From fa2d73b624344e20ed811196d9f0f58a3a6e1829 Mon Sep 17 00:00:00 2001 From: "Jip J. Dekker" Date: Fri, 4 May 2018 10:25:21 +1000 Subject: [PATCH] Update title and add initial text for week 9 --- wk7/week7.tex | 2 +- wk8/week8.tex | 2 +- wk9/week9.tex | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 56 insertions(+), 3 deletions(-) diff --git a/wk7/week7.tex b/wk7/week7.tex index 1f56d51..3ddb765 100644 --- a/wk7/week7.tex +++ b/wk7/week7.tex @@ -13,7 +13,7 @@ \usepackage{bookmark} \begin{document} - \title{Evidence and experiments} + \title{Week 7 - Evidence and experiments} \author{ Jai Bheeman \and Kelvin Davis \and Jip J. Dekker \and Nelson Frew \and Tony Silvestere diff --git a/wk8/week8.tex b/wk8/week8.tex index 5b20948..f07edd2 100644 --- a/wk8/week8.tex +++ b/wk8/week8.tex @@ -14,7 +14,7 @@ \usepackage{bookmark} \begin{document} - \title{Evidence and experiments} + \title{Week 8 - Quantitative data analysis} \author{ Jai Bheeman \and Kelvin Davis \and Jip J. Dekker \and Nelson Frew \and Tony Silvestere diff --git a/wk9/week9.tex b/wk9/week9.tex index 5b20948..76b52a5 100644 --- a/wk9/week9.tex +++ b/wk9/week9.tex @@ -14,7 +14,7 @@ \usepackage{bookmark} \begin{document} - \title{Evidence and experiments} + \title{Week 9 - Correlation and Regression} \author{ Jai Bheeman \and Kelvin Davis \and Jip J. Dekker \and Nelson Frew \and Tony Silvestere @@ -24,9 +24,62 @@ \section{Introduction} \label{sec:introduction} \section{Method} \label{sec:method} + Provided with a set of 132 unique records of the top 200 male tennis players, + we sought to investigate the relationship between the height of particular + individuals with their respective weights. We conducted basic statistical + correlation analyses of the two variables with both Pearson's and Spearman's + correlation coefficients to achieve this. Further, to understand the + correlations more deeply, we carried out these correlation tests on the full + population of cleaned data (removed duplicates etc), alongside several random + samples and samples of ranking ranges within the top 200. To this end, we made + use of Microsoft Excel tools and functions of the Python library SciPy. \section{Results} \label{sec:results} + We performed seperate statistical analyses on 10 different samples of the + population, as well as the population itself. This included 5 separate subsets + of the rankings (top 20 and 50, middle 20, bottom 20 and 50) and 5 seperate + randomly chosen samples of 20 players. +\\ \\ + \Cref{tab:excel-results} shows the the results for the conducted tests. + + \begin{table}[ht] + \centering + \begin{tabular}{|l|r|r|} + \hline + \textbf{Test Set} & \textbf{Pearson's Coefficient} & \textbf{Spearman's Coefficient} \\ + \hline + \textbf{Population} & 0.77953 & 0.73925 \\ + \textbf{Top 20} & 0.80743 & 0.80345 \\ + \textbf{Middle 20} & 0.54134 & 0.36565 \\ + \textbf{Bottom 20} & 0.84046 & 0.88172 \\ + \textbf{Top 50} & 0.80072 & 0.78979 \\ + \textbf{Bottom 50} & 0.84237 & 0.81355 \\ + \textbf{Random Set \#1} & 0.84243 & 0.80237 \\ + \textbf{Random Set \#2} & 0.56564 & 0.58714 \\ + \textbf{Random Set \#3} & 0.59223 & 0.63662 \\ + \textbf{Random Set \#4} & 0.65091 & 0.58471 \\ + \textbf{Random Set \#5} & 0.86203 & 0.77832 + \\ \hline + \end{tabular} + \caption{TODO: Insert better caption for this table. All data is rounded to 5 decimal + places} + \label{tab:excel-results} + \end{table} \section{Discussion} \label{sec:discussion} + The results generally indicate that there is a fairly strong positive + correlation between the weight and weight of an individual tennis player, + within the top 200 male players. The population maintains a strong positive + correlation with both Pearson's and Spearman's correlation coefficients, + indicating that a relationship may exist. Our population samples show + promising consistency with this, with 6 seperate samples having values above + 0.6 with both techniques. The sample taken from the middle 20 players, + however, shows a relatively weaker correlation compared with the top 20 and + middle 20, which provides some insight into the distribution of the strongest + correlated heights and weights amongst the rankings. All five random samples + of 20 taken from the population indicate however that there does appear to be + a consistent trend through the population, which corresponds accurately with + the coefficients on the general population. + \end{document}