|
Size: 990
Comment:
|
← Revision 4 as of 2017-09-14 19:17:28 ⇥
Size: 997
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 11: | Line 11: |
| 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. | --(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. )-- |
2017-09-14
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