3 years ago
BastienBennetot
commented
3 years ago I have the same problem, for me it was because on some grouping there is categories that contains only zeros. A rank test like wilcoxon test would be hardly done in this configuration. It would be nice to correct the function to avoid the grouping that is causing this issues whereas some groupings may be testable
benediktclaus
commented
3 years ago Hi @Ren01230
@BastienBennetot seems to be right with his assumption. If you look at the group-wise examples below, the dependent variable for the third group is 0 in every line and a statistical test for inference doesn't make any sense in this case.
I don't think this is an issue that should be fixed by rstatix. A package can not fix all decisions made by the researcher. Instead, one could benefit from a careful exploratory data analysis and use of statistical tests only when appropriate.
library(tidyverse)
library(rstatix)
#>
#> Attache Paket: 'rstatix'
#> Das folgende Objekt ist maskiert 'package:stats':
#>
#> filter
reprex_data <- structure(list(aid = c("A1", "A2", "A3", "A4", "B1", "B2", "B3",
"B4", "C1", "C2", "C3", "C4", "D1", "D2", "D3", "D4", "E1", "E2",
"E3", "E4", "F1", "F2", "F3", "F4"), tissue = c("sp", "sp", "sp",
"sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp",
"sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp"),
group = c("A", "A", "A", "A", "B", "B", "B", "B", "C", "C",
"C", "C", "A", "A", "A", "A", "B", "B", "B", "B", "C", "C",
"C", "C"), sex = c("m", "m", "m", "m", "m", "m", "m", "m",
"m", "m", "m", "m", "f", "f", "f", "f", "f", "f", "f", "f",
"f", "f", "f", "f"), detail = c("mCD4", "mCD4", "mCD4", "mCD4",
"mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4",
"mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4",
"mCD4", "mCD4", "mCD4", "mCD4"), value = c(0, 0, 0, 0, 0,
0, 0, 0.46, 0, 0, 0, 0, 0, 0, 0, 0.31, 0, 0, 0, 0.47, 0,
0, 0, 0)), class = c("spec_tbl_df", "tbl_df", "tbl", "data.frame"
), row.names = c(NA, -24L), spec = structure(list(cols = list(
aid = structure(list(), class = c("collector_character",
"collector")), tissue = structure(list(), class = c("collector_character",
"collector")), group = structure(list(), class = c("collector_character",
"collector")), sex = structure(list(), class = c("collector_character",
"collector")), detail = structure(list(), class = c("collector_character",
"collector")), value = structure(list(), class = c("collector_double",
"collector"))), default = structure(list(), class = c("collector_guess",
"collector")), skip = 1), class = "col_spec"))
# Nest the data for quick examination
reprex_data_nested <- reprex_data %>%
group_by(group, detail) %>%
nest()
# This works just fine
reprex_data_nested %>%
pluck("data", 1) %>%
wilcox_test(value ~ sex)
#> # A tibble: 1 x 7
#> .y. group1 group2 n1 n2 statistic p
#> * <chr> <chr> <chr> <int> <int> <dbl> <dbl>
#> 1 value f m 4 4 10 0.453
# This one as well
reprex_data_nested %>%
pluck("data", 2) %>%
wilcox_test(value ~ sex)
#> # A tibble: 1 x 7
#> .y. group1 group2 n1 n2 statistic p
#> * <chr> <chr> <chr> <int> <int> <dbl> <dbl>
#> 1 value f m 4 4 8.5 1
# Here, the error occurs
reprex_data_nested %>%
pluck("data", 3) %>%
wilcox_test(value ~ sex)
#> Error in if (f.lower <= 0) return(mumin): Fehlender Wert, wo TRUE/FALSE nötig ist
# As can be seen, all values are 0
reprex_data_nested %>%
pluck("data", 3)
#> # A tibble: 8 x 4
#> aid tissue sex value
#> <chr> <chr> <chr> <dbl>
#> 1 C1 sp m 0
#> 2 C2 sp m 0
#> 3 C3 sp m 0
#> 4 C4 sp m 0
#> 5 F1 sp f 0
#> 6 F2 sp f 0
#> 7 F3 sp f 0
#> 8 F4 sp f 0Created on 2021-10-06 by the reprex package (v2.0.1)
statistical test run
error
Error: Problem with mutate() input data. x missing value where TRUE/FALSE needed :information_source: Input data is map(.data$data, .f, ...).
data for reference
dput(spleen) structure(list(aid = c("A1", "A2", "A3", "A4", "B1", "B2", "B3", "B4", "C1", "C2", "C3", "C4", "D1", "D2", "D3", "D4", "E1", "E2", "E3", "E4", "F1", "F2", "F3", "F4"), tissue = c("sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp", "sp"), group = c("A", "A", "A", "A", "B", "B", "B", "B", "C", "C", "C", "C", "A", "A", "A", "A", "B", "B", "B", "B", "C", "C", "C", "C"), sex = c("m", "m", "m", "m", "m", "m", "m", "m", "m", "m", "m", "m", "f", "f", "f", "f", "f", "f", "f", "f", "f", "f", "f", "f"), detail = c("mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4", "mCD4"), value = c(0, 0, 0, 0, 0, 0, 0, 0.46, 0, 0, 0, 0, 0, 0, 0, 0.31, 0, 0, 0, 0.47, 0, 0, 0, 0)), class = c("spec_tbl_df", "tbl_df", "tbl", "data.frame" ), row.names = c(NA, -24L), spec = structure(list(cols = list( aid = structure(list(), class = c("collector_character", "collector")), tissue = structure(list(), class = c("collector_character", "collector")), group = structure(list(), class = c("collector_character", "collector")), sex = structure(list(), class = c("collector_character", "collector")), detail = structure(list(), class = c("collector_character", "collector")), value = structure(list(), class = c("collector_double", "collector"))), default = structure(list(), class = c("collector_guess", "collector")), skip = 1), class = "col_spec"))