R/data-smoking.R

In openintro: Data Sets and Supplemental Functions from 'OpenIntro' Textbooks and Labs

#' UK Smoking Data
#'
#' Survey data on smoking habits from the UK. The data set can be used for
#' analyzing the demographic characteristics of smokers and types of tobacco
#' consumed.
#'
#'
#' @name smoking
#' @docType data
#' @format A data frame with 1691 observations on the following 12 variables.
#' \describe{
#'   \item{gender}{Gender with levels \code{Female} and \code{Male}.}
#'   \item{age}{Age.}
#'   \item{marital_status}{Marital status with levels \code{Divorced},
#'   \code{Married}, \code{Separated}, \code{Single} and \code{Widowed}.}
#'   \item{highest_qualification}{Highest education level with levels
#'   \code{A Levels}, \code{Degree}, \code{GCSE/CSE}, \code{GCSE/O Level},
#'   \code{Higher/Sub Degree}, \code{No Qualification}, \code{ONC/BTEC} and
#'   \code{Other/Sub Degree}}
#'   \item{nationality}{Nationality with levels \code{British}, \code{English},
#'   \code{Irish}, \code{Scottish}, \code{Welsh}, \code{Other}, \code{Refused}
#'   and \code{Unknown}.}
#'   \item{ethnicity}{Ethnicity with levels \code{Asian}, \code{Black},
#'   \code{Chinese}, \code{Mixed}, \code{White} and \code{Refused}
#'   \code{Unknown}.}
#'   \item{gross_income}{Gross income with levels \code{Under 2,600},
#'   \code{2,600 to 5,200}, \code{5,200 to 10,400}, \code{10,400 to 15,600},
#'   \code{15,600 to 20,800}, \code{20,800 to 28,600}, \code{28,600 to 36,400},
#'   \code{Above 36,400}, \code{Refused} and \code{Unknown}.}
#'   \item{region}{Region with levels \code{London}, \code{Midlands & East Anglia},
#'   \code{Scotland}, \code{South East}, \code{South West}, \code{The North}
#'   and \code{Wales}}
#'   \item{smoke}{Smoking status with levels \code{No} and \code{Yes}}
#'   \item{amt_weekends}{Number of cigarettes smoked per day on weekends.}
#'   \item{amt_weekdays}{Number of cigarettes smoked per day on weekdays.}
#'   \item{type}{Type of cigarettes smoked with levels \code{Packets},
#'   \code{Hand-Rolled}, \code{Both/Mainly Packets} and \code{Both/Mainly Hand-Rolled}}
#'   }
#' @source National STEM Centre, Large Datasets from stats4schools,
#' \url{https://www.stem.org.uk/resources/elibrary/resource/28452/large-datasets-stats4schools}.
#' @keywords datasets smoking
#' @examples
#'
#' library(ggplot2)
#'
#' ggplot(smoking, aes(x = amt_weekends)) +
#'   geom_histogram(binwidth = 5)
#'
#' ggplot(smoking, aes(x = amt_weekdays)) +
#'   geom_histogram(binwidth = 5)
#'
#' ggplot(smoking, aes(x = gender, fill = smoke)) +
#'   geom_bar(position = "fill")
#'
#' ggplot(smoking, aes(x = marital_status, fill = smoke)) +
#'   geom_bar(position = "fill")
"smoking"