In edugonzaloalmorox/enseResp: Information on the Spanish Health Survey

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)

enseResp

Author: Edu Gonzalo Almorox

r badger::badge_devel("edugonzaloalmorox/enseResp", "blue")``r usethis::use_lifecycle_badge("experimental")

enseResp is a R package to tidily access healthcare data from the Spanish Health Survey (SHS) released by the Spanish Health Ministry. The main goal of enseResp is to provide data ready for analysis for researchers or other stakeholders interested in exploring health microdata in Spain. The current version of enseResp provides information about the SNS editions of 2017/19, 2011/12 and 2006/07 and compiles the surveys associated with the adult, children and household samples.

Installation

You can install the development version from GitHub with:

# install.packages("devtools")
devtools::install_github("edugonzaloalmorox/enseResp")

Load main datasets

This package contains surveys formatted to be convenient for being accessed and analysed. The current version of the package is composed of the following datsets:

adults_19: Dataset for adults survey for 2017/19
children_19: Dataset for children survey for 2017/19
household_19: Dataset for household survey for 2017/19
adults_12: Dataset for adults survey for 2011/12
children_12: Dataset for children survey for 2011/12
household_12: Dataset for household survey for 2011/12
adults_06: Dataset for adults survey for 2006/07
children_06: Dataset for children survey for 2006/07
household_06: Dataset for household survey for 2006/07

This is a basic example of how to obtain a dataset. For example, the survey of adults corresponding to 2017-19 survey.

library(enseResp)
library(dplyr)

enseResp::adults_19

Variables information

adults_19 contains 455 variables. adults_19_info provides information about the description of every variable (in Spanish). In addition it offers other information such as the type of variable, the positions in the text archive or the module the variable belongs to (for example, European Health Survey)

library(enseResp)
library(dplyr)
library(knitr)

enseResp::adults_19_info %>% 
  select(variable_ine, descripcion_del_campo) %>% 
  head(10) %>% kable()

Variables values

enseResp also provides information on the values for each variable. This is given by the labels datasets. adults_19_labels renders information on the values associated with the variables that compose adults_19. For example, lets check the values in the level of physical activity (variable T111)

library(enseResp)
library(dplyr)
library(knitr)

enseResp::adults_19_labels %>% 
  filter(variable_ine == "T111") %>%
 kable()

Example analysis

library(enseResp)
library(dplyr)
library(knitr)
library(ggplot2)

kids = enseResp::children_19
info = enseResp::children_19_info
labels = enseResp::children_19_labels

# Tidy data  --------------------------------

obesity = kids %>%
  count(CCAA, IMCm) %>%
  mutate_at(vars(IMCm), as.factor) %>%
  mutate(IMCm = case_when(IMCm == "1"~  "Peso insuficiente",
          IMCm == '2' ~ "Normopeso", 
          IMCm == '3' ~ "Sobrepeso", 
          IMCm == '4' ~ "Obesidad", 
          IMCm == '9' ~ "No consta", 
          is.na(IMCm) ~ "No disponible"))

obesity$IMCm = factor(obesity$IMCm , levels = c("No disponible", 
                                                "No consta", 
                                                "Peso insuficiente",
                                                "Normopeso",
                                                "Sobrepeso",
                                                "Obesidad"))

ccaa_lab = labels %>%
  filter(variable_ine == "CCAA") %>%
  select(valores_ine, valores)

obesity = obesity %>%
  left_join(., ccaa_lab, by = c("CCAA" = "valores_ine"))%>%
  select(ccaa = valores, IMCm, n)

# Plot ------------------------------------
 obesity %>%
  group_by(ccaa) %>%
  mutate(prop = n/sum(n)) %>%
  ungroup() %>%
  ggplot(aes(x = 2, y = prop, fill = IMCm)) +
  geom_bar(stat = "identity", width = 1, alpha = 0.85) +
  facet_wrap(facets=. ~ ccaa) +
  xlim(0.5, 2.5) +
  coord_polar(theta = "y") +
  theme_void() +
  scale_fill_brewer(palette = "Dark1") +
   labs(title = "Obesidad infantil", 
       subtitle = "Propocion IMC") +
  theme(legend.position = "bottom",
    legend.title = element_blank(), 
    panel.background  = element_blank(),
    strip.text.x = element_text(
      size = 4.75, color = "black", face = "bold"
    ))