I a statistical test on this data set by using the following codes:
# DF1
Name <- c("Sam", "Anna", "Anna", "Sam", "Anna")
Companies <- c(23, 21, 22, 24, 45)
Store <- c(10, 8, 5, 5, 6)
Cars <- c(10, 7, 5, 6, 7)
Home <- c(8, 4, 5, 8, 4)
DF1 <- data.frame(Name, Companies, Store, Cars, Home)
DF1$Name <- as.factor(DF1$Name)
Z <- lapply(DF1[-1], function(x){
wilcox.test(x ~ DF1$Name)
})
Now in Z, there is a list in a list for each column name. For example, when I look at the data frame Z, and click Companies, I see statistic and null.value. I am trying to unlist them to have them in separate columns based on the specific group it belongs to (shown below). The code I use is this, but this isnt quite what I am looking for, and cant find anything else online.
Z_unlisted <- as.data.frame(unlist(Z))
I am not sure why I am really confused on this, since I feel it should be pretty simple using unlist(), but all of the lists expand out into one column, but not into separate columns.
How can I unlist all of these out so each category (statistic, parameter, p.value, etc.) is in the column, and the groupings (Companies, Store, Cars, and Home are in one column? Example shown: (where each column is part of the list)
Companies 2 0.8 Wilcoxon rank sum exact test two.sided
Store 2.5 1 Wilcoxon rank sum test with continuity correction two.sided
Cars 2 0.767 Wilcoxon rank sum test with continuity correction two.sided
Home 0 0.128 Wilcoxon rank sum test with continuity correction two.sided
CodePudding user response：
Instead of unlisting on the whole list, do it inside and rbind
do.call(rbind, lapply(Z, unlist))
CodePudding user response：
Use tidy from broom and apply it using map_dfr from purrr:
library(broom)
library(purrr)
map_dfr(DF1[-1], ~ tidy(wilcox.test(.x ~ Name, DF1)), .id = "Companies")
giving
# A tibble: 4 x 5
Companies statistic p.value method alternative
<chr> <dbl> <dbl> <chr> <chr>
1 Companies 2 0.8 Wilcoxon rank sum exact test two.sided
2 Store 2.5 1 Wilcoxon rank sum test with continuit~ two.sided
3 Cars 2 0.767 Wilcoxon rank sum test with continuit~ two.sided
4 Home 0 0.128 Wilcoxon rank sum test with continuit~ two.sided
CodePudding user response：
If you look at the structure of Z you see that it is a list of 4 items, each of which is an instance of an "htest"-classed value.
str(Z)
#---------
List of 4
$ Companies:List of 7
..$ statistic : Named num 2
.. ..- attr(*, "names")= chr "W"
..$ parameter : NULL
..$ p.value : num 0.8
..$ null.value : Named num 0
.. ..- attr(*, "names")= chr "location shift"
..$ alternative: chr "two.sided"
..$ method : chr "Wilcoxon rank sum exact test"
..$ data.name : chr "x by DF1$Name"
..- attr(*, "class")= chr "htest"
# -- remaining items have similar structures.
Since each of the sub-items in those values is of length-1 it's easy to construct a matrix using the do.call(rbind, ...) approach suggested by @akrun.
do.call(rbind, Z)
statistic parameter p.value null.value alternative
Companies 2 NULL 0.8 0 "two.sided"
Store 2.5 NULL 1 0 "two.sided"
Cars 2 NULL 0.7670969 0 "two.sided"
Home 0 NULL 0.1281466 0 "two.sided"
method data.name
Companies "Wilcoxon rank sum exact test" "x by DF1$Name"
Store "Wilcoxon rank sum test with continuity correction" "x by DF1$Name"
Cars "Wilcoxon rank sum test with continuity correction" "x by DF1$Name"
Note that the groupings (Companies, Store, Cars, and Home) are not actually a column but are rownames.
You could have achieved a matrix result (although it will be the transpose of above) more simply by using sapply instead of lapply, beacus sapply has a default option of "simplifying" its results if they are all the same length:
( Z <- sapply(DF1[-1], function(x){
wilcox.test(x ~ DF1$Name)
}) )
#----------
Companies Store
statistic 2 2.5
parameter NULL NULL
p.value 0.8 1
null.value 0 0
alternative "two.sided" "two.sided"
method "Wilcoxon rank sum exact test" "Wilcoxon rank sum test with continuity correction"
data.name "x by DF1$Name" "x by DF1$Name"
Cars
statistic 2
parameter NULL
p.value 0.7670969
null.value 0
alternative "two.sided"
method "Wilcoxon rank sum test with continuity correction"
data.name "x by DF1$Name"
Home
statistic 0
parameter NULL
p.value 0.1281466
null.value 0
alternative "two.sided"
method "Wilcoxon rank sum test with continuity correction"
data.name "x by DF1$Name"
Warning messages:
1: In wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...) :
cannot compute exact p-value with ties
2: In wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...) :
cannot compute exact p-value with ties
3: In wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...) :
cannot compute exact p-value with ties