将描述性统计严格地重组为R中的表格格式

Question

让我们看看虹膜分类的结果。样本很少。

iris=structure(list(Sepal.Length = c(5.1, 4.9, 4.7, 4.6, 5, 5.4, 4.6, 
5, 4.4, 4.9, 5.4, 4.8, 4.8, 4.3, 5.8, 5.7, 5.4, 5.1, 5.7, 5.1, 
5.4, 5.1, 4.6, 5.1, 4.8, 5, 5, 5.2, 5.2, 4.7, 4.8, 5.4, 5.2, 
5.5, 4.9, 5, 5.5, 4.9, 4.4, 5.1, 5, 4.5, 4.4, 5, 5.1, 4.8, 5.1, 
4.6, 5.3, 5), Sepal.Width = c(3.5, 3, 3.2, 3.1, 3.6, 3.9, 3.4, 
3.4, 2.9, 3.1, 3.7, 3.4, 3, 3, 4, 4.4, 3.9, 3.5, 3.8, 3.8, 3.4, 
3.7, 3.6, 3.3, 3.4, 3, 3.4, 3.5, 3.4, 3.2, 3.1, 3.4, 4.1, 4.2, 
3.1, 3.2, 3.5, 3.6, 3, 3.4, 3.5, 2.3, 3.2, 3.5, 3.8, 3, 3.8, 
3.2, 3.7, 3.3), Petal.Length = c(1.4, 1.4, 1.3, 1.5, 1.4, 1.7, 
1.4, 1.5, 1.4, 1.5, 1.5, 1.6, 1.4, 1.1, 1.2, 1.5, 1.3, 1.4, 1.7, 
1.5, 1.7, 1.5, 1, 1.7, 1.9, 1.6, 1.6, 1.5, 1.4, 1.6, 1.6, 1.5, 
1.5, 1.4, 1.5, 1.2, 1.3, 1.4, 1.3, 1.5, 1.3, 1.3, 1.3, 1.6, 1.9, 
1.4, 1.6, 1.4, 1.5, 1.4), Petal.Width = c(0.2, 0.2, 0.2, 0.2, 
0.2, 0.4, 0.3, 0.2, 0.2, 0.1, 0.2, 0.2, 0.1, 0.1, 0.2, 0.4, 0.4, 
0.3, 0.3, 0.3, 0.2, 0.4, 0.2, 0.5, 0.2, 0.2, 0.4, 0.2, 0.2, 0.2, 
0.2, 0.4, 0.1, 0.2, 0.2, 0.2, 0.2, 0.1, 0.2, 0.2, 0.3, 0.3, 0.2, 
0.6, 0.4, 0.3, 0.2, 0.2, 0.2, 0.2), flower = c(1L, 3L, 3L, 3L, 
1L, 2L, 3L, 1L, 3L, 3L, 2L, 1L, 3L, 3L, 2L, 2L, 2L, 1L, 2L, 2L, 
1L, 1L, 1L, 1L, 1L, 3L, 1L, 1L, 1L, 3L, 3L, 1L, 2L, 2L, 3L, 1L, 
2L, 1L, 3L, 1L, 1L, 3L, 3L, 1L, 2L, 3L, 2L, 3L, 2L, 1L)), class = "data.frame", row.names = c(NA, 
-50L))

3纲。但问题是如何获得每个参数和每个类的描述性统计数据(DS(？我使用library(psych)，但在使用describeby函数时，(DS(的结果格式不方便。我需要一张严格按照这种格式的现成桌子。我把它作为.data.frame 提供

structure(list(variable.name = c("Sepal,Length", "", "", "", 
"Sepal,Width", "", "", "", "Petal,Length", "", "", "", "Petal,Width", 
"", "", ""), number.of.flower.class = c("1", "2", "3", "total", 
"1", "2", "3", "total", "1", "2", "3", "total", "1", "2", "3", 
"total"), count.observations.in.class = c(20L, 13L, 17L, 50L, 
20L, 13L, 17L, 50L, 20L, 13L, 17L, 50L, 20L, 13L, 17L, 50L), 
Mean = c(5.04, 5.4, 4.6647, 5.006, 3.45, 3.8923, 3.0471, 
3.428, 1.475, 1.5077, 1.4118, 1.462, 0.27, 0.2692, 0.2, 0.246
), stdev = c(0.1875, 0.23805, 0.21196, 0.35249, 0.11921, 
0.23616, 0.22671, 0.37906, 0.1916, 0.18913, 0.13173, 0.17366, 
0.12607, 0.10316, 0.06124, 0.10539), X.95.DI = c(4.9522, 
5.2561, 4.5557, 4.9058, 3.3942, 3.7496, 2.9305, 3.3203, 1.3853, 
1.3934, 1.344, 1.4126, 0.211, 0.2069, 0.1685, 0.216), X95.DI = c(5.1278, 
5.5439, 4.7737, 5.1062, 3.5058, 4.035, 3.1636, 3.5357, 1.5647, 
1.622, 1.4795, 1.5114, 0.329, 0.3316, 0.2315, 0.276), min = c(4.6, 
5.1, 4.3, 4.3, 3.2, 3.5, 2.3, 2.3, 1, 1.2, 1.1, 1, 0.1, 0.1, 
0.1, 0.1), max = c(5.4, 5.8, 5, 5.8, 3.7, 4.4, 3.4, 4.4, 
1.9, 1.9, 1.6, 1.9, 0.6, 0.4, 0.3, 0.6)), class = "data.frame", row.names = c(NA, 
-16L))

如何将描述性统计数据严格重组为每个类的表格格式？我对统计学感兴趣：变量名

number of flower class
count observations in class
Mean
stdev
-95%DI
95%DI
min
max

Answer 1

我不确定是否有一种简洁的方法可以按组进行总结并进行总体总结，所以我计算了您对这两个方面的兴趣指标，并将它们组合起来。

library(dplyr)
library(tidyr)
data(iris)
myci <- function(x, dir){
se.x <- (sd(x) / sqrt(length(x)))
mean.x <- mean(x)
if(dir=="lower"){
return(mean.x - qt(1 - (0.05 / 2), length(x) - 1) * se.x)
} else if(dir=="upper"){
return(mean.x + qt(1 - (0.05 / 2), length(x) - 1) * se.x)
}
}

output <- bind_rows(
# Calculate group metrics
iris %>%
pivot_longer(setdiff(names(iris), "Species"), names_to = "variable") %>%
group_by(Species, variable) %>%
summarize_if(is.numeric, list(n=length,
mean=mean,
sd=sd,
min=min,
max=max,
ci_lower=function(x){myci(x, "lower")}, 
ci_upper=function(x){myci(x, "upper")})),
# Caculate overall metrics
iris %>%
pivot_longer(setdiff(names(iris), "Species"), names_to = "variable") %>%
group_by(variable) %>%
summarize_if(is.numeric, list(n=length,
mean=mean,
sd=sd,
min=min,
max=max,
ci_lower=function(x){myci(x, "lower")}, 
ci_upper=function(x){myci(x, "upper")})) %>%
mutate(Species = "Total"))
output[order(output$variable),]
#> # A tibble: 16 x 9
#> # Groups:   Species [4]
#>    Species    variable         n  mean    sd   min   max ci_lower ci_upper
#>    <chr>      <chr>        <int> <dbl> <dbl> <dbl> <dbl>    <dbl>    <dbl>
#>  1 setosa     Petal.Length    50 1.46  0.174   1     1.9    1.41     1.51 
#>  2 versicolor Petal.Length    50 4.26  0.470   3     5.1    4.13     4.39 
#>  3 virginica  Petal.Length    50 5.55  0.552   4.5   6.9    5.40     5.71 
#>  4 Total      Petal.Length   150 3.76  1.77    1     6.9    3.47     4.04 
#>  5 setosa     Petal.Width     50 0.246 0.105   0.1   0.6    0.216    0.276
#>  6 versicolor Petal.Width     50 1.33  0.198   1     1.8    1.27     1.38 
#>  7 virginica  Petal.Width     50 2.03  0.275   1.4   2.5    1.95     2.10 
#>  8 Total      Petal.Width    150 1.20  0.762   0.1   2.5    1.08     1.32 
#>  9 setosa     Sepal.Length    50 5.01  0.352   4.3   5.8    4.91     5.11 
#> 10 versicolor Sepal.Length    50 5.94  0.516   4.9   7      5.79     6.08 
#> 11 virginica  Sepal.Length    50 6.59  0.636   4.9   7.9    6.41     6.77 
#> 12 Total      Sepal.Length   150 5.84  0.828   4.3   7.9    5.71     5.98 
#> 13 setosa     Sepal.Width     50 3.43  0.379   2.3   4.4    3.32     3.54 
#> 14 versicolor Sepal.Width     50 2.77  0.314   2     3.4    2.68     2.86 
#> 15 virginica  Sepal.Width     50 2.97  0.322   2.2   3.8    2.88     3.07 
#> 16 Total      Sepal.Width    150 3.06  0.436   2     4.4    2.99     3.13
Created on 2021-12-16 by the reprex package (v2.0.1)