freq: ================

In feranpre/udaicR: Basic functions that I use all the time

================

Description

Intervalo de confianza para proporciones Hacerlo para medias tb

Usage

freq(
  df,
  ...,
  group_by_col = NULL,
  col_names = c("Variable", "Values", "n", "rel.freq", "rel.valid.freq"),
  col_names_groups = c("grouping.by", "groups", "rel.group.freq"),
  decimals = 2,
  show_warnings = TRUE,
  total = TRUE,
  total_by_group = TRUE,
  sort_by_values = FALSE,
  sort_by_freq = FALSE,
  sort_by_percent = FALSE,
  sort_decreasing = TRUE,
  debug = FALSE
)

Arguments

df	data
...	variables (no quotes needed)
group_by_col	column used to group the other variables
col_names	vector with names for the 4 columns
col_names_groups	vector with the names of the 2 columns regarding grouping
decimals	number of decimals to show
show_warnings	if you want to print any warning that may come up
total	total values of frequencies and percentajes without groups
total_by_group	total values of frequencies and percentajes within each group
sort_by_values	sort results by variable categories
sort_by_freq	sort results by frequency
sort_by_percent	sort results by perecentage
sort_decreasing	make the sorting descending
debug	show debug information

Details

==========================================

Confidence Interval = p +/- z*(√p(1-p) / n)

where:

p: sample proportion z: the chosen z-value n: sample size

Title freq

The freq function creates a dataframe with the frequencies of the independent values in one or more variables passed as arguments. It can also give the information grouping said variable/s by a different one

Value

list of dataframes (1 per variable)

Examples

## Not run: 

data_ <- data.frame(AGE=sample(x = 65:100, size=30, replace = TRUE ),
                    HEIGHT=sample(x = 120:205, size=30, replace = TRUE ),
                    SEX=sample(x = c("Male", "Female"), prob = c(.5,.5), size = 30, replace = TRUE),
                    BLOND=sample(x = c("Yes", "No"), prob = c(.2,.8), size = 30, replace = TRUE)
)
data_ <- rbind(data_, list(NA,NA,NA,NA))
data_ <- rbind(data_, list(NA,NA,"Male",NA))
data_ <- rbind(data_, list(NA,NA,NA,"No"))



# -- regular freq
freq(data_, SEX)

# -- freq sorted by Value
freq(data_,SEX, sort_by_values = TRUE, sort_decreasing = FALSE)

# -- multiple variables
freq(data_, SEX, BLOND)

# -- one variable grouped by another
freq(data_, SEX, group_by_col = BLOND)

# -- one variable grouped by another, without groups totals
freq(data_, SEX, group_by_col = BLOND, total_by_group = FALSE)


## End(Not run)

feranpre/udaicR documentation built on July 15, 2022, 12:54 p.m.