From 8abefe28148b0dd1fb13a4929c2113a60f85bf70 Mon Sep 17 00:00:00 2001 From: phga Date: Sun, 18 Jul 2021 21:07:15 +0200 Subject: [PATCH] update: results own --- chap3/implementation.tex | 6 +-- chap5/results.tex | 83 +++++++++++++++++++++++++++++++++++++++- glossary.tex | 6 ++- ref_shelf.bib | 38 ++++++++++++++++++ 4 files changed, 127 insertions(+), 6 deletions(-) diff --git a/chap3/implementation.tex b/chap3/implementation.tex index f813e84..5ee9456 100644 --- a/chap3/implementation.tex +++ b/chap3/implementation.tex @@ -121,9 +121,6 @@ C = TL - INF; CER = roundToPrecision(IF / (TL + IF), 5); UER = roundToPrecision(INF / (TL + IF), 5); TER = roundToPrecision((INF + IF)/(TL + IF), 5); -KSPC = roundToPrecision(ISL / TL, 5); -// Correct / Any input char -accuracy = roundToPrecision(C / (TL + IF) * 100, 2); // Speed metrics // TL - 1 because the first char is entered at 0 seconds @@ -132,6 +129,9 @@ AdjWPM = roundToPrecision(WPM * Math.pow((1 - UER), a), 2); KSPS = roundToPrecision((ISL - 1) / TEST_TIME, 5); \end{minted} \end{listing} +% // Correct / Any input char +% accuracy = roundToPrecision(C / (TL + IF) * 100, 2); +% KSPC = roundToPrecision(ISL / TL, 5); For further implementation details on how input was captured or sent to the backend refer to the code in the online repository \footnote{TODO: GITHUB}. diff --git a/chap5/results.tex b/chap5/results.tex index b5e171b..079b22f 100644 --- a/chap5/results.tex +++ b/chap5/results.tex @@ -6,5 +6,84 @@ This section addresses the statistical analysis of the data obtained throughout the main, within-subject, user study (n = 24) that consisted of five repeated measurements. Because the data was from related, dependent groups, we used -repeated measurement \gls{ANOVA} if all required assumption were met and -Friedman's Test otherwise. +\textit{Repeated Measurement \gls{ANOVA}} if all required assumption were met +and \textit{Friedman's Test} otherwise. To identify the specific pairs of +treatments that differed significantly, we ran either \textit{Dependent T-Tests} +or \textit{Wilcoxon Signed Rank Tests} (both with \textit{Holm correction + (sequetially rejective Bonferroni test)} \cite{holm_correction}) as post-hoc +tests \cite{field_stats, downey_stats}. The reliability of the two sub-scales +(hedonic and pragmatic quality) in the \glsfirst{UEQ-S} was estimated using +\textit{Cronbach's alpha} \cite{tavakol_cronbachs_alpha}. All results are +reported statistically significant with an $\alpha$-level of $p < 0.05$. We used +95\% confidence intervals in visualizations of certain results. Normality of +data or residuals was checked using visual assessment of \gls{Q-Q} plots and +additionally \textit{Shapiro-Wilk} Test \cite{field_stats, downey_stats}. + +\subsubsection{Own Keyboard \& Reference Values} +\label{sec:res_OPC} +As mentioned in Section \ref{sec:main_design}, the keyboard \textit{Own} was +used as a reference for some metrics captured during the experiment. Since the +measurements with \textit{Own} took place at the start (T0\_1) and end (T0\_2) +of the experiment, we compared the results of both typing tests to detect +possible variations in performance due to fatigue. Using dependent T-tests, we +found that there were no significant differences in \glsfirst{KSPS} for T0\_1 (M += 5.39, sd = 1.49) compared to T0\_2 (M = 5.47, sd = 1.48, t = -1.53, p = +0.139), \glsfirst{UER} was overall negligible with T0\_1 (M = 0.005, sd = 0.013, +85th percentile = 0.0051) and T0\_2 (M = 0.008, sd = 0.028, 85th percentile = +0.0052) and \glsfirst{WPM} showed a trend to approach significance with T0\_1 (M += 54.2, sd = 14.7) compared to T0\_2 (M = 53.0, sd = 14.5, t = 1.92, p = +0.067). Further, using dependent T-tests we were able to find statistically +significant differences in \glsfirst{AdjWPM} for T0\_1 (M = 53.9, sd = 14.5) and +T0\_2 (M = 52.5, sd = 14.3, t = 2.44, p = 0.023), \glsfirst{CER} for T0\_1 (M = +0.057, sd = 0.028) and T0\_2 (M = 0.078, sd = 0.038, t = -3.54, p = 0.002) and +\glsfirst{TER} for T0\_1 (M = 0.063, sd = 0.031) and T0\_2 (M = 0.086, sd = +0.039, t = -4.27, p = 0.0003). Because of the differences, we decided to use the +means of all metrics gathered for each participant through T0\_1 and T0\_2 as +the reference values to compute the \textit{\gls{OPC}} for the test keyboards +(\textit{Athena, Aphrodite, Nyx} and \textit{Hera}). + +Additionally, using a dependent T-test, we compared the muscle activity (\% of +\glsfirst{MVC}) and found, that there are significant differences in left flexor +(\glsfirst{FDP} \& \glsfirst{FDS}) \%\gls{MVC} for T0\_1 (M = 12.0, sd = 8.27) +and T0\_2 (M = 8.53, sd = 7.16, t = 3.18, p = 0.004). Residuals of right flexor +(\gls{FDF} \& \gls{FDS}) were not normally distributed, therefore we used the +Wilcoxon Signed Rank Test and found an significant difference for T0\_1 (M = +10.8, sd = 8.18, Med = 9.52) and T0\_2 (M = 7.71, sd = 6.08, Med = 5.32, p = +0.021). It has to be noted, that we had to remove two erroneous measurements for +the right flexor (n = 22). No significant differences have been found in left or +right extensor (\glsfirst{ED}) \%\gls{MVC} between T0\_1 and T0\_2. + +\begin{table}[ht] + \centering + \ra{1.3} + \begin{tabular}{?l^l^l^l^l^l^l^l} + \toprule + \rowstyle{\itshape} + Y & Comparison & Statistic & p & Estimate & CI & Method & Alternative \\ + \midrule + WPM & T0\_1 - T0\_2 & 1.92 & 0.07 & 1.18 & [-0.09, 2.45] & T-test & two.sided \\ + AdjWPM & T0\_1 - T0\_2 & 2.44 & 0.02* & 1.35 & [0.21, 2.50] & T-test & two.sided \\ + KSPS & T0\_1 - T0\_2 & -1.53 & 0.14 & -0.08 & [-0.19, 0.03] & T-test & two.sided \\ + CER & T0\_1 - T0\_2 & -3.54 & 0.00* & -0.02 & [-0.03, -0.01] & T-test & two.sided \\ + TER & T0\_1 - T0\_2 & -4.27 & 0.00* & -0.02 & [-0.03, -0.01] & T-test & two.sided \\ + \%MVC_{LF} & T0\_1 - T0\_2 & 3.18 & 0.004* & 3.44 & [1.20, 5.68] & T-test & two.sided \\ + \%MVC_{LE} & T0\_1 - T0\_2 & 1.44 & 0.163 & 0.956 & [-0.42, 2.33] & T-test & two.sided \\ + + \%MVC_{RF} & T0\_1 - T0\_2 & 3.18 & 0.004* & 3.44 & [1.20, 5.68] & T-test & two.sided \\ + \%MVC_{RE} & T0\_1 - T0\_2 & 3.18 & 0.004 & 3.44 & [1.20, 5.68] & T-test & two.sided \\ + \bottomrule + \end{tabular} +\end{table} + +\subsection{Performance Metrics} +\label{sec:res_perf} +\subsubsection{Typing Speed} +\label{sec:res_typing_speed} +The typing speed for each individual keyboard and typing test was automatically +captured with the help of the typing test functionality offered by +\glsfirst{GoTT}. We captured \gls{WPM}, \gls{AdjWPM} and +\gls{KSPS} according to the formulas mentioned in Section +\ref{sec:meas_perf}. The individual measurements were then converted into +percentage values of the mean of the reference values gathered from typing tests +with keyboard \textit{Own}. None of the gathered data for the individual +treatments was distributed normally and thus, Friedman's Test was applied. diff --git a/glossary.tex b/glossary.tex index ebbb7c6..206f2dd 100644 --- a/glossary.tex +++ b/glossary.tex @@ -36,7 +36,11 @@ \newacronym{OLED}{OLED}{organic light-emitting diode} \newacronym{GMMK}{GMMK}{Glorious Modular Mechanical Keyboards} -\newacronym{ANOVA}{ANOVA}{analysis of variance} +\newacronym{ANOVA}{ANOVA}{Analysis Of Variance} +\newacronym{Q-Q}{Q-Q}{quantile-quantile} +\newacronym{OPC}{OPC}{percentage of keyboard ``Own''} + + \newglossaryentry{N}{ name={N}, diff --git a/ref_shelf.bib b/ref_shelf.bib index 893442e..865e796 100644 --- a/ref_shelf.bib +++ b/ref_shelf.bib @@ -872,4 +872,42 @@ urldate = {2021-07-06} pages={525--528}, year={1958}, publisher={Taylor \& Francis} +} + +@article{holm_correction, + ISSN = {03036898, 14679469}, + URL = {http://www.jstor.org/stable/4615733}, + abstract = {This paper presents a simple and widely applicable multiple test procedure of the sequentially rejective type, i.e. hypotheses are rejected one at a time until no further rejections can be done. It is shown that the test has a prescribed level of significance protection against error of the first kind for any combination of true hypotheses. The power properties of the test and a number of possible applications are also discussed.}, + author = {Sture Holm}, + journal = {Scandinavian Journal of Statistics}, + number = {2}, + pages = {65--70}, + publisher = {[Board of the Foundation of the Scandinavian Journal of Statistics, Wiley]}, + title = {A Simple Sequentially Rejective Multiple Test Procedure}, + volume = {6}, + year = {1979} +} + +@book{field_stats, + title={Discovering statistics using R}, + author={Field, Andy and Miles, Jeremy and Field, Zo{\"e}}, + year={2012}, + publisher={Sage publications} +} + +@book{downey_stats, + title={Think stats: exploratory data analysis}, + author={Downey, Allen}, + year={2014}, + publisher={" O'Reilly Media, Inc."} +} + +@article{tavakol_cronbachs_alpha, + title={Making sense of Cronbach's alpha}, + author={Tavakol, Mohsen and Dennick, Reg}, + journal={International journal of medical education}, + volume={2}, + pages={53}, + year={2011}, + publisher={IJME} } \ No newline at end of file