R/data.R

In natstrat: Obtain Unweighted Natural Strata that Balance Many Covariates

#' Homocysteine and smoking example data
#'
#' NHANES 2005-2006 data on smoking and homocysteine levels in adults.
#'
#' @format A data frame with 2928 rows and 11 variables:
#' \describe{
#'   \item{SEQN}{NHANES identification number.}
#'   \item{z}{smoking status treatment indicator: 1 = daily smoker, 0 = never smoker.}
#'   \item{sex}{factor with levels "Male" and "Female".}
#'   \item{age}{age in years, 20-85, with 85 recorded for everyone >= 85 years.}
#'   \item{race}{factor with levels "Mexican American",
#'   "Other Hispanic", "Non-Hispanic White", "Non-Hispanic Black", and
#'   "Other Race - Including Multi-Racial".}
#'   \item{education}{factor with levels "< Grade 9",
#'   "9-11th grade", "High school grad/GED", "Some college or AA degree",
#'   "College graduate or above".}
#'   \item{povertyr}{ratio of family income to the poverty level,
#'   capped at 5 times poverty, has missing entries.}
#'   \item{bmi}{BMI (body mass index), has missing entries.}
#'   \item{cigsperday30}{cigarettes smoked per day, 0 for never smokers.}
#'   \item{cotinine}{blood cotinine level, a biomarker of recent exposure to tobacco.}
#'   \item{homocysteine}{homocysteine level.}
#' }
#'
#' @details The code used to generate this data is documented
#' in the source version of this package under `data-raw/`.
#' This data is composed of adults aged at least 20 years.
#' Individuals who have smoked at least 100 cigarettes
#' but do not now smoke at least 10 cigarettes daily are
#' excluded. Individuals with missing homocysteine
#' values, cotinine values, or smoking information are excluded.
#' After filtering for all these criteria,
#' one individual with unknown education remains and is also excluded.
#' Missing values remain in the poverty ratio and bmi covariates.
#' @source \url{https://wwwn.cdc.gov/nchs/nhanes/ContinuousNhanes/Default.aspx?BeginYear=2005}
#' @examples
#' data('nh0506')
"nh0506"

#' Homocysteine and smoking example data with multiple control groups
#'
#' NHANES 2005-2006 data on smoking and homocysteine levels in adults,
#' comparing daily smokers to never smokers and occasional smokers.
#'
#' @format A data frame with 4457 rows and 11 variables:
#' \describe{
#'   \item{SEQN}{NHANES identification number.}
#'   \item{z}{smoking status treatment factor: 0 = never smoker, 1 = some smoking, 2 = daily smoker.}
#'   \item{sex}{factor with levels "Male" and "Female".}
#'   \item{age}{age in years, 20-85, with 85 recorded for everyone >= 85 years.}
#'   \item{race}{factor with levels "Mexican American",
#'   "Other Hispanic", "Non-Hispanic White", "Non-Hispanic Black", and
#'   "Other Race - Including Multi-Racial".}
#'   \item{education}{factor with levels "< Grade 9",
#'   "9-11th grade", "High school grad/GED", "Some college or AA degree",
#'   "College graduate or above".}
#'   \item{povertyr}{ratio of family income to the poverty level,
#'   capped at 5 times poverty, has missing entries.}
#'   \item{bmi}{BMI (body mass index), has missing entries.}
#'   \item{cigsperday30}{cigarettes smoked per day, 0 for never smokers.}
#'   \item{cotinine}{blood cotinine level, a biomarker of recent exposure to tobacco.}
#'   \item{homocysteine}{homocysteine level.}
#' }
#'
#' @details The code used to generate this data is documented
#' in the source version of this package under `data-raw/`.
#' This data is composed of adults aged at least 20 years.
#' Individuals who have smoked at least 100 cigarettes
#' but do not now smoke at least 10 cigarettes daily are
#' excluded. Individuals with missing homocysteine
#' values, cotinine values, or smoking information are excluded.
#' After filtering for all these criteria,
#' five individuals with unknown education remain and are also excluded.
#' Missing values remain in the poverty ratio and bmi covariates.
#' @source \url{https://wwwn.cdc.gov/nchs/nhanes/ContinuousNhanes/Default.aspx?BeginYear=2005}
#' @examples
#' data('nh0506_3groups')
"nh0506_3groups"