In RobinHankin/hyper2: The Hyperdirichlet Distribution, Mark 2

set.seed(1)
knitr::opts_chunk$set(echo = TRUE)
library("hyper2")
library("disordR")

knitr::include_graphics(system.file("help/figures/hyper2.png", package = "hyper2"))

To cite the hyper2 package in publications, please use @hankin2017_rmd. Here we analyse results from the men's javelin, 2020 Summer Olympics.

javelin_table <- read.table("javelin.txt",header=TRUE)
a <- javelin_table # saves typing
javelin_table

Above, we see that Chopra threw 87.03m on his first throw, 87.58m on his second, and so on. Vadlejch threw 83.98m on his first throw, etc. We may convert this to a named vector with elements being the throw distances, and names being the competitors, using attemptstable2supp3():

javelin_vector <- attemptstable2supp3(a,decreasing=TRUE,give.supp=FALSE)
javelin_vector
o <- javelin_vector # saves typing

Above we see that Chopra threw the longest and second-longest throws of 87.58m and 87.03 respectively; Vadlejch threw the third-longest throw of 86.67m, and so on. NA entries correspond to no-throws. It is easy to plot the data in visual form:

n <- length(levels(as.factor(names(o))))
plot(o,pch=16,col=rainbow(n)[as.factor(names(o))])
legend("topright",pch=16,col=rainbow(n),legend=levels(as.factor(names(o))))

Now convert the attempts table to a hyper3 object, again using function attemptstable2supp3() but this time pass give.supp=TRUE. However, note that there are two reasonable interpretations: firstly, we simply ignore no-throws [in the package docs, these are sometimes referred to as "DNF", or "Did not finish", following Formula 1 terminology]:

javelin1 <- ordervec2supp3(v=names(o)[!is.na(o)])
H1 <- javelin1 # saves typing
javelin1_maxp  <- maxp(H1)
m1 <- javelin1_maxp

Secondly, we may treat no-throws as being inferior to any actual measured throw. To do this it is easiest to pass give.supp=TRUE to attemptstable2supp3():

javelin2 <- attemptstable2supp3(a,decreasing=TRUE,give.supp=TRUE)
H2 <- javelin2 # saves typing
javelin2_maxp <- maxp(H2)
m2 <- javelin2_maxp

Investigation:

rbind(one=m1,two=m2)
pie(m1)
pie(m2)
dotchart(m1,pch=16)
dotchart(m2,pch=16)
abline(0,1)
ordertransplot(m1,m2)

equalp.test(javelin1)
equalp.test(javelin2)

Package dataset {-}

Following lines create javelin.rda, residing in the data/ directory of the package.

save(javelin1,javelin2,javelin_table,javelin_vector,javelin1_maxp,javelin2_maxp,  file="javelin.rda")

References {-}

https://en.wikipedia.org/w/index.php?title=Athletics_at_the_2020_Summer_Olympics_%E2%80%93_Men%27s_javelin_throw&oldid=1051014985

RobinHankin/hyper2 documentation built on April 21, 2024, 11:38 a.m.