Hands-on Exercise 4

Visualising Distribution

Loading R packages

pacman::p_load(ggdist, ggridges, ggthemes,
               colorspace, tidyverse)

Importing the data

exam <- read_csv("data/Exam_data.csv")

Plotting Practice

Visualising Distribution with Ridgeline Plot

Plotting ridgeline graph: ggridges() method.

ggplot(exam, 
       aes(x = ENGLISH, 
           y = CLASS)) +
  geom_density_ridges(
    scale = 3,
    rel_min_height = 0.01,
    bandwidth = 3.4,
    fill = lighten("#7097BB", .3),
    color = "white"
  ) +
  scale_x_continuous(
    name = "English grades",
    expand = c(0, 0)
    ) +
  scale_y_discrete(name = NULL, expand = expansion(add = c(0.2, 2.6))) +
  theme_ridges()

Varying fill colors along the x axis.

ggplot(exam, 
       aes(x = ENGLISH, 
           y = CLASS,
           fill = stat(x))) +
  geom_density_ridges_gradient(
    scale = 3,
    rel_min_height = 0.01) +
  scale_fill_viridis_c(name = "Student_Score",
                       option = "C") +
  scale_x_continuous(
    name = "English grades",
    expand = c(0, 0)
  ) +
  scale_y_discrete(name = NULL, expand = expansion(add = c(0.2, 2.6))) +
  theme_ridges()

Mapping the probabilities directly onto colour.

ggplot(exam,
       aes(x = ENGLISH, 
           y = CLASS, 
           fill = 0.5 - abs(0.5-stat(ecdf)))) +
  stat_density_ridges(geom = "density_ridges_gradient", 
                      calc_ecdf = TRUE) +
  scale_fill_viridis_c(name = "Tail probability",
                       direction = -1) +
  theme_ridges()

Ridgeline plots with quantile lines.

ggplot(exam,
       aes(x = ENGLISH, 
           y = CLASS, 
           fill = factor(stat(quantile))
           )) +
  stat_density_ridges(
    geom = "density_ridges_gradient",
    calc_ecdf = TRUE, 
    quantiles = 4,
    quantile_lines = TRUE) +
  scale_fill_viridis_d(name = "Quartiles") +
  theme_ridges()

ggplot(exam,
       aes(x = ENGLISH, 
           y = CLASS, 
           fill = factor(stat(quantile))
           )) +
  stat_density_ridges(
    geom = "density_ridges_gradient",
    calc_ecdf = TRUE, 
    quantiles = c(0.025, 0.975)
    ) +
  scale_fill_manual(
    name = "Probability",
    values = c("#FF0000A0", "#A0A0A0A0", "#0000FFA0"),
    labels = c("(0, 0.025]", "(0.025, 0.975]", "(0.975, 1]")
  ) +
  theme_ridges()

Visualising Distribution with Raincloud Plot

Plotting a Half Eye graph.

ggplot(exam, 
       aes(x = RACE, 
           y = ENGLISH)) +
  stat_halfeye(adjust = 0.5,
               justification = -0.2,
               .width = 0,
               point_colour = NA)

Adding the boxplot with geom_boxplot().

ggplot(exam, 
       aes(x = RACE, 
           y = ENGLISH)) +
  stat_halfeye(adjust = 0.5,
               justification = -0.2,
               .width = 0,
               point_colour = NA) +
  geom_boxplot(width = .20,
               outlier.shape = NA)

Adding the Dot Plots with stat_dots().

ggplot(exam, 
       aes(x = RACE, 
           y = ENGLISH)) +
  stat_halfeye(adjust = 0.5,
               justification = -0.2,
               .width = 0,
               point_colour = NA) +
  geom_boxplot(width = .20,
               outlier.shape = NA) +
  stat_dots(side = "left", 
            justification = 1.2, 
            binwidth = .5,
            dotsize = 2)

ggplot(exam, 
       aes(x = RACE, 
           y = ENGLISH)) +
  stat_halfeye(adjust = 0.5,
               justification = -0.2,
               .width = 0,
               point_colour = NA) +
  geom_boxplot(width = .20,
               outlier.shape = NA) +
  stat_dots(side = "left", 
            justification = 1.2, 
            binwidth = .5,
            dotsize = 1.5) +
  coord_flip() +
  theme_economist()

Visual Statistical Analysis

Loading R packages_1

pacman::p_load(ggstatsplot, tidyverse)

Importing the data_1

exam <- read_csv("data/Exam_data.csv")

Plotting Practice_1

Visual Statistical Analysis with ggstatsplot

One-sample test: gghistostats() method.

set.seed(1234)

gghistostats(
  data = exam,
  x = ENGLISH,
  type = "bayes",
  test.value = 60,
  xlab = "English scores"
)

Two-sample mean test: ggbetweenstats().

ggbetweenstats(
  data = exam,
  x = GENDER, 
  y = MATHS,
  type = "np",
  messages = FALSE
)

Oneway ANOVA Test: ggbetweenstats() method.

ggbetweenstats(
  data = exam,
  x = RACE, 
  y = ENGLISH,
  type = "p",
  mean.ci = TRUE, 
  pairwise.comparisons = TRUE, 
  pairwise.display = "s",
  p.adjust.method = "fdr",
  messages = FALSE
)

Significant Test of Correlation: ggscatterstats().

ggscatterstats(
  data = exam,
  x = MATHS,
  y = ENGLISH,
  marginal = FALSE,
  )

Significant Test of Association (Depedence) : ggbarstats() methods.

exam1 <- exam %>% 
  mutate(MATHS_bins = 
           cut(MATHS, 
               breaks = c(0,60,75,85,100))
)
ggbarstats(exam1, 
           x = MATHS_bins, 
           y = GENDER)

Loading R packages_2

pacman::p_load(readxl, performance, parameters, see)

Importing the data_2

car_resale <- read_xls("data/ToyotaCorolla.xls", 
                       "data")
car_resale

# A tibble: 1,436 × 38
      Id Model    Price Age_08_04 Mfg_Month Mfg_Year     KM Quarterly_Tax Weight
   <dbl> <chr>    <dbl>     <dbl>     <dbl>    <dbl>  <dbl>         <dbl>  <dbl>
 1    81 TOYOTA … 18950        25         8     2002  20019           100   1180
 2     1 TOYOTA … 13500        23        10     2002  46986           210   1165
 3     2 TOYOTA … 13750        23        10     2002  72937           210   1165
 4     3  TOYOTA… 13950        24         9     2002  41711           210   1165
 5     4 TOYOTA … 14950        26         7     2002  48000           210   1165
 6     5 TOYOTA … 13750        30         3     2002  38500           210   1170
 7     6 TOYOTA … 12950        32         1     2002  61000           210   1170
 8     7  TOYOTA… 16900        27         6     2002  94612           210   1245
 9     8 TOYOTA … 18600        30         3     2002  75889           210   1245
10    44 TOYOTA … 16950        27         6     2002 110404           234   1255
# ℹ 1,426 more rows
# ℹ 29 more variables: Guarantee_Period <dbl>, HP_Bin <chr>, CC_bin <chr>,
#   Doors <dbl>, Gears <dbl>, Cylinders <dbl>, Fuel_Type <chr>, Color <chr>,
#   Met_Color <dbl>, Automatic <dbl>, Mfr_Guarantee <dbl>,
#   BOVAG_Guarantee <dbl>, ABS <dbl>, Airbag_1 <dbl>, Airbag_2 <dbl>,
#   Airco <dbl>, Automatic_airco <dbl>, Boardcomputer <dbl>, CD_Player <dbl>,
#   Central_Lock <dbl>, Powered_Windows <dbl>, Power_Steering <dbl>, …

Plotting Practice_2

Visualise model diagnostic and model parameters by using parameters package

Multiple Regression Model using lm().

model <- lm(Price ~ Age_08_04 + Mfg_Year + KM + 
              Weight + Guarantee_Period, data = car_resale)
model

Call:
lm(formula = Price ~ Age_08_04 + Mfg_Year + KM + Weight + Guarantee_Period, 
    data = car_resale)

Coefficients:
     (Intercept)         Age_08_04          Mfg_Year                KM  
      -2.637e+06        -1.409e+01         1.315e+03        -2.323e-02  
          Weight  Guarantee_Period  
       1.903e+01         2.770e+01  

Model Diagnostic: checking for multicolinearity.

check_collinearity(model)

# Check for Multicollinearity

Low Correlation

             Term  VIF     VIF 95% CI Increased SE Tolerance Tolerance 95% CI
               KM 1.46 [ 1.37,  1.57]         1.21      0.68     [0.64, 0.73]
           Weight 1.41 [ 1.32,  1.51]         1.19      0.71     [0.66, 0.76]
 Guarantee_Period 1.04 [ 1.01,  1.17]         1.02      0.97     [0.86, 0.99]

High Correlation

      Term   VIF     VIF 95% CI Increased SE Tolerance Tolerance 95% CI
 Age_08_04 31.07 [28.08, 34.38]         5.57      0.03     [0.03, 0.04]
  Mfg_Year 31.16 [28.16, 34.48]         5.58      0.03     [0.03, 0.04]

check_c <- check_collinearity(model)
plot(check_c)

Model Diagnostic: checking normality assumption.

model1 <- lm(Price ~ Age_08_04 + KM + 
              Weight + Guarantee_Period, data = car_resale)

check_n <- check_normality(model1)

plot(check_n)

Model Diagnostic: Check model for homogeneity of variances.

check_h <- check_heteroscedasticity(model1)

plot(check_h)

Model Diagnostic: Complete check.

check_model(model1)

Visualising Regression Parameters: see methods.

plot(parameters(model1))

Visualising Regression Parameters: ggcoefstats() methods.

ggcoefstats(model1, 
            output = "plot")

Visualising Uncertainty

Loading R packages

devtools::install_github("wilkelab/ungeviz")

pacman::p_load(ungeviz, plotly, crosstalk,
               DT, ggdist, ggridges,
               colorspace, gganimate, tidyverse)

package 'tweenr' successfully unpacked and MD5 sums checked
package 'gganimate' successfully unpacked and MD5 sums checked

The downloaded binary packages are in
    C:\Users\WHL\AppData\Local\Temp\RtmpYpOwG7\downloaded_packages

Importing the data

exam <- read_csv("data/Exam_data.csv")

Plotting Practice

Visualizing the uncertainty of point estimates: ggplot2 methods

my_sum <- exam %>%
  group_by(RACE) %>%
  summarise(
    n=n(),
    mean=mean(MATHS),
    sd=sd(MATHS)
    ) %>%
  mutate(se=sd/sqrt(n-1))

knitr::kable(head(my_sum), format = 'html')

RACE	n	mean	sd	se
Chinese	193	76.50777	15.69040	1.132357
Indian	12	60.66667	23.35237	7.041005
Malay	108	57.44444	21.13478	2.043177
Others	9	69.66667	10.72381	3.791438

Plotting standard error bars of point estimates.

ggplot(my_sum) +
  geom_errorbar(
    aes(x=RACE, 
        ymin=mean-se, 
        ymax=mean+se), 
    width=0.2, 
    colour="black", 
    alpha=0.9, 
    size=0.5) +
  geom_point(aes
           (x=RACE, 
            y=mean), 
           stat="identity", 
           color="red",
           size = 1.5,
           alpha=1) +
  ggtitle("Standard error of mean maths score by rac")

Plotting confidence interval of point estimates.

ggplot(my_sum) +
  geom_errorbar(
    aes(x=reorder(RACE, -mean), 
        ymin=mean-1.96*se, 
        ymax=mean+1.96*se), 
    width=0.2, 
    colour="black", 
    alpha=0.9, 
    size=0.5) +
  geom_point(aes
           (x=RACE, 
            y=mean), 
           stat="identity", 
           color="red",
           size = 1.5,
           alpha=1) +
  labs(x = "Maths score",
       title = "95% confidence interval of mean maths score by race")

Visualizing the uncertainty of point estimates with interactive error bars.

shared_df = SharedData$new(my_sum)

bscols(widths = c(4,8),
       ggplotly((ggplot(shared_df) +
                   geom_errorbar(aes(
                     x=reorder(RACE, -mean),
                     ymin=mean-2.58*se, 
                     ymax=mean+2.58*se), 
                     width=0.2, 
                     colour="black", 
                     alpha=0.9, 
                     size=0.5) +
                   geom_point(aes(
                     x=RACE, 
                     y=mean, 
                     text = paste("Race:", `RACE`, 
                                  "<br>N:", `n`,
                                  "<br>Avg. Scores:", round(mean, digits = 2),
                                  "<br>95% CI:[", 
                                  round((mean-2.58*se), digits = 2), ",",
                                  round((mean+2.58*se), digits = 2),"]")),
                     stat="identity", 
                     color="red", 
                     size = 1.5, 
                     alpha=1) + 
                   xlab("Race") + 
                   ylab("Average Scores") + 
                   theme_minimal() + 
                   theme(axis.text.x = element_text(
                     angle = 45, vjust = 0.5, hjust=1)) +
                   ggtitle("99% Confidence interval of average /<br>maths scores by race")), 
                tooltip = "text"), 
       DT::datatable(shared_df, 
                     rownames = FALSE, 
                     class="compact", 
                     width="100%", 
                     options = list(pageLength = 10,
                                    scrollX=T), 
                     colnames = c("No. of pupils", 
                                  "Avg Scores",
                                  "Std Dev",
                                  "Std Error")) %>%
         formatRound(columns=c('mean', 'sd', 'se'),
                     digits=2))

Visualising Uncertainty: ggdist package

Visualizing the uncertainty of point estimates: ggdist methods.

exam %>%
  ggplot(aes(x = RACE, 
             y = MATHS)) +
  stat_pointinterval() +
  labs(
    title = "Visualising confidence intervals of mean math score",
    subtitle = "Mean Point + Multiple-interval plot")

exam %>%
  ggplot(aes(x = RACE, y = MATHS)) +
  stat_pointinterval(.width = 0.95,
  .point = median,
  .interval = qi) +
  labs(
    title = "Visualising confidence intervals of median math score",
    subtitle = "Median Point + Multiple-interval plot")

exam %>%
  ggplot(aes(x = RACE, 
             y = MATHS)) +
  stat_pointinterval(
    show.legend = FALSE) +   
  labs(
    title = "Visualising confidence intervals of mean math score",
    subtitle = "Mean Point + Multiple-interval plot")

exam %>%
  ggplot(aes(x = RACE, 
             y = MATHS)) +
  stat_gradientinterval(   
    fill = "skyblue",      
    show.legend = TRUE     
  ) +                        
  labs(
    title = "Visualising confidence intervals of mean math score",
    subtitle = "Gradient + interval plot")

Visualising Uncertainty with Hypothetical Outcome Plots (HOPs)

devtools::install_github("wilkelab/ungeviz")

library(ungeviz)

Funnel Plots for Fair Comparisons

Loading R packages

pacman::p_load(tidyverse, FunnelPlotR, plotly, knitr)

Importing the data

covid19 <- read_csv("data/COVID-19_DKI_Jakarta.csv") %>%
  mutate_if(is.character, as.factor)

Plotting Practice

FunnelPlotR methods

FunnelPlotR methods: The basic plot.

funnel_plot(
  numerator = covid19$Positive,
  denominator = covid19$Death,
  group = covid19$`Sub-district`
)

A funnel plot object with 267 points of which 0 are outliers. 
Plot is adjusted for overdispersion. 

FunnelPlotR methods: Makeover 1.

funnel_plot(
  numerator = covid19$Death,
  denominator = covid19$Positive,
  group = covid19$`Sub-district`,
  data_type = "PR",     #<<
  xrange = c(0, 6500),  #<<
  yrange = c(0, 0.05)   #<<
)

A funnel plot object with 267 points of which 7 are outliers. 
Plot is adjusted for overdispersion. 

FunnelPlotR methods: Makeover 2.

funnel_plot(
  numerator = covid19$Death,
  denominator = covid19$Positive,
  group = covid19$`Sub-district`,
  data_type = "PR",   
  xrange = c(0, 6500),  
  yrange = 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"  #<<
)

A funnel plot object with 267 points of which 7 are outliers. 
Plot is adjusted for overdispersion. 

Funnel Plot for Fair Visual Comparison: ggplot2 methods

Computing the basic derived fields.

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

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

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

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)

Plotting 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

Interactive Funnel Plot: plotly + ggplot2.

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