= 2017-09-14 =
[[/Attendees]]

== Minutes ==
Ran Cory's bar-chart versus pie-chart experiment (available at http://piechartssuck.com/) with 3 participants, and got:

 * Bar-chart mean error: 2.133
 * Pie-chart mean error: 1.733
 * P-value: 0.50

--(Slightly surprising to swing the way of pie-chart estimating being more accurate, but the p-value indicates that the effect is small enough that we need more participants to reliably detect it. )--

Talked about whether the tick marks on bar-charts are biasing the experiment, and alternative ways to present the charts (''something'' is needed to show the user where "100%" is for a bar-chart).

Read Cory's code.  Discovered some tracking of subjects/observations may have been wrong, leading to a bad p-value.  Cory's going to fix up the code and try this again later.  However, the mean errors should be correct.

== Next Time ==
 * NEXT_MEETING_DATE
 * Be ready to discuss Chapter XXX of AnIntroductionToStatisticalLearning