dekker.one
Group work for a Monash Research Methods course
Merge branch 'master' of https://github.com/Dekker1/ResearchMethods
+70
-29
wk7/week7.tex
+70
-29
wk7/week7.tex
···
23
23
24
24
\section{Introduction} \label{sec:introduction}
25
25
26
+
In this report we have documented a series of hypothesis tests regarding provided data in high-ranking
27
+
Tennis players. The focus of these hypotheses concerns a player's handedness with regards to overall
28
+
ranking. We first provide an overview of how we address these notions, with visualisations and
29
+
descriptions of our overall methodology. Following this, we then provide a brief discussion of what we
30
+
can infer given our statistical analysis techniques.
31
+
26
32
\section{Method} \label{sec:method}
27
33
28
-
We are testing two hypotheses. The first hypothesis that we test is that tall players have an advantage over smaller players. The second hypothesis that we test is that left-handed players have an advantage over right-handed players. To build an intuition of how the data behaves with respect to the hypotheses we are testing, we created visual representations using tools from the Matplotlib, and Seaborn libraries and then we perform statistical tests to measure these effects.
34
+
We are testing two hypotheses. The first hypothesis that we test is that tall players have an advantage
35
+
over smaller players. The second hypothesis that we test is that left-handed players have an advantage
36
+
over right-handed players. To build an intuition of how the data behaves with respect to the hypotheses
37
+
we are testing, we created visual representations using tools from the Matplotlib, and Seaborn libraries
38
+
and then we perform statistical tests to measure these effects.
29
39
30
40
\subsection{Visualisation} \label{subsec:visualisation}
31
41
···
89
99
90
100
\section{Results} \label{sec:results}
91
101
102
+
We investigate both the advantage of height and the advantage of being
103
+
left-handed using a $\chi^2$ test and a T-test. For every test we will state
104
+
the exact hypothesis and the null-hypothesis.
105
+
92
106
\subsection{The advantage of height}
93
107
108
+
\textbf{$\chi^2$-test:} To test if there is an advantage of being tall we ran
109
+
a $\chi^2$ with the following hypotheses:\\
110
+
$H$: Players that are taller have a higher rank \\
111
+
$H_0$: The rank of a player is independent of their height \\
112
+
\\
113
+
To perform the test the players are groups into groups dependant on their
114
+
rank and if they are taller than the mean height for their gender. The
115
+
expected data is computed using the chances of being taller than the mean, and
116
+
the chance of being in the group of rankings. The data used is found in table
117
+
1.
118
+
94
119
\begin{table}[ht]
95
120
\centering
96
-
\label{tab:chi-height}
97
121
\begin{tabular}{|l|r|r|r|r|}
98
122
\hline
99
123
& \textbf{M: 168 - 188} & \textbf{M: 189 - 210} & \textbf{F: 155 - 171} & \textbf{F: 172 - 189} \\ \hline
···
105
129
& 7 / 8 \\
106
130
\hline
107
131
\end{tabular}
132
+
\label{tab:chiheight}
108
133
\caption{Observed / Expected values used for the $\chi^2$-test. The groups are divided by their rank (vertical) and, per gender, their height (horizontal).}
109
134
\end{table}
110
135
111
-
$$
112
-
\chi^2 \approx 7.697606186049128
113
-
$$
136
+
The $\chi^2$ value found is approximately $7.697606186049128$. With 12 degrees
137
+
of freedom our $p$-value will be $0.8082925814979871$
114
138
115
-
$$
116
-
df = (5-1)(4-1) = 12
117
-
$$
139
+
\textbf{T-test:} A slightly different hypothesis can be tested using a T-Test:
140
+
\\
141
+
$H$: Players that are taller have significantly more point \\
142
+
$H_0$: The points a player has is independent of their height \\
118
143
119
-
$$
120
-
\chi^2(7.69\dots,12) \approx 0.8082925814979871
121
-
$$
144
+
We ran this T-test twice, once for the women and once for the men, by
145
+
splitting the groups of players into two: one being taller than the mean
146
+
height, one being shorter than the mean height. Our T-test for the men
147
+
revealed a T-value of 1.711723, this has a p-value of 0.043815. For the women
148
+
the T-value found was 1.860241, which has a p-value of 0.032030.
122
149
150
+
\subsection{The advantage of left-handedness}
123
151
124
-
\textbf {t-test men:} T score: 1.711723, P score: 0.043815
125
-
126
-
\textbf {t-test women:} T score: 1.860241, P score: 0.032030
127
-
128
-
129
-
\subsection{The advantage of left-handedness}
152
+
\textbf{$\chi^2$-test:} To test if there is an advantage of being left-handed
153
+
we ran a $\chi^2$ with the following hypotheses:\\
154
+
$H$: Players that are left-handed have a higher rank \\
155
+
$H_0$: The rank of a player is independent their preferred hand \\
156
+
\\
157
+
To perform the test the players are groups into groups dependant on their rank
158
+
and if they play with their left hand. The expected data is computed using the
159
+
chances of being left-handed. The data used is found in table
160
+
2.
130
161
131
162
\begin{table}[ht]
132
163
\centering
133
-
\label{tab:chi-hand}
164
+
\label{tab:chihand}
134
165
\begin{tabular}{|l|l|l|l|l|l|}
135
166
\hline
136
167
& \textbf{1 - 99} & \textbf{100 - 199} & \textbf{200 - 299} & \textbf{300 - 399} & \textbf{400 - 499} \\
···
143
174
\caption{Observed / Expected values used for the $\chi^2$-test. The groups are divided by which hand they use (vertical) and their rank (horizontal).}
144
175
\end{table}
145
176
177
+
The $\chi^2$ value found is approximately $6.467312944404331$. With 4 degrees
178
+
of freedom our $p$-value will be $0.1668616190847413$
146
179
147
-
$$
148
-
\chi^2 \approx 6.467312944404331
149
-
$$
180
+
\textbf{T-test:} A slightly different hypothesis can be tested using a T-Test:
181
+
\\
182
+
$H$: Players that are left-handed have significantly more point \\
183
+
$H_0$: The points a player has is independent of their preferred hand \\
150
184
151
-
$$
152
-
df = (2-1)(5-1) = 4
153
-
$$
185
+
We ran this T-test by splitting the groups of players into two depending on
186
+
their preferred hand. Our T-test revealed a T-value of 0.451694,
187
+
this has a p-value of 0.325815.
154
188
155
-
$$
156
-
\chi^2(6.46\dots,4) \approx 0.1668616190847413
157
-
$$
158
189
159
-
\textbf {t-test:} T score: 0.451694, P score: 0.325815
190
+
\section{Discussion} \label{sec:discussion}
160
191
192
+
In our investigation we did not find any strong correlation between the
193
+
ranking of a player (or their number of points) and with which hand they
194
+
played or how tall they are. Most tests failed to pass the required p value of
195
+
$<0.05$. The only tests that did give us positive results are the T-test that
196
+
were conducted on the correlation between height and the number of points.
197
+
However, without the $\chi^2$-test confirming the correlation, the existence
198
+
of the correlation is questionable.
161
199
162
-
\section{Discussion} \label{sec:discussion}
200
+
These results might not be so surprising when the visual exploration is taken
201
+
into account. Only slight deviations are visible in our graphs, so the test
202
+
mainly confirmed our suspicion that no definitive correlation exists between
203
+
the different attributes.
163
204
164
205
\end{document}
+1
-1
wk8/week8.tex
+1
-1
wk8/week8.tex
···
47
47
The re-analysis is conducted on the data provided in the
48
48
paper\cite{dong2018methods}, using Python in conjunction with packages such as
49
49
pandas, matplotlib, numpy and seaborn, to process and visualise the data. As
50
-
aformentioned, only spatial data and the variables mentioned above are
50
+
aforementioned, only spatial data and the variables mentioned above are
51
51
considered, for the reference days and the change occuring Day 62 (day of
52
52
first socially disruptive event). The distribution of the difference between
53
53
the reference period and Day 62 is visualised by plotting a histogram for each