Make a tidy dataset out of freq() or descr() outputs
tb(
x,
order = 1,
drop.var.col = FALSE,
recalculate = TRUE,
fct.to.chr = FALSE,
...
)Integer. Useful for grouped results produced with
stby or dplyr::group_by. When set to 1
(default), the ordering is done using the grouping variables first.
When set to 2, the ordering is done according to the analytical
(not grouping) variable. When set to 3, the same ordering
as with 2 is used, but the analytical variable is placed in
first position. Depending on what function was used for grouping,
the results will be different in subtle ways. See Details.
Logical. For descr objects, drop the
variable column. This is possible only when statistics are
produced for a single variable; when multiple variables are present,
this parameter is ignored. FALSE by default.
Logical. TRUE by default. For grouped
freq results, recalculate percentages to have total
proportions sum up to 1. Defaults to TRUE.
Logical. When grouped objects
are created with dplyr::group_by, the resulting
tibble will have factor columns when the grouping variable itself is
a factor. To convert them to character, set this to TRUE. See
Details.
For internal use only.
A tibble which is constructed following the
tidy principles.
stby, which is based on and by, initially make the first
variable vary, keeping the other(s) constant. On the other hand,
group_by initially keeps the first grouping variable(s) constant,
making the last one vary. This will impact the ordering of the rows (and
as a result, the cumulative percent columns, if present).
Also, keep in mind that while group_by shows NA groups by
default, useNA = TRUE must be used to achieve the same
results with stby.
tb(freq(iris$Species))
#> # A tibble: 4 × 6
#> Species freq pct_valid pct_valid_cum pct_tot pct_tot_cum
#> <fct> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 setosa 50 33.3 33.3 33.3 33.3
#> 2 versicolor 50 33.3 66.7 33.3 66.7
#> 3 virginica 50 33.3 100 33.3 100
#> 4 NA 0 NA NA 0 100
tb(descr(iris, stats = "common"))
#> # A tibble: 4 × 9
#> variable mean sd min med max n.valid n pct.valid
#> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 Petal.Length 3.76 1.77 1 4.35 6.9 150 150 100
#> 2 Petal.Width 1.20 0.762 0.1 1.3 2.5 150 150 100
#> 3 Sepal.Length 5.84 0.828 4.3 5.8 7.9 150 150 100
#> 4 Sepal.Width 3.06 0.436 2 3 4.4 150 150 100
data("tobacco")
tb(stby(tobacco, tobacco$gender, descr, stats = "fivenum",check.nas = FALSE),
order=3)
#> NA detected in grouping variable(s); consider using useNA = TRUE
#> # A tibble: 8 × 7
#> variable gender min q1 med q3 max
#> <chr> <fct> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 BMI F 9.01 23.0 25.9 29.5 39.4
#> 2 BMI M 8.83 22.5 25.1 28.0 36.8
#> 3 age F 18 34 50 66 80
#> 4 age M 18 34 49.5 66 80
#> 5 cigs.per.day F 0 0 0 10.5 40
#> 6 cigs.per.day M 0 0 0 11 40
#> 7 samp.wgts F 0.861 0.861 1.04 1.05 1.06
#> 8 samp.wgts M 0.861 0.861 1.04 1.05 1.06
tb(stby(tobacco, tobacco$gender, descr, stats = "common", useNA = TRUE))
#> # A tibble: 12 × 10
#> gender variable mean sd min med max n.valid n pct.valid
#> <fct> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 F BMI 26.1 4.95 9.01 25.9 39.4 475 489 97.1
#> 2 F age 49.6 18.3 18 50 80 475 489 97.1
#> 3 F cigs.per.day 6.88 12.0 0 0 40 468 489 95.7
#> 4 F samp.wgts 1.00 0.0840 0.861 1.04 1.06 489 489 100
#> 5 M BMI 25.3 3.98 8.83 25.1 36.8 477 489 97.5
#> 6 M age 49.6 18.3 18 49.5 80 478 489 97.8
#> 7 M cigs.per.day 6.72 11.8 0 0 40 475 489 97.1
#> 8 M samp.wgts 1.00 0.0840 0.861 1.04 1.06 489 489 100
#> 9 NA BMI 26.9 3.51 20.2 27.2 32.4 22 22 100
#> 10 NA age 50.9 18.2 19 55.5 80 22 22 100
#> 11 NA cigs.per.day 6.09 9.72 0 0 28 22 22 100
#> 12 NA samp.wgts 1.01 0.0811 0.861 1.05 1.06 22 22 100
# Compare stby() and group_by() groups' ordering
tb(with(tobacco, stby(diseased, list(gender, smoker), freq, useNA = TRUE)))
#> # A tibble: 18 × 8
#> gender smoker diseased freq pct_valid pct_valid_cum pct_tot pct_tot_cum
#> <fct> <fct> <fct> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 F Yes Yes 62 6.2 6.2 6.2 6.2
#> 2 F Yes No 85 8.5 14.7 8.5 14.7
#> 3 F Yes NA 0 NA NA 0 14.7
#> 4 M Yes Yes 63 6.3 21 6.3 21
#> 5 M Yes No 80 8 29 8 29
#> 6 M Yes NA 0 NA NA 0 29
#> 7 NA Yes Yes 0 0 29 0 29
#> 8 NA Yes No 8 0.8 29.8 0.8 29.8
#> 9 NA Yes NA 0 NA NA 0 29.8
#> 10 F No Yes 49 4.9 34.7 4.9 34.7
#> 11 F No No 293 29.3 64 29.3 64
#> 12 F No NA 0 NA NA 0 64
#> 13 M No Yes 47 4.7 68.7 4.7 68.7
#> 14 M No No 299 29.9 98.6 29.9 98.6
#> 15 M No NA 0 NA NA 0 98.6
#> 16 NA No Yes 3 0.3 98.9 0.3 98.9
#> 17 NA No No 11 1.1 100 1.1 100
#> 18 NA No NA 0 NA NA 0 100
if (FALSE) { # \dontrun{
tobacco |> dplyr::group_by(gender, smoker) |> freq(diseased) |> tb()
} # }