Defines factors using value-label mapping

Description

A base-R approximation of case_match() (from 'dplyr'). Unlike case_match(), base_when() returns a factor. The levels will be ordered according to the order included in ... (see below).

Usage

base_match(original_variable, ..., as_factor = TRUE, string_for_na = "")

Arguments

Value

a factor

Examples

# load data
data(nhanes)

# define country
nhanes<-nhanes |> transform(
  country=base_match(dmdborn4,'USA'=1,'Other'=2)
)

Defines factors using logical objects

Description

A base-R approximation of case_when() (from 'dplyr'). Unlike case_when(), base_when() returns a factor. The levels will be ordered according to the order included in ... (see below).

Usage

base_when(..., as_factor = TRUE, string_for_na = "")

Arguments

Value

a factor

Examples

# load data
data(nhanes)

nhanes<-nhanes |>
  transform(
    cholesterol=base_when(
      'Desirable' = (lbxtc<200),
      'Borderline high' = (lbxtc>=200)&(lbxtc<240),
      'High' = (lbxtc>=240)
    )
  )

Tables variables

Description

Creates a table for a variable, mimicking count() (from 'dplyr'). ET stands for exploratory table.

Usage

et(data_frame, variable_name)

Arguments

Value

a data frame

Examples

# load data
data(nhanes)

# define country
nhanes<-nhanes |> transform(
  country=base_match(nhanes$dmdborn4,'USA'=1,'Other'=2)
)

# examine variable, with native piping
nhanes |> et(country)

# examine variable, with dollar-sign notation
et(nhanes$country)

National Health and Nutrition Examination Survey data

Description

A subset of data from the National Health and Nutrition Examination Survey

Usage

nhanes

Format

nhanes

A data frame with 8,153 rows and 3 columns:

seqn

a unique identifier

riagendr

gender

ridageyr

age

dmqmiliz

military status

dmdborn4

country of birth

lbxtc

total cholesterol

bpxosy1

systolic blood pressure

bpxosy2

systolic blood pressure

bpxodi1

diastolic blood pressure

bpxodi2

diastolic blood pressure

mcq010

asthma

smq020

smoking status

Source

https://wwwn.cdc.gov/nchs/nhanes/continuousnhanes/default.aspx?Cycle=2021-2023

Finds correlation coefficients, with support for piping

Description

A wrapper function to cor(), with support for piping.

Usage

p_cor(data, x, y, ...)

Arguments

Value

a numeric object

Examples

# load the data
data(nhanes)

# get correlation coefficient for systolic and diastolic
nhanes |> p_cor(bpxosy1,bpxodi1,use='complete.obs')

Fits generalized linear models, with support for piping

Description

A wrapper function to glm(), with the data argument listed first to support piping.

Usage

p_glm(data, formula, ...)

Arguments

Value

a glm object

Examples

# load the data
data(nhanes)

# define asthma
nhanes<-nhanes |> transform(
  asthma=base_match(mcq010,'No'=2,'History of asthma'=1)
)

# define smoking
nhanes<-nhanes |> transform(
  smoking=base_match(smq020,'No'=2,'History of smoking'=1)
)

# fit a model
mymodel<-nhanes |> p_glm(asthma~smoking,family=binomial(link='logit'))

# obtain model details
mymodel |> summary()

# obtain confidence interval
mymodel |> confint() |> exp()

Fits linear models, with support for piping

Description

A wrapper function to lm(), with the data argument listed first to support native piping.

Usage

p_lm(data, formula, ...)

Arguments

Value

an lm object

Examples

# load the data
data(nhanes)

# define country
nhanes<-nhanes |> transform(
  country=base_match(dmdborn4,'USA'=1,'Other'=2)
)

# fit a model
mymodel<-nhanes |> p_lm(bpxosy1~country)

# obtain model details
mymodel |> summary()

# obtain confidence interval
mymodel |> confint()

Conducts t-tests, with support for piping

Description

A wrapper function to t.test(), with the data argument listed first to support piping.

Usage

p_t.test(data, x = NULL, y = NULL, formula = NULL, ...)

Arguments

Value

an htest object

Examples

# load the data
data(nhanes)

# define smoking
nhanes<-nhanes |> transform(
  smoking=base_match(smq020,'No'=2,'History of smoking'=1)
)

# conduct a one-sample t-test
nhanes |> p_t.test(bpxosy1)

# conduct a two-sample t-test, using formula notation
nhanes |> p_t.test(bpxosy1~smoking)

# conduct a two-sample t-test, using formula notation
nhanes |> p_t.test(formula=bpxosy1~smoking)

# conduct a paired t-test, using x and y
nhanes |> p_t.test(bpxosy1,bpxosy2,paired=TRUE)

Tables variables, with support for piping

Description

A wrapper function to table(), with support for piping.

Usage

p_table(data, x, y = NULL, ...)

Arguments

Value

a table object

Examples

# load the data
data(nhanes)

# define smoking
nhanes<-nhanes |> transform(
  smoking=base_match(smq020,'No'=2,'History of smoking'=1)
)

# define asthma
nhanes<-nhanes |> transform(
  asthma=base_match(mcq010,'Asthma'=1,'No'=2)
)

# table smoking
nhanes |> p_table(smoking)

# table smoking and asthma
nhanes |> p_table(smoking,asthma)

Conducts Wilcoxon rank-sum tests, with support for piping

Description

A wrapper function to wilcox.test(), with the data argument listed first to support piping.

Usage

p_wilcox.test(data, x = NULL, y = NULL, formula = NULL, ...)

Arguments

Value

an htest object

Examples

# load the data
data(nhanes)

# define smoking
nhanes<-nhanes |> transform(
  smoking=base_match(smq020,'No'=2,'History of smoking'=1)
)

# conduct a one-sample wilcoxon test
nhanes |> p_wilcox.test(bpxosy1)

# conduct a two-sample wilcoxon test, using formula notation
nhanes |> p_wilcox.test(bpxosy1~smoking)

# conduct a two-sample wilcoxon test, using formula notation
nhanes |> p_wilcox.test(formula=bpxosy1~smoking)

# conduct a paired wilcoxon test, using x and y
nhanes |> p_wilcox.test(bpxosy1,bpxosy2,paired=TRUE)