R/ff_summ_bygroup.R
ff_summ_allvars_bygroup.Rd
Generate distributional and other statistics for a particular continuous variable, categorized by some discrete variables. Wage by gender for example.
ff_summ_allvars_bygroup(
df,
vars.group,
var.numeric,
str.stats.group = "main",
ar.perc = c(0.01, 0.05, 0.1, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99),
str.stats.specify = NULL,
boo.overall.stats = TRUE
)
dataframe input dataframe of interest
list of strings containing grouping variables, could be gender and age groups for example
string variable name of continuous quantitative variable to summarize
string what type of statistics to consider see line 31 and below
array of percentiles to calculate, only calculated if str.stats.group = 'mainperc'
a list of various variables
df_table_grp_stats - A dataframe where each row is a combination of categories, and columns are categories and statistics
df_row_grp_stats - A single row with all statistics
df_overall_stats - A dataframe with non-grouped overall summaries
df_row_stats_all - A named list of all statistics generated
https://fanwangecon.github.io/REconTools/reference/ff_summ_bygroup.html https://fanwangecon.github.io/REconTools/articles/fv_summ_bygroup.html https://github.com/FanWangEcon/REconTools/blob/master/R/ff_summ_bygroup.R
data(mtcars)
df_mtcars <- mtcars
df <- df_mtcars
vars.group <- c('am', 'vs')
var.numeric <- 'mpg'
str.stats.group <- 'allperc'
ar.perc <- c(0.01, 0.05, 0.10, 0.25, 0.5, 0.75, 0.9, 0.95, 0.99)
ls_summ_by_group <- ff_summ_bygroup(df, vars.group, var.numeric, str.stats.group, ar.perc)
#> Warning: `funs()` was deprecated in dplyr 0.8.0.
#> Please use a list of either functions or lambdas:
#>
#> # Simple named list:
#> list(mean = mean, median = median)
#>
#> # Auto named with `tibble::lst()`:
#> tibble::lst(mean, median)
#>
#> # Using lambdas
#> list(~ mean(., trim = .2), ~ median(., na.rm = TRUE))
#> This warning is displayed once every 8 hours.
#> Call `lifecycle::last_lifecycle_warnings()` to see where this warning was generated.
#> Warning: attributes are not identical across measure variables;
#> they will be dropped
df_table_grp_stats <- ls_summ_by_group$df_table_grp_stats
df_row_grp_stats <- ls_summ_by_group$df_row_grp_stats
df_overall_stats <- ls_summ_by_group$df_overall_stats
df_row_stats_all <- ls_summ_by_group$df_row_stats_all
print(df_table_grp_stats)
#> # A tibble: 4 x 21
#> # Groups: am [2]
#> am vs mean median sd IQR mad `1%` `5%` `10%` `25%` `50%` `75%`
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 0 0 15.0 15.2 2.77 2.57 2.30 10.4 10.4 10.7 14.0 15.2 16.6
#> 2 0 1 20.7 21.4 2.47 3.5 3.26 17.8 17.9 18.0 18.6 21.4 22.2
#> 3 1 0 19.8 20.4 4.01 4.22 3.85 15.0 15.2 15.4 16.8 20.4 21
#> 4 1 1 28.4 30.4 4.76 6.35 4.60 21.5 21.8 22.2 25.0 30.4 31.4
#> # ... with 8 more variables: 90% <dbl>, 95% <dbl>, 99% <dbl>, min <dbl>,
#> # max <dbl>, first <dbl>, last <dbl>, n.distinct <int>
print(df_row_grp_stats)
#> # A tibble: 1 x 76
#> `mpg.am.vs.0.0.1%` `mpg.am.vs.0.0.10%` `mpg.am.vs.0.0.25%` `mpg.am.vs.0.0.5%`
#> <dbl> <dbl> <dbl> <dbl>
#> 1 10.4 10.7 14.0 10.4
#> # ... with 72 more variables: mpg.am.vs.0.0.50% <dbl>, mpg.am.vs.0.0.75% <dbl>,
#> # mpg.am.vs.0.0.90% <dbl>, mpg.am.vs.0.0.95% <dbl>, mpg.am.vs.0.0.99% <dbl>,
#> # mpg.am.vs.0.0.IQR <dbl>, mpg.am.vs.0.0.first <dbl>,
#> # mpg.am.vs.0.0.last <dbl>, mpg.am.vs.0.0.mad <dbl>, mpg.am.vs.0.0.max <dbl>,
#> # mpg.am.vs.0.0.mean <dbl>, mpg.am.vs.0.0.median <dbl>,
#> # mpg.am.vs.0.0.min <dbl>, mpg.am.vs.0.0.n.distinct <dbl>,
#> # mpg.am.vs.0.0.sd <dbl>, mpg.am.vs.0.1.1% <dbl>, ...
print(df_overall_stats)
#> mpg.mean mpg.median mpg.sd mpg.IQR mpg.mad mpg.1% mpg.5% mpg.10% mpg.25%
#> 1 20.09062 19.2 6.026948 7.375 5.41149 10.4 11.995 14.34 15.425
#> mpg.50% mpg.75% mpg.90% mpg.95% mpg.99% mpg.min mpg.max mpg.first mpg.last
#> 1 19.2 22.8 30.09 31.3 33.435 10.4 33.9 21 21.4
#> mpg.n_distinct
#> 1 25
print(df_row_stats_all)
#> $`mpg.am.vs.0.0.1%`
#> [1] 10.4
#>
#> $`mpg.am.vs.0.0.10%`
#> [1] 10.69
#>
#> $`mpg.am.vs.0.0.25%`
#> [1] 14.05
#>
#> $`mpg.am.vs.0.0.5%`
#> [1] 10.4
#>
#> $`mpg.am.vs.0.0.50%`
#> [1] 15.2
#>
#> $`mpg.am.vs.0.0.75%`
#> [1] 16.625
#>
#> $`mpg.am.vs.0.0.90%`
#> [1] 18.56
#>
#> $`mpg.am.vs.0.0.95%`
#> [1] 18.925
#>
#> $`mpg.am.vs.0.0.99%`
#> [1] 19.145
#>
#> $mpg.am.vs.0.0.IQR
#> [1] 2.575
#>
#> $mpg.am.vs.0.0.first
#> [1] 10.4
#>
#> $mpg.am.vs.0.0.last
#> [1] 19.2
#>
#> $mpg.am.vs.0.0.mad
#> [1] 2.29803
#>
#> $mpg.am.vs.0.0.max
#> [1] 19.2
#>
#> $mpg.am.vs.0.0.mean
#> [1] 15.05
#>
#> $mpg.am.vs.0.0.median
#> [1] 15.2
#>
#> $mpg.am.vs.0.0.min
#> [1] 10.4
#>
#> $mpg.am.vs.0.0.n.distinct
#> [1] 10
#>
#> $mpg.am.vs.0.0.sd
#> [1] 2.774396
#>
#> $`mpg.am.vs.0.1.1%`
#> [1] 17.818
#>
#> $`mpg.am.vs.0.1.10%`
#> [1] 17.98
#>
#> $`mpg.am.vs.0.1.25%`
#> [1] 18.65
#>
#> $`mpg.am.vs.0.1.5%`
#> [1] 17.89
#>
#> $`mpg.am.vs.0.1.50%`
#> [1] 21.4
#>
#> $`mpg.am.vs.0.1.75%`
#> [1] 22.15
#>
#> $`mpg.am.vs.0.1.90%`
#> [1] 23.44
#>
#> $`mpg.am.vs.0.1.95%`
#> [1] 23.92
#>
#> $`mpg.am.vs.0.1.99%`
#> [1] 24.304
#>
#> $mpg.am.vs.0.1.IQR
#> [1] 3.5
#>
#> $mpg.am.vs.0.1.first
#> [1] 17.8
#>
#> $mpg.am.vs.0.1.last
#> [1] 24.4
#>
#> $mpg.am.vs.0.1.mad
#> [1] 3.26172
#>
#> $mpg.am.vs.0.1.max
#> [1] 24.4
#>
#> $mpg.am.vs.0.1.mean
#> [1] 20.74286
#>
#> $mpg.am.vs.0.1.median
#> [1] 21.4
#>
#> $mpg.am.vs.0.1.min
#> [1] 17.8
#>
#> $mpg.am.vs.0.1.n.distinct
#> [1] 7
#>
#> $mpg.am.vs.0.1.sd
#> [1] 2.471071
#>
#> $`mpg.am.vs.1.0.1%`
#> [1] 15.04
#>
#> $`mpg.am.vs.1.0.10%`
#> [1] 15.4
#>
#> $`mpg.am.vs.1.0.25%`
#> [1] 16.775
#>
#> $`mpg.am.vs.1.0.5%`
#> [1] 15.2
#>
#> $`mpg.am.vs.1.0.50%`
#> [1] 20.35
#>
#> $`mpg.am.vs.1.0.75%`
#> [1] 21
#>
#> $`mpg.am.vs.1.0.90%`
#> [1] 23.5
#>
#> $`mpg.am.vs.1.0.95%`
#> [1] 24.75
#>
#> $`mpg.am.vs.1.0.99%`
#> [1] 25.75
#>
#> $mpg.am.vs.1.0.IQR
#> [1] 4.225
#>
#> $mpg.am.vs.1.0.first
#> [1] 15
#>
#> $mpg.am.vs.1.0.last
#> [1] 26
#>
#> $mpg.am.vs.1.0.mad
#> [1] 3.85476
#>
#> $mpg.am.vs.1.0.max
#> [1] 26
#>
#> $mpg.am.vs.1.0.mean
#> [1] 19.75
#>
#> $mpg.am.vs.1.0.median
#> [1] 20.35
#>
#> $mpg.am.vs.1.0.min
#> [1] 15
#>
#> $mpg.am.vs.1.0.n.distinct
#> [1] 5
#>
#> $mpg.am.vs.1.0.sd
#> [1] 4.008865
#>
#> $`mpg.am.vs.1.1.1%`
#> [1] 21.484
#>
#> $`mpg.am.vs.1.1.10%`
#> [1] 22.24
#>
#> $`mpg.am.vs.1.1.25%`
#> [1] 25.05
#>
#> $`mpg.am.vs.1.1.5%`
#> [1] 21.82
#>
#> $`mpg.am.vs.1.1.50%`
#> [1] 30.4
#>
#> $`mpg.am.vs.1.1.75%`
#> [1] 31.4
#>
#> $`mpg.am.vs.1.1.90%`
#> [1] 33
#>
#> $`mpg.am.vs.1.1.95%`
#> [1] 33.45
#>
#> $`mpg.am.vs.1.1.99%`
#> [1] 33.81
#>
#> $mpg.am.vs.1.1.IQR
#> [1] 6.35
#>
#> $mpg.am.vs.1.1.first
#> [1] 21.4
#>
#> $mpg.am.vs.1.1.last
#> [1] 33.9
#>
#> $mpg.am.vs.1.1.mad
#> [1] 4.59606
#>
#> $mpg.am.vs.1.1.max
#> [1] 33.9
#>
#> $mpg.am.vs.1.1.mean
#> [1] 28.37143
#>
#> $mpg.am.vs.1.1.median
#> [1] 30.4
#>
#> $mpg.am.vs.1.1.min
#> [1] 21.4
#>
#> $mpg.am.vs.1.1.n.distinct
#> [1] 6
#>
#> $mpg.am.vs.1.1.sd
#> [1] 4.757701
#>
#> $mpg.mean
#> [1] 20.09062
#>
#> $mpg.median
#> [1] 19.2
#>
#> $mpg.sd
#> [1] 6.026948
#>
#> $mpg.IQR
#> [1] 7.375
#>
#> $mpg.mad
#> [1] 5.41149
#>
#> $`mpg.1%`
#> 1%
#> 10.4
#>
#> $`mpg.5%`
#> 5%
#> 11.995
#>
#> $`mpg.10%`
#> 10%
#> 14.34
#>
#> $`mpg.25%`
#> 25%
#> 15.425
#>
#> $`mpg.50%`
#> 50%
#> 19.2
#>
#> $`mpg.75%`
#> 75%
#> 22.8
#>
#> $`mpg.90%`
#> 90%
#> 30.09
#>
#> $`mpg.95%`
#> 95%
#> 31.3
#>
#> $`mpg.99%`
#> 99%
#> 33.435
#>
#> $mpg.min
#> [1] 10.4
#>
#> $mpg.max
#> [1] 33.9
#>
#> $mpg.first
#> [1] 21
#>
#> $mpg.last
#> [1] 21.4
#>
#> $mpg.n_distinct
#> [1] 25
#>