Type:	Package
Title:	Handling and Analysing EQ-5d Data
Version:	1.0.1
Maintainer:	Kim Rand <krand@mathsinhealth.com>
Description:	The EQ-5D is a widely-used standarized instrument for measuring Health Related Quality Of Life (HRQOL), developed by the EuroQol group https://euroqol.org/. It assesses five dimensions; mobility, self-care, usual activities, pain/discomfort, and anxiety/depression, using either a three-level (EQ-5D-3L) or five-level (EQ-5D-5L) scale. Scores from these dimensions are commonly converted into a single utility index using country-specific value sets, which are critical in clinical and economic evaluations of healthcare and in population health surveys. The eq5dsuite package enables users to calculate utility index values for the EQ-5D instruments, including crosswalk utilities using the original crosswalk developed by van Hout et al. (2012) <doi:10.1016/j.jval.2012.02.008> (mapping EQ-5D-5L responses to EQ-5D-3L index values), or the recently developed reverse crosswalk by van Hout et al. (2021) <doi:10.1016/j.jval.2021.03.009> (mapping EQ-5D-3L responses to EQ-5D-5L index values). Users are allowed to add and/or remove user-defined value sets. Additionally, the package provides tools to analyze EQ-5D data according to the recommended guidelines outlined in "Methods for Analyzing and Reporting EQ-5D data" by Devlin et al. (2020) <doi:10.1007/978-3-030-47622-9>.
License:	GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
Encoding:	UTF-8
LazyData:	true
RoxygenNote:	7.3.2
Depends:	R (≥ 3.5)
Imports:	dplyr, ggplot2, moments, RColorBrewer, rlang, scales, stringr, tidyr, rappdirs
NeedsCompilation:	no
Packaged:	2025-06-23 13:38:52 UTC; aeste
Author:	Kim Rand [aut, cre], Iryna Schlackow [aut], Anabel Estévez-Carrillo [aut]
Repository:	CRAN
Date/Publication:	2025-06-24 13:30:18 UTC

.EQxwrprob

Description

Takes a matrix of parameters for reverse crosswalk model, returns 243 x 25 matrix of state/level transition probabilities.

Usage

.EQxwrprob(par = NULL)

Arguments

Value

An 243 * 25 matrix with probabilities for state level transitions.

Add utility values to a data frame

Description

This function adds utility values to a data frame based on a specified version of EQ-5D and a country name.

Usage

.add_utility(df, eq5d_version, country)

Arguments

Value

A data frame with an additional column named 'utility' containing the calculated utility values. If the input country name is not found in the country_codes dataset, a list of available codes is printed, and subsequentyl an error message is displayed and the function stops.

Examples

df <- data.frame(state = c("11111", "11123", "32541"))
.add_utility(df, "5L", "DK")

Check the uniqueness of groups This function takes a data frame 'df' and a vector of columns 'group_by', and checks whether the combinations of values in the columns specified by 'group_by' are unique. If the combinations are not unique, a warning message is printed.

Description

Check the uniqueness of groups This function takes a data frame 'df' and a vector of columns 'group_by', and checks whether the combinations of values in the columns specified by 'group_by' are unique. If the combinations are not unique, a warning message is printed.

Usage

.check_uniqueness(df, group_by)

Arguments

Value

No return value, called for side effects: it will stop with an error if any group combinations are not unique.

Examples

df <- data.frame(id = c(1, 1, 1, 1, 2, 2),
                 fu = rep(c("baseline", "follow-up"), 3),
                 value = rnorm(6))
.check_uniqueness(df, c("id", "fu"))

Helper function for frequency of levels by dimensions tables

Description

Helper function for frequency of levels by dimensions tables

Usage

.freqtab(
  df,
  names_eq5d = NULL,
  name_fu = NULL,
  levels_fu = NULL,
  eq5d_version = NULL
)

Arguments

Value

Summary data frame.

Generate colours for PCHC figures

Description

This internal function generates a vector of colours based on the specified base colour. Currently only green and orange colours are implemented. The wrapper is used in Figures 2.2-2.4.

Usage

.gen_colours(col, n)

Arguments

Value

A vector of colours generated based on the specified base colour and number of colours.

Examples

# generate 10 colours for base colour "green"
.gen_colours("green", 10)
# generate 7 colours for base colour "orange"
.gen_colours("orange", 7)

Calculate the Level Frequency Score (LFS)

Description

This function calculates the Level Frequency Score (LFS) for a given EQ-5D state and a specified version of EQ-5D. If at least one domain contains a missing entry, the whole LFS is set to be NA.

Usage

.get_lfs(s, eq5d_version)

Arguments

Value

A character vector representing the calculated LFS.

Examples

.get_lfs("333", "3L") # returns 003
.get_lfs("333", "5L") # returns 00300
.get_lfs("12345", "5L") # returns 11111

Replace NULL names with default values

Description

This function takes in a list of parameters, which would be column names of the input data frame, and checks if they are null. Any nulls are replaced with default values, and the updated list of parameters is returned.

Usage

.get_names(df = NULL, ...)

Arguments

Value

a list of parameters with null entries replaced with default values.

Examples

.get_names(names_eq5d = c("mo", "sc", "ua", "pd", "ad"))
.get_names(names_eq5d = NULL, eq5d_version = NULL, name_vas = NULL)

Get the mode of a vector.

Description

This function calculates the mode of a numeric or character vector. If there are multiple modes, the first one is returned. The code is taken from an R help page.

Usage

.getmode(v)

Arguments

Value

The mode of 'v'.

Examples

.getmode(c(1, 2, 3, 3))
.getmode(c("a", "b", "b", "c"))

Modify ggplot2 theme

Description

Modify ggplot2 theme

Usage

.modify_ggplot_theme(p)

Arguments

Value

ggplot2 plot with modified theme

Wrapper to determine Paretian Classification of Health Change

Description

This internal function determines Paretian Classification of Health Change (PCHC) for each combination of the variables specified in the 'group_by' argument. It is used in the code for table_2_4-table_2_5 and figure_2_1-figure_2_4. An EQ-5D health state is deemed to be 'better' than another if it is better on at least one dimension and is no worse on any other dimension. An EQ-5D health state is deemed to be 'worse' than another if it is worse in at least one dimension and is no better in any other dimension.

Usage

.pchc(df, level_fu_1, add_noprobs = FALSE)

Arguments

Value

A data frame with PCHC value for each combination of the grouping variables. If 'add_noprobs' is TRUE, a separate classification for those without problems is also included.

Examples

df <- data.frame(id = c(1, 1, 2, 2),
                 fu = c(1, 2, 1, 2),
                 mo = c(1, 1, 1, 1),
                 sc = c(1, 1, 5, 1),
                 ua = c(1, 1, 4, 3),
                 pd = c(1, 1, 1, 3),
                 ad = c(1, 1, 1, 1))
.pchc(df, level_fu_1 = 1, add_noprobs = TRUE)

Wrapper to generate Paretian Classification of Health Change plot by dimension

Description

This internal function plots Paretian Classification of Health Change (PCHC) by dimension. The input is a data frame containing the information to plot, and the plot will contain bars representing the proportion of the total data that falls into each dimension, stacked by covariate. The wrapper is used in Figures 2.2-2.4.

Usage

.pchc_plot_by_dim(plot_data, ylab, title, cols, text_rotate = FALSE)

Arguments

Value

A ggplot object containing the PCHC plot.

Examples

df <- data.frame(
  name = rep(c("Dim1", "Dim2"), each = 2),
  p = c(0.6, 0.4, 0.7, 0.3),
  groupvar = rep(c("Group A", "Group B"), 2)
)
colors <- c("Group A" = "#1b9e77", "Group B" = "#d95f02")
.pchc_plot_by_dim(df, ylab = "Proportion", title = "Example Plot", cols = colors)

.pchctab: Changes in health according to the PCHC (Paretian Classification of Health Change)

Description

.pchctab: Changes in health according to the PCHC (Paretian Classification of Health Change)

Usage

.pchctab(
  df,
  name_id,
  name_groupvar,
  names_eq5d = NULL,
  name_fu = NULL,
  levels_fu = NULL,
  add_noprobs = FALSE
)

Arguments

Value

Summary data frame

Examples

.pchctab(df = example_data, 
  name_id = "id", 
  name_groupvar = "procedure", 
  name_fu = "time", 
  levels_fu = c('Pre-op', 'Post-op')
)

Data checking/preparation: EQ-5D variables

Description

This function prepares a data frame for analysis by extracting, processing, and adding columns for EQ-5D variables, including state, LSS (Level Sum Score), LFS (Level Frequency Score) and utility.

Usage

.prep_eq5d(
  df,
  names,
  add_state = FALSE,
  add_lss = FALSE,
  add_lfs = FALSE,
  add_utility = FALSE,
  eq5d_version = NULL,
  country = NULL
)

Arguments

Value

a modified data frame with EQ-5D domain columns renamed to default names, and, if necessary, with added columns for state, LSS, LFS, and/or utility. If any of the checks fail (e.g. EQ-5D columns are not in an integer format), an error message is displayed and the function is stopping.

Examples

set.seed(1234)
df <- data.frame(mo = sample(1:5, 3), sc = sample(1:5, 3), 
  ua = sample(1:5, 3), pd = sample(1:5, 3), ad = sample(1:5, 3))
.prep_eq5d(df, names = c("mo", "sc", "ua", "pd", "ad"), 
  add_state = TRUE, add_lss = TRUE)
.prep_eq5d(df, names = c("mo", "sc", "ua", "pd", "ad"),
  add_state = TRUE, add_lss = TRUE, add_lfs = TRUE, add_utility = TRUE,
  eq5d_version = "5L", country = "ES")

Data checking/preparation: follow-up variable

Description

This function prepares the follow-up (FU) variable for analysis by giving it a default name ('fu') and factorising

Usage

.prep_fu(df, name = NULL, levels = NULL)

Arguments

Value

A data frame with the follow-up variable renamed as "fu" and factorised.

Examples

df <- data.frame(id = c(1, 1, 2, 2),
  visit = c("baseline", "follow-up", "baseline", "follow-up"))
.prep_fu(df = df, name = "visit", levels = c("baseline", "follow-up"))

Data checking/preparation: VAS variable

Description

The function prepares the data for VAS (Visual Analogue Scale) analyses.

Usage

.prep_vas(df, name)

Arguments

Value

A modified data frame with the VAS score renamed to "vas". If any checks fail (e.g. column is not numeric), an error message is displayed and the function is stopping.

Examples

df <- data.frame(vas_score = c(20, 50, 80, NA, 100))
.prep_vas(df = df, name = "vas_score")
df <- data.frame(vas_score = c(20.5, 50, 80, NA, 100))
.prep_vas(df = df, name = "vas_score")

.pstate3t5

Description

Takes a N x 25 matrix with probabilities per level/dimension, and creates an N * 3125 matrix with probabilities per state

Usage

.pstate3t5(PPP)

Arguments

Value

An N * 3125 matrix with probabilities per state

.pstate5t3

Description

Takes a 15 x 5 matrix with probabilities per level/dimension, and creates an 3125x243 matrix with probabilities per state

Usage

.pstate5t3(probs = .EQxwprob)

Arguments

Value

An 3125x243 matrix with probabilities per state

Wrapper to summarise a continuous variable by follow-up (FU)

Description

This function summarizes a continuous variable for each follow-up (FU) and calculates various statistics such as mean, standard deviation, median, mode, kurtosis, skewness, minimum, maximum, range, and number of observations. It also reports the total sample size and the number (and proportion) of missing values for each FU. The input 'df' must contain an ordered FU variable and the continuous variable of interest. The name of the continuous variable must be specified using 'name_v'. The wrapper is used in Table 3.1 (for VAS) or Table 4.2 (for EQ-5D utility)

Usage

.summary_cts_by_fu(df, name_v)

Arguments

Value

Data frame with one row for each statistic and one column for each FU.

Examples

df <- data.frame(fu = c(1,1,2,2,3,3), 
                 vas = c(7,8,9,NA,7,6))
.summary_cts_by_fu(df, name_v = "vas")

Wrapper to calculate summary mean with 95% confidence interval

Description

This internal function calculates summary mean and 95% confidence interval of the utility variable, which can also be grouped. The function is used in Figures 4.2-4.4.

Usage

.summary_mean_ci(df, group_by)

Arguments

Value

A data frame with the mean, lower bound, and upper bound of the 95

Examples

df <- data.frame(group = c("A", "A", "B", "B"), 
                 utility = c(0.5, 0.7, 0.8, 0.9))
.summary_mean_ci(df, group_by = "group")

Wrapper for the repetitive code in function_table_2_1. Data frame summary

Description

This internal function summarises a data frame by grouping it based on the variables specified in the 'group_by' argument and calculates the frequency of each group. The output is used in Table 2.1

Usage

.summary_table_2_1(df, group_by)

Arguments

Value

A summarised data frame with groups defined by 'eq5d' and 'fu' variables, the count of observations in each group, and the frequency of each group.

Examples

set.seed(1234)
df <- data.frame(eq5d = rep(rnorm(5), 2),
                 fu = rep(c(1, 0, 1, 0, 1), 2))
.summary_table_2_1(df, c("eq5d", "fu"))

Summary wrapper for Table 4.3

Description

This internal function creates a summary of the data frame for Table 4.3. It groups the data by the variables specified in 'group_by' and calculates various summary statistics.

Usage

.summary_table_4_3(df, group_by)

Arguments

Value

A data frame with the summary statistics.

Examples

df <- data.frame(group = c("A", "A", "B", "B"), 
                 utility = c(0.5, 0.7, 0.8, 0.9))
.summary_table_4_3(df, group_by = "group")

Summary wrapper for Table 4.4

Description

This internal function creates a summary of the data frame for Table 4.4. It groups the data by the variables specified in 'group_by' and calculates various summary statistics.

Usage

.summary_table_4_4(df, group_by)

Arguments

Value

A data frame with the summary statistics.

Examples

df <- data.frame(group = c("A", "A", "B", "B"), 
                 utility = c(0.5, 0.7, 0.8, 0.9))
.summary_table_4_4(df, group_by = "group")

eq5d

Description

Get EQ-5D index values for the -3L, -5L, crosswalk (-3L value set applied to -5L health states), reverse crosswealk (-5L value set applied to -3L health states), and -Y-3L

Usage

eq5d(
  x,
  country = NULL,
  version = "5L",
  dim.names = c("mo", "sc", "ua", "pd", "ad")
)

Arguments

Value

A vector of values or data.frame with one column for each value set requested.

Examples

# US -3L value set
eq5d(c(11111, 12321, 32123, 33333), 'US', '3L') 
# Danish and US -5L value sets applied to -3L descriptives, i.e. reverse crosswalk
eq5d(make_all_EQ_states('3L'), c('DK', 'US'), 'XWR') 
# US -5L value set
eq5d(c(11111, 12321, 32153, 55555), 'US', '5L') 

eq5d3l

Description

Get EQ-5D-3L index values from individual responses to the five dimensions of the EQ-5D-3L.

Usage

eq5d3l(x, country = NULL, dim.names = c("mo", "sc", "ua", "pd", "ad"))

Arguments

Value

A vector of EQ-5D-3L values or data.frame with one column for each value set requested.

Examples

eq5d3l(c(11111, 12321, 32123, 33333), country = "US")
eq5d3l(make_all_EQ_states('3L'), c('DK', 'CA')) # Danish and Canada -3L value sets 

eq5d5l

Description

Get EQ-5D-5L index values from individual responses to the five dimensions of the EQ-5D-5L.

Usage

eq5d5l(x, country = NULL, dim.names = c("mo", "sc", "ua", "pd", "ad"))

Arguments

Value

A vector of EQ-5D-5L values or data.frame with one column for each value set requested.

Examples

eq5d5l(c(11111, 12321, 32423, 55555), 'IT') # Italy -5L value set
eq5d5l(make_all_EQ_states('5L'), c('ES', 'DE')) # Spanish and german value sets

eq5dy3l

Description

Get EQ-5D-Y3L index values from individual responses to the five dimensions of the EQ-5D-Y3L.

Usage

eq5dy3l(x, country = NULL, dim.names = c("mo", "sc", "ua", "pd", "ad"))

Arguments

Value

A vector of EQ-5D-Y3L values or data.frame with one column for each value set requested.

Examples

# Slovenia -Y3L value set
eq5dy3l(x = c(11111, 12321, 33333), country = 'SI') 
# Germany and Spain -Y3L value sets 
eq5dy3l(make_all_EQ_states('3L'), c('ES', 'DE')) # Spanish and german value sets

eqvs_add

Description

Add user-defined EQ-5D value set and corresponding crosswalk option.

Usage

eqvs_add(
  df,
  version = "5L",
  country = NULL,
  countryCode = NULL,
  VSCode = NULL,
  description = NULL,
  saveOption = 1,
  savePath = NULL
)

Arguments

Value

True/False, indicating success or error.

Examples

# make nonsense value set
new_df <- data.frame(state = make_all_EQ_indexes(), TEST = runif(3125))
# Add as value set for Fantasia
eqvs_add(
   new_df,
   version = "5L",
   country = 'Fantasia',
   countryCode = "MyCountry",
   VSCode = "FAN",
   saveOption = 1
)
eq5d5l(55555,country = "FAN")

eqvs_display

Description

Display available value sets, which can also be used as (reverse) crosswalks.

Usage

eqvs_display(version = "5L", return_df = FALSE)

Arguments

Value

Default NULL, if return_df == TRUE, returns a data.frame with the displayed information.

Examples

# Display available value sets.
eqvs_display

eqvs_drop

Description

Drop user-defined EQ-5D value set to reverse crosswalk options.

Usage

eqvs_drop(country = NULL, version = "5L", saveOption = 1, savePath = NULL)

Arguments

Value

True/False, indicating success or error.

Examples

  # make nonsense value set
  new_df <- data.frame(state = make_all_EQ_indexes(), TEST = runif(3125))
  # Add as value set for Fantasia
  eqvs_add(
   new_df,
   version = "5L",
   country = 'Fantasia',
   countryCode = "MyCountry",
   VSCode = "FAN",
   saveOption = 1
  )
  # Test the new value set
  eq5d5l(55555,country = "FAN")
  # Drop value set for Fantasia
  eqvs_drop(country = 'FAN', saveOption = 1)

eqvs_load

Description

Load cache data from a specified path.

Usage

eqvs_load(loadPath)

Arguments

Value

TRUE if loading is successful, FALSE otherwise.

eqxw

Description

Get crosswalk values

Usage

eqxw(x, country = NULL, dim.names = c("mo", "sc", "ua", "pd", "ad"))

Arguments

Value

A vector of reverse crosswalk values or data.frame with one column per reverse crosswalk set requested.

Examples

eqxw(c(11111, 12521, 32123, 55555), 'US')
eqxw(make_all_EQ_states('5L'), c('DK', 'US'))

eqxw_UK

Description

Crosswalks EQ-5D-5L responses to EQ-5D-3L utilities using NICE's mapping.

Usage

eqxw_UK(x, age, male, dim.names = c("mo", "sc", "ua", "pd", "ad"), bwidth = 0)

Arguments

Value

A vector or data frame with crosswalked EQ-5D-3L utilities.

Examples

eqxw_UK(c(11111, 12345, 32423, 55555), age = c(30, 40, 55, 70), male = c(1, 0, 1, 0))

eqxwr

Description

Get reverse crosswalk values

Usage

eqxwr(x, country = NULL, dim.names = c("mo", "sc", "ua", "pd", "ad"))

Arguments

Value

A vector of reverse crosswalk values or data.frame with one column per reverse crosswalk set requested.

Examples

eqxwr(c(11111, 12321, 32123, 33333), 'US')
eqxwr(make_all_EQ_states('3L'), c('DK', 'US'))

example_data

Description

A dataset containing patient-level data in a long format.

Usage

data(example_data)

Format

A data frame with 10000 rows and 14 variables:

id

double Patient id

time

character Follow-up (Pre-op / Post-op)

mo

double EQ-5D-5L Mobility dimension

sc

double EQ-5D-5L Self-care dimension

ua

double EQ-5D-5L Usual activities dimension

pd

double EQ-5D-5L Pain / discomfort dimension

ad

double EQ-5D-5L Anxiety/depression dimension

vas

double Value of the VAS scale measurememnt

providercode

character Provider code

procedure

character Type of surgery

year

character Year of intervention

ageband

character Age in pre-defined ranges

gender

character Patient's gender (Female / Male)

Figure 1.2.1: Paretian Classification of Health Change (PCHC) by Group This function computes PCHC categories between two time points for each subject, stratifies them by a grouping variable, and produces a single bar chart with side-by-side bars showing the distribution of PCHC categories.

Description

Figure 1.2.1: Paretian Classification of Health Change (PCHC) by Group This function computes PCHC categories between two time points for each subject, stratifies them by a grouping variable, and produces a single bar chart with side-by-side bars showing the distribution of PCHC categories.

Usage

figure_1_2_1(
  df,
  name_id,
  name_groupvar,
  names_eq5d = NULL,
  name_fu = NULL,
  levels_fu = NULL
)

Arguments

Value

A list with two elements:

Examples

result <- figure_1_2_1(
  df = example_data,
  name_id = "id",
  name_groupvar = "procedure",
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"),
  name_fu = "time",
  levels_fu = c("Pre-op", "Post-op")
)
result$p        # shows the plot
result$plot_data  # shows the summary table

Figure 1.2.2: Percentage of Respondents Who Improved in Each EQ-5D Dimension, by Group This function calculates how many respondents improved in each dimension between two time points and summarizes the results for each group. The, it prodcuces a dimension-focused chart illustrating improvement percentages by dimension.

Description

Figure 1.2.2: Percentage of Respondents Who Improved in Each EQ-5D Dimension, by Group This function calculates how many respondents improved in each dimension between two time points and summarizes the results for each group. The, it prodcuces a dimension-focused chart illustrating improvement percentages by dimension.

Usage

figure_1_2_2(
  df,
  name_id,
  name_groupvar,
  names_eq5d = NULL,
  name_fu = NULL,
  levels_fu = NULL
)

Arguments

Value

A list containing:

Examples

result <- figure_1_2_2(
  df = example_data,
  name_id = "id",
  name_groupvar = "procedure",
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"),
  name_fu = "time",
  levels_fu = c("Pre-op","Post-op")
)
result$p
result$plot_data

Figure 1.2.3: Percentage of Respondents Who Worsened in Each EQ-5D Dimension, by Group

Description

This function identifies respondents with a "Worsen" PCHC state (i.e., overall health state got worse between levels_fu[1] and levels_fu[2]), checks dimension-specific changes (e.g., mo_diff < 0), and summarizes by a grouping variable (e.g., procedure) and time points. It returns a data table and a ggplot object.

Usage

figure_1_2_3(
  df,
  name_id,
  name_groupvar,
  names_eq5d = NULL,
  name_fu = NULL,
  levels_fu = NULL
)

Arguments

Value

A list containing:

Examples

result <- figure_1_2_3(
  df = example_data,
  name_id = "id",
  name_groupvar = "procedure",
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"),
  name_fu = "time",
  levels_fu = c("Pre-op","Post-op")
)
result$p        # shows the plot
result$plot_data  # shows the summary table

Figure 1.2.4: Percentage of Respondents Who Had a Mixed Change Overall, by Dimension Improved or Worsened, Grouped by Procedure (or Other Grouping)

Description

This function focuses on patients classified as having "Mixed change" overall (i.e., some dimensions improved, others worsened). It then examines which dimensions improved vs. worsened for each subject. Results are summarized by a grouping variable (e.g., procedure) and time points. The final output is a table plus a ggplot object.

Usage

figure_1_2_4(
  df,
  name_id,
  name_groupvar,
  names_eq5d = NULL,
  name_fu = NULL,
  levels_fu = NULL
)

Arguments

Value

A list with two elements:

Examples

result <- figure_1_2_4(
  df = example_data,
  name_id = "id",
  name_groupvar = "procedure",
  names_eq5d = c("mo","sc","ua","pd","ad"),
  name_fu = "time",
  levels_fu = c("Pre-op","Post-op")
)
result$plot_data
result$p

Figure 1.2.5: Health Profile Grid (HPG) for Two Time Points

Description

This function creates a Health Profile Grid (HPG) for EQ-5D data, plotting each individual's change in health states (ranked from best to worst) between two time points. A diagonal reference line indicates no change; points above the line reflect improvement, and points below indicate deterioration.

Usage

figure_1_2_5(
  df,
  names_eq5d,
  name_fu,
  levels_fu = NULL,
  name_id,
  eq5d_version,
  country
)

Arguments

Value

A list with components:

Examples

tmp <- figure_1_2_5(
           df = example_data, 
           names_eq5d = c("mo", "sc", "ua", "pd", "ad"), 
           name_fu = "time", 
           levels_fu = c("Pre-op", "Post-op"), 
           name_id = "id", 
           eq5d_version = "3L", 
           country = "UK"
       )

Figure 1.3.1: EQ-5D values plotted against LSS

Description

Figure 1.3.1: EQ-5D values plotted against LSS

Usage

figure_1_3_1(df, names_eq5d = NULL, eq5d_version = NULL, country)

Arguments

Value

Summary plot and data used for plotting

Examples

df <- data.frame(make_all_EQ_states(version = "5L"))
tmp <- figure_1_3_1(
 df, 
 names_eq5d = c("mo", "sc", "ua", "pd", "ad"), 
 eq5d_version = "5L", 
 country = "US"
)
tmp$p
tmp$plot_data

Figure 1.3.2: EQ-5D values plotted against LFS

Description

Figure 1.3.2: EQ-5D values plotted against LFS

Usage

figure_1_3_2(df, names_eq5d = NULL, eq5d_version = NULL, country)

Arguments

Value

Summary plot and data used for plotting

Examples

tmp <- figure_1_3_2(
 example_data, 
 names_eq5d = c("mo", "sc", "ua", "pd", "ad"), 
 eq5d_version = "3L",
 country = "UK"
)
tmp$p
tmp$plot_data

Figure 1.4.1: Generate a Health State Density Curve (HSDC) for EQ-5D Data

Description

This function calculates and plots the Health State Density Curve (HSDC) for a given EQ-5D dataset. It concatenates dimension values to form health state profiles, filters out invalid states based on the specified EQ-5D version, then computes the cumulative distribution of profiles (profiles vs. observations). A diagonal reference line indicates a perfectly even distribution. The function also calculates the Health State Density Index (HSDI), representing how sharply the observed distribution deviates from the diagonal.

Usage

figure_1_4_1(df, names_eq5d, eq5d_version)

Arguments

Value

A list containing:

Examples

figure <- figure_1_4_1(
            df = example_data, 
            names_eq5d = c("mo", "sc", "ua", "pd", "ad"), 
            eq5d_version = "3L"
          )
figure$plot_data
figure$p

Figure 2.1: EQ VAS scores

Description

Figure 2.1: EQ VAS scores

Usage

figure_2_1(df, name_vas = NULL)

Arguments

Value

Summary plot and data used for plotting

Examples

tmp <- figure_2_1(example_data, name_vas = 'vas')
tmp$p
tmp$plot_data

Figure 2.2: Mid-point EQ VAS scores

Description

Figure 2.2: Mid-point EQ VAS scores

Usage

figure_2_2(df, name_vas = NULL)

Arguments

Value

Summary plot and data used for plotting

Examples

tmp <- figure_2_2(example_data, name_vas = 'vas')
tmp$p
tmp$plot_data

Figure 3.1: EQ-5D values by timepoints: mean values and 95% confidence intervals

Description

Figure 3.1: EQ-5D values by timepoints: mean values and 95% confidence intervals

Usage

figure_3_1(
  df,
  names_eq5d = NULL,
  name_fu = NULL,
  levels_fu = NULL,
  eq5d_version = NULL,
  country
)

Arguments

Value

Summary plot and data used for plotting

Examples

tmp <- figure_3_1(
 example_data,
 names_eq5d = c("mo", "sc", "ua", "pd", "ad"), 
 name_fu = "time",
 levels_fu = c('Pre-op', 'Post-op'),
 eq5d_version = "3L",
 country = "UK"
)
tmp$p
tmp$plot_data

Figure 3.2: Mean EQ-5D values and 95% confidence intervals: all vs by groupvar

Description

Figure 3.2: Mean EQ-5D values and 95% confidence intervals: all vs by groupvar

Usage

figure_3_2(df, names_eq5d = NULL, name_groupvar, eq5d_version = NULL, country)

Arguments

Value

Summary plot and data used for plotting

Examples

tmp <- figure_3_2(
 example_data,
 names_eq5d = c("mo", "sc", "ua", "pd", "ad"), 
 name_groupvar = "procedure",
 eq5d_version = "3L",
 country = "UK"
)
tmp$p
tmp$plot_data

Figure 3.3: EQ-5D values: smoothed lines and confidence intervals by groupvar

Description

Figure 3.3: EQ-5D values: smoothed lines and confidence intervals by groupvar

Usage

figure_3_3(
  df,
  names_eq5d = NULL,
  name_fu = NULL,
  levels_fu = NULL,
  name_groupvar,
  eq5d_version = NULL,
  country
)

Arguments

Value

Summary plot and data used for plotting

Examples

tmp <- figure_3_3(
 example_data,
 names_eq5d = c("mo", "sc", "ua", "pd", "ad"), 
 name_fu = "time",
 levels_fu = c('Pre-op', 'Post-op'),
 name_groupvar = "procedure",
 eq5d_version = "3L",
 country = "UK"
)
tmp$p
tmp$plot_data

Figure 3.4: EQ-5D values: smoothed lines and confidence intervals by groupvar

Description

Figure 3.4: EQ-5D values: smoothed lines and confidence intervals by groupvar

Usage

figure_3_4(df, names_eq5d = NULL, eq5d_version = NULL, country)

Arguments

Value

Summary plot and data used for plotting

Examples

tmp <- figure_3_4(
 example_data,
 names_eq5d = c("mo", "sc", "ua", "pd", "ad"), 
 eq5d_version = "3L",
 country = "UK"
)
tmp$p
tmp$plot_data

Figure 3.5: EQ-5D values: smoothed lines and confidence intervals by groupvar

Description

Figure 3.5: EQ-5D values: smoothed lines and confidence intervals by groupvar

Usage

figure_3_5(
  df,
  names_eq5d = NULL,
  name_vas = NULL,
  eq5d_version = NULL,
  country
)

Arguments

Value

Summary plot and data used for plotting

Examples

tmp <- figure_3_5(
   example_data,
   names_eq5d = c("mo", "sc", "ua", "pd", "ad"),
   name_vas = "vas",
   eq5d_version = "3L",
   country = "UK"
 )
tmp$p
tmp$plot_data

make_all_EQ_indexes

Description

Make a vector containing all 5-digit EQ-5D indexes for -3L or -5L version.

Usage

make_all_EQ_indexes(
  version = "5L",
  dim.names = c("mo", "sc", "ua", "pd", "ad")
)

Arguments

Value

A vector with 5-digit state indexes for all 243 (-3L) or 3125 (-5L) EQ-5D health states

Examples

make_all_EQ_indexes('3L')

make_all_EQ_states

Description

Make a data.frame with all health states defined by dimensions

Usage

make_all_EQ_states(
  version = "5L",
  dim.names = c("mo", "sc", "ua", "pd", "ad"),
  append_index = FALSE
)

Arguments

Value

A data.frame with 5 columns and 243 (-3L) or 3125 (-5L) health states

Examples

make_all_EQ_states('3L')

EQ_dummies

Description

Make a data.frame of all EQ-5D dummies relevant for e.g. regression modeling.

Usage

make_dummies(
  df,
  version = "5L",
  dim.names = c("mo", "sc", "ua", "pd", "ad"),
  drop_level_1 = TRUE,
  add_intercept = FALSE,
  incremental = FALSE,
  prepend = NULL,
  append = NULL,
  return_df = TRUE
)

Arguments

Value

A data.frame of dummy variables

Examples

make_dummies(make_all_EQ_states('3L'), '3L')

make_dummies(df = make_all_EQ_states('3L'), 
             version =  '3L', 
             incremental = TRUE, 
             add_intercept = TRUE, 
             prepend = "d_")

Table 1.1.1: Frequency of levels by dimensions, cross-sectional

Description

Table 1.1.1: Frequency of levels by dimensions, cross-sectional

Usage

table_1_1_1(df, names_eq5d = NULL, eq5d_version = NULL)

Arguments

Value

Summary data frame.

Examples

table_1_1_1(
 df = example_data[example_data$time == "Pre-op",],
 names_eq5d = c("mo", "sc", "ua", "pd", "ad"),
 eq5d_version = "3L"
)

Table 1.1.2: Frequency of levels by dimensions, separated by category

Description

Table 1.1.2: Frequency of levels by dimensions, separated by category

Usage

table_1_1_2(
  df,
  names_eq5d = NULL,
  name_cat = NULL,
  levels_cat = NULL,
  eq5d_version = NULL
)

Arguments

Value

Summary data frame.

Examples

table_1_1_2(
 df = example_data[example_data$time == "Pre-op",],
 names_eq5d = c("mo", "sc", "ua", "pd", "ad"),
 name_cat = "procedure",
 levels_cat = c("Hip Replacement", "Knee Replacement"),
 eq5d_version = "3L"
)

Table 1.1.3: Prevalence of the 10 most frequently observed self-reported health states

Description

Table 1.1.3: Prevalence of the 10 most frequently observed self-reported health states

Usage

table_1_1_3(df, names_eq5d = NULL, eq5d_version = NULL, n = 10)

Arguments

Value

Summary data frame

Examples

table_1_1_3(
  df = example_data[example_data$time == "Pre-op",],
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"),
  eq5d_version = "3L",
  n = 10
)

Table 1.2.1: Frequency of levels by dimensions, by follow-up

Description

Table 1.2.1: Frequency of levels by dimensions, by follow-up

Usage

table_1_2_1(
  df,
  names_eq5d = NULL,
  name_fu = NULL,
  levels_fu = NULL,
  eq5d_version = NULL
)

Arguments

Value

Summary data frame.

Examples

table_1_2_1(
  df = example_data,
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"),
  name_fu = "time",
  levels_fu = c("Pre-op" , "Post-op"),
  eq5d_version = "3L"
)

Table 1.2.2: Changes in health according to the PCHC (Paretian Classification of Health Change)

Description

Table 1.2.2: Changes in health according to the PCHC (Paretian Classification of Health Change)

Usage

table_1_2_2(
  df,
  name_id,
  name_groupvar,
  names_eq5d = NULL,
  name_fu = NULL,
  levels_fu = NULL
)

Arguments

Value

Summary data frame

Examples

table_1_2_2(
  df = example_data,
  name_id = "id",
  name_groupvar = "procedure",
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"),
  name_fu = "time",
  levels_fu = c("Pre-op" , "Post-op")
)

Table 1.2.3: Changes in health according to the PCHC, taking account of those with no problems

Description

Table 1.2.3: Changes in health according to the PCHC, taking account of those with no problems

Usage

table_1_2_3(
  df,
  name_id,
  name_groupvar,
  names_eq5d = NULL,
  name_fu = NULL,
  levels_fu = NULL
)

Arguments

Value

Summary data frame

Examples

table_1_2_3(
  df = example_data,
  name_id = "id",
  name_groupvar = "procedure",
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"),
  name_fu = "time",
  levels_fu = c("Pre-op" , "Post-op")
)

Table 1.2.4: Changes in levels in each dimension, percentages of total and of type of change

Description

Table 1.2.4: Changes in levels in each dimension, percentages of total and of type of change

Usage

table_1_2_4(df, name_id, names_eq5d = NULL, name_fu = NULL, levels_fu = NULL)

Arguments

Value

Summary data frame

Examples

table_1_2_4(
  df = example_data,
  name_id = "id",
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"),
  name_fu = "time",
  levels_fu = c("Pre-op" , "Post-op")
)

Table 1.3.1: Summary statistics for the EQ-5D values by all the different LSSs (Level Sum Scores)

Description

Table 1.3.1: Summary statistics for the EQ-5D values by all the different LSSs (Level Sum Scores)

Usage

table_1_3_1(df, names_eq5d = NULL, eq5d_version = NULL, country)

Arguments

Value

Summary data frame

Examples

df <- data.frame(make_all_EQ_states(version = "5L"))
table_1_3_1(
  df, 
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"), 
  eq5d_version = "3L", 
  country = "US"
)

Table 1.3.2: Distribution of the EQ-5D states by LFS (Level Frequency Score)

Description

Table 1.3.2: Distribution of the EQ-5D states by LFS (Level Frequency Score)

Usage

table_1_3_2(df, names_eq5d = NULL, eq5d_version = NULL)

Arguments

Value

Summary data frame

Examples

table_1_3_2(
  example_data, 
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"), 
  eq5d_version = "3L"
)

Table 1.3.3: Number of observations in the LFS (Level Frequency Score) according to the EQ-5D values

Description

Table 1.3.3: Number of observations in the LFS (Level Frequency Score) according to the EQ-5D values

Usage

table_1_3_3(df, names_eq5d = NULL, eq5d_version = NULL, country)

Arguments

Value

Summary data frame

Examples

table_1_3_3(
  example_data, 
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"), 
  eq5d_version = "3L",
  country = "UK"
)

Table 1.3.4: Summary statistics of EQ-5D values by LFS (Level Frequency Score)

Description

Table 1.3.4: Summary statistics of EQ-5D values by LFS (Level Frequency Score)

Usage

table_1_3_4(df, names_eq5d = NULL, eq5d_version = NULL, country)

Arguments

Value

Summary data frame

Examples

table_1_3_4(
  example_data, 
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"), 
  eq5d_version = "3L",
  country = "UK"
)

Table 2.1: EQ VAS Score by timepoints

Description

Table 2.1: EQ VAS Score by timepoints

Usage

table_2_1(df, name_vas = NULL, name_fu = NULL, levels_fu = NULL)

Arguments

Value

Summary data frame

Examples

table_2_1(
  example_data,
  name_vas = 'vas', 
  name_fu = 'time', 
  levels_fu = c('Pre-op', 'Post-op')
)

Table 2.2: EQ VAS Scores frequency of mid-points

Description

Table 2.2: EQ VAS Scores frequency of mid-points

Usage

table_2_2(df, name_vas = NULL, add_na_total = TRUE)

Arguments

Value

Summary data frame

Examples

table_2_2(
  example_data,
  name_vas = 'vas', 
  add_na_total =  TRUE
  )

Table 3.1: EQ-5D values: by timepoints

Description

Table 3.1: EQ-5D values: by timepoints

Usage

table_3_1(
  df,
  names_eq5d = NULL,
  name_fu = NULL,
  levels_fu = NULL,
  eq5d_version = NULL,
  country
)

Arguments

Value

Summary data frame

Examples

table_3_1(
  example_data,
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"), 
  name_fu = "time",
  levels_fu = c('Pre-op', 'Post-op'),
  eq5d_version = "3L",
  country = "UK"
)

Table 3.2 EQ-5D values: by groupvar

Description

Table 3.2 EQ-5D values: by groupvar

Usage

table_3_2(df, names_eq5d = NULL, name_groupvar, eq5d_version = NULL, country)

Arguments

Value

Summary data frame

Examples

table_3_2(
  example_data,
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"),
  name_groupvar = "procedure",
  eq5d_version = "3L",
  country = "UK"
)

Table 3.3 EQ-5D values: by age and groupvar

Description

Table 3.3 EQ-5D values: by age and groupvar

Usage

table_3_3(
  df,
  names_eq5d = NULL,
  name_fu = NULL,
  levels_fu = NULL,
  name_groupvar,
  name_age,
  eq5d_version = NULL,
  country
)

Arguments

Value

Summary data frame

Examples

example_data$ageband <- factor(
  example_data$ageband,
  levels = c("20 to 29", "30 to 39", "40 to 49", "50 to 59", "60 to 69", "70 to 79", "80 to 89")
)
example_data <- example_data[example_data$gender %in% c("Male", "Female"),]
table_3_3(
  example_data,
  names_eq5d = c("mo", "sc", "ua", "pd", "ad"),
  name_fu = "time",
  levels_fu = c('Pre-op', 'Post-op'),
  name_groupvar = "gender",
  name_age = "ageband",
  eq5d_version = "3L",
  country = "UK"
)

toEQ5Ddims

Description

Generate dimension vectors based on state index

Usage

toEQ5Ddims(x, dim.names = c("mo", "sc", "ua", "pd", "ad"))

Arguments

Value

A data.frame with 5 columns, one for each EQ-5D dimension, with names from dim.names argument.

Examples

toEQ5Ddims(c(12345, 54321, 12321))

toEQ5DIndex

Description

Generate EQ-5D state vector from data.frame/matrix or named vector with dimensions.

Usage

toEQ5Dindex(x, dim.names = c("mo", "sc", "ua", "pd", "ad"))

Arguments

Value

A vector of 5-digit EQ-5D health state indexes.

Examples

toEQ5Dindex(c(1,2,3,4,5))

example_data <- as.data.frame(matrix(data = c(1, 2, 3, 4, 5, 
                                              5, 4, 3, 2, 1, 
                                              3, 2, 1, 2, 3), 
                                     ncol = 5, 
                                     byrow = TRUE, 
                                     dimnames = list(NULL, c("mo", "sc", "ua", "pd", "ad"))))
example_data$irrelevant <- c(6,5,3)
toEQ5Dindex(example_data)