By starting from this code, I would like to compute the between 7-time-point difference:
data <- out %>%
group_by(tests0, GROUP) %>%
summarise(
all = list(across(starts_with("score")) %>%
{
tibble(
means = data.frame(map(., ~ mean(.x, na.rm = TRUE)) %>% set_names(., str_replace(names(.), "\\D ", "mean"))),
stderrs = data.frame(map(., ~ std.error(.x, na.rm = TRUE)) %>% set_names(., str_replace(names(.), "\\D ", "stederr"))),
ttest1 = data.frame(possibly(~ reduce(., ~ t.test(.x, .y, paired = TRUE))["estimate"], NA)(.)),
ttest2 = data.frame(possibly(~ reduce(., ~ t.test(.x, .y, paired = TRUE))["p.value"], NA)(.))
)
})
)>%
unnest(all)
# Groups: tests0 [6]
tests0 GROUP means$mean0 $mean7 stderrs$stederr0 $stederr7 ttest1$estimate ttest2$p.value
<fct> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 ADAS_CogT0 CONTROL 12.6 13.6 0.525 0.662 -1.15 0.00182
2 ADAS_CogT0 TRAINING 14.0 12.6 0.613 0.570 1.40 0.00295
3 PVF_T0 CONTROL 32.1 31.3 1.22 1.45 0.498 0.636
4 PVF_T0 TRAINING 31.6 34.3 1.37 1.51 -2.48 0.0102
5 ROCF_CT0 CONTROL 29.6 30.3 0.893 0.821 -0.180 0.835
6 ROCF_CT0 TRAINING 30.1 29.5 0.906 0.929 0.489 0.615
7 ROCF_IT0 CONTROL 12.8 12.2 0.563 0.683 0.580 0.356
8 ROCF_IT0 TRAINING 10.9 12.3 0.735 0.768 -1.44 0.0238
9 ROCF_RT0 CONTROL 12.1 12.5 0.725 0.797 -0.370 0.598
10 ROCF_RT0 TRAINING 10.5 10.9 0.746 0.742 -0.534 0.370
11 SVF_T0 CONTROL 35.5 34 1.05 1.15 1.42 0.107
12 SVF_T0 TRAINING 34.1 32.9 1.04 1.16 0.962 0.231
Or better to add a column reporting mean7column-difference betwenn group (CONTROL and TRAINING). Do you what I should enter intoo the code above.
Here the dataset, if someone would like to try to figure out a possible solution.
Thanks in advance
> dput(head(out, 100))
structure(list(ID = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12,
13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28,
29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44,
45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60,
61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76,
77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92,
93, 94, 95, 96, 97, 98, 99, 100), GROUP = structure(c(2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 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), .Label = c("CONTROL", "TRAINING"), class = "factor"),
Gender = structure(c(1L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 2L,
2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L,
2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 1L,
2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L,
2L), .Label = c("M", "F"), class = "factor"), Age = c(74,
76, 81, 74, 69, 72, 75, 83, 78, 72, 82, 68, 72, 72, 73, 80,
69, 72, 70, 80, 75, 80, 78, 74, 82, 74, 80, 82, 78, 81, 66,
71, 70, 79, 78, 73, 72, 77, 77, 71, 83, 74, 70, 71, 77, 69,
67, 64, 79, 71, 77, 77, 73, 67, 68, 79, 81, 67, 84, 75, 80,
73, 68, 74, 77, 79, 79, 72, 73, 78, 76, 78, 77, 74, 78, 77,
77, 82, 77, 70, 77, 81, 79, 75, 74, 78, 69, 77, 73, 77, 70,
79, 70, 72, 77, 72, 71, 71, 73, 81), Education = c(18, 4,
8, 5, 8, 11, 5, 5, 4, 8, 8, 12, 5, 18, 13, 5, 13, 13, 5,
5, 13, 5, 3, 8, 17, 5, 8, 5, 5, 8, 17, 8, 18, 18, 13, 13,
13, 13, 15, 17, 8, 5, 5, 13, 8, 5, 11, 13, 8, 8, 8, 5, 13,
8, 5, 17, 8, 12, 13, 5, 8, 8, 8, 5, 3, 8, 18, 5, 8, 13, 8,
5, 17, 8, 5, 17, 5, 8, 11, 8, 8, 5, 12, 3, 8, 8, 8, 13, 5,
5, 8, 8, 13, 5, 5, 8, 13, 5, 8, 12), tests0 = 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,
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, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("ADAS_CogT0",
"PVF_T0", "ROCF_CT0", "ROCF_IT0", "ROCF_RT0", "SVF_T0"), class = "factor"),
score0 = c(14.66, 15.33, 17.33, 19, 7.66, 12.6, 18.67, 14.99,
17.99, 17.33, 13.66, 16.99, 10.66, 9.66, 14.99, 15.66, 13.33,
4.33, 14.33, 15.99, 16.33, 10.66, 14.66, 10.66, 19.33, 17.66,
15.99, 20.66, 20.6, 17, 10.33, 6.33, 6.66, 19.99, 13.33,
24.33, 12.33, 10.33, 12.33, 9.66, 10.99, 13.99, 23, 6.32,
11.32, 13.99, 14.66, 8.99, 14.33, 9.99, 7.33, 15.66, 14,
7.99, 23.32, 14.66, 9.99, 5.66, 6.99, 11.66, 10.33, 6.99,
19.32, NA, 10, 17.66, 13.66, 10.32, NA, NA, 8.66, 9, 6.99,
14.99, 9.66, 13.66, 15.32, 12, 14, 13.66, 11.99, 15.66, 16,
15, 16.99, 20, 11, 7.99, 8.33, 8.32, 14.99, 18.66, 10.33,
11.99, 9.32, 17, 14.33, 14.66, 16.6, 9.99), tests7 = 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,
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, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("ADAS_CogT7",
"PVF_T7", "ROCF_CT7", "ROCF_IT7", "ROCF_RT7", "SVF_T7"), class = "factor"),
score7 = c(16, 9.32, 21.33, 17, 8.32, 11, 14.99, 10.99, 17,
18.33, 13.32, 14.34, 8.99, 7, 11.99, 15.33, 6.99, 5.33, 12.32,
13, 21.32, 7.99, 13.33, 11.99, 17.32, 16.32, 16.33, 14.66,
18.99, 17.33, 7.99, 9.33, 10.99, NA, 12.99, 16.33, 21.66,
9, 9.34, 8.66, 8.33, 13.66, 15.66, 6.66, 10.99, 13.33, 13.33,
7.99, 11.99, 11.32, 7.33, 9.66, 6.99, NA, 15.99, 15.66, 14.66,
6.32, 7, 11, 14, 10.33, 24.66, NA, 14.99, NA, 15.99, 9.32,
NA, NA, 9.99, 9.33, 7.66, 17.33, 10.32, 16, 17, 12.99, 15,
14.33, 10, 14.99, 19, 13.99, 19.33, NA, 10, 6.99, 11.66,
6.66, 14.33, 16, 8.66, 10, NA, 20, 14.99, 19.66, 26.66, 8.99
)), row.names = c(NA, -100L), class = c("tbl_df", "tbl",
"data.frame"))
>
CodePudding user response：
what_you_have %>%
group_by(tests0) %>%
arrange(GROUP) %>%
mutate(mean7_ctrl_train_diff = diff(`$mean7`))
Using this data:
what_you_have = read.table(text = ' tests0 GROUP means$mean0 $mean7 stderrs$stederr0 $stederr7 ttest1$estimate ttest2$p.value
1 ADAS_CogT0 CONTROL 12.6 13.6 0.525 0.662 -1.15 0.00182
2 ADAS_CogT0 TRAINING 14.0 12.6 0.613 0.570 1.40 0.00295
3 PVF_T0 CONTROL 32.1 31.3 1.22 1.45 0.498 0.636
4 PVF_T0 TRAINING 31.6 34.3 1.37 1.51 -2.48 0.0102
5 ROCF_CT0 CONTROL 29.6 30.3 0.893 0.821 -0.180 0.835
6 ROCF_CT0 TRAINING 30.1 29.5 0.906 0.929 0.489 0.615
7 ROCF_IT0 CONTROL 12.8 12.2 0.563 0.683 0.580 0.356
8 ROCF_IT0 TRAINING 10.9 12.3 0.735 0.768 -1.44 0.0238
9 ROCF_RT0 CONTROL 12.1 12.5 0.725 0.797 -0.370 0.598
10 ROCF_RT0 TRAINING 10.5 10.9 0.746 0.742 -0.534 0.370
11 SVF_T0 CONTROL 35.5 34 1.05 1.15 1.42 0.107
12 SVF_T0 TRAINING 34.1 32.9 1.04 1.16 0.962 0.231', header = T, check.names = FALSE)
CodePudding user response：
The data is created with columns as data.frame.
> str(data)
grouped_df [2 × 6] (S3: grouped_df/tbl_df/tbl/data.frame)
$ tests0 : Factor w/ 6 levels "ADAS_CogT0","PVF_T0",..: 1 1
$ GROUP : Factor w/ 2 levels "CONTROL","TRAINING": 1 2
$ means :'data.frame': 2 obs. of 2 variables:
..$ mean0: num [1:2] 12.5 14
..$ mean7: num [1:2] 13.5 12.6
$ stderrs:'data.frame': 2 obs. of 2 variables:
..$ stederr0: num [1:2] 0.574 0.613
..$ stederr7: num [1:2] 0.77 0.57
$ ttest1 :'data.frame': 2 obs. of 1 variable:
..$ estimate: num [1:2] -1.24 1.4
$ ttest2 :'data.frame': 2 obs. of 1 variable:
..$ p.value: num [1:2] 0.00471 0.00295
- attr(*, "groups")= tibble [1 × 2] (S3: tbl_df/tbl/data.frame)
..$ tests0: Factor w/ 6 levels "ADAS_CogT0","PVF_T0",..: 1
..$ .rows : list<int> [1:1]
.. ..$ : int [1:2] 1 2
.. ..@ ptype: int(0)
..- attr(*, ".drop")= logi TRUE
So, we may need to unpack those data.frame columns before doing the diff
library(dplyr)
library(tidyr)
data %>%
unpack(where(is.data.frame)) %>%
mutate(mean7diff = c(NA, diff(mean7))) %>%
ungroup
-output
# A tibble: 2 × 9
tests0 GROUP mean0 mean7 stederr0 stederr7 estimate p.value mean7diff
<fct> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 ADAS_CogT0 CONTROL 12.5 13.5 0.574 0.770 -1.24 0.00471 NA
2 ADAS_CogT0 TRAINING 14.0 12.6 0.613 0.570 1.40 0.00295 -0.878
CodePudding user response：
Not sure if this is what you are looking for?
out %>%
drop_na() %>%
select(-c(ID, Gender, Age, Education)) %>%
group_by(tests0) %>%
ungroup() %>%
pivot_wider(names_from = GROUP, values_from = contains('score'), values_fn = mean) %>%
transmute(
tests0 = tests0,
diff0 = score0_TRAINING - score0_CONTROL,
diff7 = score7_TRAINING - score7_CONTROL
)
# A tibble: 1 x 3
tests0 diff0 diff7
<fct> <dbl> <dbl>
1 ADAS_CogT0 1.76 -0.878