hseclean.RmdThere are separate functions in hseclean to read each
year of HSE data. You must specify the link to where the data is stored.
The functions read in all variables related to tobacco and alcohol and
selected socio-economic and other descriptor variables.
test_2001 <- read_2001(
root = "X:/",
file = "ScHARR/PR_Consumption_TA/HSE/HSE 2001/UKDA-4628-tab/tab/hse01ai.tab"
)hseclean contains separate functions for reading the
survey data for each year, e.g. read_SHeS_2008().
There are separate functions that focus on processing a different
theme of socioeconomic, demographic and health variables. See
vignette("covariate_data"). Note that the order in which
the cleaning functions are applied can matter - as some functions use
variables that are cleaned by others.
Detailed description of how to clean the alcohol data are given in
vignette("alcohol_data"). As an example, here is the
workflow to plot the frquency of drinking among people who drank in
2017.
library(magrittr)
library(dplyr)
library(ggplot2)
# Frequency of drinking in 2017 among drinkers
root_dir <- "/Volumes/Shared/"
#root_dir <- "X:/"
read_2017(root = root_dir) %>%
clean_age %>%
clean_demographic %>%
alc_drink_now_allages %>%
filter(age < 90, age >= 8, drinks_now == "drinker") %>%
group_by(imd_quintile, age_cat) %>%
summarise(av_freq = mean(drink_freq_7d, na.rm = T)) %>%
ggplot(aes(x = imd_quintile, y = av_freq, fill = age_cat)) +
geom_bar(stat = "identity", position = "dodge") +
theme_minimal() +
ylab("average number of days drink in a week")See vignette("smoking_data").
library(magrittr)
# Wrap the individual cleaning functions in another function for applying to each year
cleandata <- function(data) {
data %<>%
clean_age %>%
clean_demographic %>%
clean_education %>%
clean_economic_status %>%
clean_family %>%
clean_income %>%
clean_health_and_bio %>%
smk_status %>%
smk_former %>%
smk_life_history %>%
smk_amount %>%
alc_drink_now_allages %>%
alc_weekmean_adult %>%
alc_sevenday_adult %>%
alc_sevenday_child %>%
select_data(
ages = 12:89,
years = 2001:2017,
# variables to retain
keep_vars = c("wt_int", "psu", "cluster", "year", "quarter",
"age", "age_cat", "sex", "imd_quintile",
"ethnicity_4cat", "ethnicity_2cat",
"degree", "relationship_status", "employ2cat", "social_grade", "kids", "income5cat",
"nssec3_lab", "man_nonman", "activity_lstweek", "eduend4cat",
"hse_cancer", "hse_endocrine", "hse_heart", "hse_mental", "hse_nervous", "hse_eye", "hse_ear", "hse_respir",
"hse_disgest", "hse_urinary", "hse_skin", "hse_muscskel", "hse_infect", "hse_blood",
"weight", "height", "bmi",
"cig_smoker_status", "years_since_quit", "years_reg_smoker", "cig_ever",
"cigs_per_day", "smoker_cat", "banded_consumption", "cig_type", "time_to_first_cig",
"smk_start_age", "smk_stop_age", "censor_age", "giveup_smk",
"drinks_now",
"drink_freq_7d", "n_days_drink", "peakday", "binge_cat",
"beer_units", "wine_units", "spirit_units", "rtd_units",
"weekmean",
"perc_spirit_units", "perc_wine_units", "perc_rtd_units", "perc_beer_units",
"drinker_cat",
"spirits_pref_cat", "wine_pref_cat", "rtd_pref_cat", "beer_pref_cat",
"total_units7_ch"
),
# The variables that must have complete cases
complete_vars = c("age", "sex", "year", "quarter", "psu", "cluster")
)
return(data)
}
# Read and clean each year of data and bind them together in one big dataset
data <- combine_years(list(
cleandata(read_2001(root = root_dir)),
cleandata(read_2002(root = root_dir)),
cleandata(read_2003(root = root_dir)),
cleandata(read_2004(root = root_dir)),
cleandata(read_2005(root = root_dir)),
cleandata(read_2006(root = root_dir)),
cleandata(read_2007(root = root_dir)),
cleandata(read_2008(root = root_dir)),
cleandata(read_2009(root = root_dir)),
cleandata(read_2010(root = root_dir)),
cleandata(read_2011(root = root_dir)),
cleandata(read_2012(root = root_dir)),
cleandata(read_2013(root = root_dir)),
cleandata(read_2014(root = root_dir)),
cleandata(read_2015(root = root_dir)),
cleandata(read_2016(root = root_dir)),
cleandata(read_2017(root = root_dir))
))
# clean the survey weights
data <- clean_surveyweights(data)The function survey::svyby() in the survey
R package is used by the function prop_summary() in
hseclean to estimate the uncertainty around proportions
calculated from a binary variable - prop_summary() was
designed to simplify the process of estimating smoking prevalence from
the HSE data, stratified by a specified set of variables.
prop_smokers <- prop_summary(
data = hse_data,
var_name = "smk.state",
levels_1 = "current",
levels_0 = c("former", "never"),
strat_vars = c("year", "sex", "imd_quintile")
)hseclean uses the function mice::mice() in
the mice R package, implemented in a basic way by the
impute_data_mice() function. See
vignette("missing_data").
# Run the imputation (takes a long time)
imp <- impute_data_mice(data = hse_data,
var_names = c("smk.state", "agegroup", "sex",
"imd_quintile", "degree", "kids", "income5cat",
"relationship_status", "employ2cat", "social_grade"),
var_methods = c("", "", "",
"polr", "logreg", "polr", "polr",
"polyreg", "logreg", "logreg"),
n_imputations = 5)
# imp$data is a single data.table containing all 5 imputed versions of the data
hse_data_imputed <- copy(imp$data)