Hands-on_Exercise 4D

Visualising Models

Author

patriciatrisno

Published

May 8, 2025

Modified

May 9, 2025

1 Overview

Funnel plot is a specially designed data visualisation for conducting unbiased comparison between outlets, stores or business entities. By the end of this hands-on exercise, you will gain hands-on experience on:

  • plotting funnel plots by using funnelPlotR package,
  • plotting static funnel plot by using ggplot2 package, and
  • plotting interactive funnel plot by using both plotly R and ggplot2 packages.

2 Getting Started

2.1 Installing and Launching R Packages

In this exercise, four R packages will be used. They are:

  • readr for importing csv into R.
  • FunnelPlotR for creating funnel plot.
  • ggplot2 for creating funnel plot manually.
  • knitr for building static html table.
  • plotly for creating interactive funnel plot.
Code 
pacman::p_load(tidyverse, FunnelPlotR, plotly, knitr)

2.2 Importing Data

In this section, COVID-19_DKI_Jakarta will be used. The data was downloaded from Open Data Covid-19 Provinsi DKI Jakarta portal. For this hands-on exercise, we are going to compare the cumulative COVID-19 cases and death by sub-district (i.e. kelurahan) as at 31st July 2021, DKI Jakarta.

The code chunk below imports the data into R and save it into a tibble data frame object called covid19.

Code 
covid19 <- read_csv("~/Documents/SMU/April Term 2/Visual Analytics/patriciatrisno/ISSS608-VAA/Hands-on_Ex/Hands-on_Ex04/data/COVID-19_DKI_Jakarta.csv") %>%
  mutate_if(is.character, as.factor)
Sub-district ID City District Sub-district Positive Recovered Death
3172051003 JAKARTA UTARA PADEMANGAN ANCOL 1776 1691 26
3173041007 JAKARTA BARAT TAMBORA ANGKE 1783 1720 29
3175041005 JAKARTA TIMUR KRAMAT JATI BALE KAMBANG 2049 1964 31
3175031003 JAKARTA TIMUR JATINEGARA BALI MESTER 827 797 13
3175101006 JAKARTA TIMUR CIPAYUNG BAMBU APUS 2866 2792 27
3174031002 JAKARTA SELATAN MAMPANG PRAPATAN BANGKA 1828 1757 26

3 Funnel Plot R methods

FunnelPlotR package uses ggplot to generate funnel plots. It requires a numerator (events of interest), denominator (population to be considered) and group. The key arguments selected for customisation are:

  • limit: plot limits (95 or 99).
  • label_outliers: to label outliers (true or false).
  • Poisson_limits: to add Poisson limits to the plot.
  • OD_adjust: to add overdispersed limits to the plot.
  • xrange and yrange: to specify the range to display for axes, acts like a zoom function.
  • Other aesthetic components such as graph title, axis labels etc.

3.1 Funnel Plot R methods: The basic plot

Attention!
What is wrong with the graph?

Observe and check part after!

A funnel plot object with 267 points of which 0 are outliers. 
Plot is adjusted for overdispersion. 
funnel_plot(
  .data = covid19,
  numerator = Positive,
  denominator = Death,
  group = `Sub-district`,
  title = "COVID-19 Fatality Rate vs. Positive Cases by Sub-District"
)

Things to learn from the code chunk above.

  • group in this function is different from the scatterplot. Here, it defines the level of the points to be plotted i.e. Sub-district, District or City. If Cityc is chosen, there are only six data points.
  • By default, data_typeargument is “SR”.
  • limit: Plot limits, accepted values are: 95 or 99, corresponding to 95% or 99.8% quantiles of the distribution.
Important

This graph doesn’t seem pleasing and useful isn’t it? It is hard for us the get what the plot is about moreover to understand the information!

That is a lot to be fixed!

Let’s check below !

3.2 Funnel Plot R methods: Makeover 1

In this part, we gonna fix the plot’s data type, axis ranges, and scaling to ensure the funnel plot accurately reflects COVID-19 fatality rates (proportions) and focuses on the relevant data range

A funnel plot object with 267 points of which 7 are outliers. 
Plot is adjusted for overdispersion. 
funnel_plot(
  .data = covid19,
  numerator = Death,
  denominator = Positive,
  group = `Sub-district`,
  title = "COVID-19 Fatality Rate vs. Positive Cases by Sub-District",
  data_type = "PR",     #<<
  xrange = c(0, 6500),  #<<
  yrange = c(0, 0.05)   #<<
)

Things to learn from the code chunk above. + data_type argument is used to change from default “SR” to “PR” (i.e. proportions). + xrange and yrange are used to set the range of x-axis and y-axis

What is Different?

Now we can see what this plot is about. However looking at the plot as a whole, there are a lot of details that not properly placed or arranged, even not properly explain the data.

3.3 Funnel Plot R methods: Makeover 2

Here we gonna look into axis label and its placement / arrangement.

A funnel plot object with 267 points of which 7 are outliers. 
Plot is adjusted for overdispersion. 
funnel_plot(
  .data = covid19,
  numerator = Death,
  denominator = Positive,
  group = `Sub-district`,
  data_type = "PR",   
  x_range = c(0, 6500),  
  y_range = c(0, 0.05),
  label = NA,
  title = "Cumulative COVID-19 Fatality Rate by Cumulative Total Number of COVID-19 Positive Cases", #<<           
  x_label = "Cumulative COVID-19 Positive Cases", #<<
  y_label = "Cumulative Fatality Rate"  #<<
)

Things to learn from the code chunk above.

  • label = NA argument is to removed the default label outliers feature.
  • title argument is used to add plot title.
  • x_label and y_label arguments are used to add/edit x-axis and y-axis titles.

4 Funnel Plot for Fair Visual Comparison: ggplot2 methods

In this section, you will gain hands-on experience on building funnel plots step-by-step by using ggplot2. It aims to enhance you working experience of ggplot2 to customise speciallised data visualisation like funnel plot.

4.1 Computing the basic derived fields

To plot the funnel plot from scratch, we need to derive cumulative death rate and standard error of cumulative death rate.

Code 
df <- covid19 %>%
  mutate(rate = Death / Positive) %>%
  mutate(rate.se = sqrt((rate*(1-rate)) / (Positive))) %>%
  filter(rate > 0)

df
# A tibble: 266 × 9
   `Sub-district ID` City       District `Sub-district` Positive Recovered Death
               <dbl> <fct>      <fct>    <fct>             <dbl>     <dbl> <dbl>
 1        3172051003 JAKARTA U… PADEMAN… ANCOL              1776      1691    26
 2        3173041007 JAKARTA B… TAMBORA  ANGKE              1783      1720    29
 3        3175041005 JAKARTA T… KRAMAT … BALE KAMBANG       2049      1964    31
 4        3175031003 JAKARTA T… JATINEG… BALI MESTER         827       797    13
 5        3175101006 JAKARTA T… CIPAYUNG BAMBU APUS         2866      2792    27
 6        3174031002 JAKARTA S… MAMPANG… BANGKA             1828      1757    26
 7        3175051002 JAKARTA T… PASAR R… BARU               2541      2433    37
 8        3175041004 JAKARTA T… KRAMAT … BATU AMPAR         3608      3445    68
 9        3171071002 JAKARTA P… TANAH A… BENDUNGAN HIL…     2012      1937    38
10        3175031002 JAKARTA T… JATINEG… BIDARA CINA        2900      2773    52
# ℹ 256 more rows
# ℹ 2 more variables: rate <dbl>, rate.se <dbl>

Next, the fit.mean is computed by using the code chunk below.

Code 
fit.mean <- weighted.mean(df$rate, 1/df$rate.se^2)

4.2 Calculate lower and upper limits for 95% and 99.9% CI

The code chunk below is used to compute the lower and upper limits for 95% confidence interval.

Code 
number.seq <- seq(1, max(df$Positive), 1)
number.ll95 <- fit.mean - 1.96 * sqrt((fit.mean*(1-fit.mean)) / (number.seq)) 
number.ul95 <- fit.mean + 1.96 * sqrt((fit.mean*(1-fit.mean)) / (number.seq)) 
number.ll999 <- fit.mean - 3.29 * sqrt((fit.mean*(1-fit.mean)) / (number.seq)) 
number.ul999 <- fit.mean + 3.29 * sqrt((fit.mean*(1-fit.mean)) / (number.seq)) 
dfCI <- data.frame(number.ll95, number.ul95, number.ll999, 
                   number.ul999, number.seq, fit.mean)

4.3 Plotting a static funnel plot

In the code chunk below, ggplot2 functions are used to plot a static funnel plot.

p <- ggplot(df, aes(x = Positive, y = rate)) +
  geom_point(aes(label=`Sub-district`), 
             alpha=0.4) +
  geom_line(data = dfCI, 
            aes(x = number.seq, 
                y = number.ll95), 
            size = 0.4, 
            colour = "grey40", 
            linetype = "dashed") +
  geom_line(data = dfCI, 
            aes(x = number.seq, 
                y = number.ul95), 
            size = 0.4, 
            colour = "grey40", 
            linetype = "dashed") +
  geom_line(data = dfCI, 
            aes(x = number.seq, 
                y = number.ll999), 
            size = 0.4, 
            colour = "grey40") +
  geom_line(data = dfCI, 
            aes(x = number.seq, 
                y = number.ul999), 
            size = 0.4, 
            colour = "grey40") +
  geom_hline(data = dfCI, 
             aes(yintercept = fit.mean), 
             size = 0.4, 
             colour = "grey40") +
  coord_cartesian(ylim=c(0,0.05)) +
  annotate("text", x = 1, y = -0.13, label = "95%", size = 3, colour = "grey40") + 
  annotate("text", x = 4.5, y = -0.18, label = "99%", size = 3, colour = "grey40") + 
  ggtitle("Cumulative Fatality Rate by Cumulative Number of COVID-19 Cases") +
  xlab("Cumulative Number of COVID-19 Cases") + 
  ylab("Cumulative Fatality Rate") +
  theme_light() +
  theme(plot.title = element_text(size=12),
        legend.position = c(0.91,0.85), 
        legend.title = element_text(size=7),
        legend.text = element_text(size=7),
        legend.background = element_rect(colour = "grey60", linetype = "dotted"),
        legend.key.height = unit(0.3, "cm"))

p

4.4 Interactive Funnel Plot: plotly + ggplot2

The funnel plot created using ggplot2 functions can be made interactive with ggplotly() of plotly r package.

fp_ggplotly <- ggplotly(p,
  tooltip = c("label", 
              "x", 
              "y"))

References