(for Deborah Nolan and Louise Ryan, ISCB/ASC 2018, after Henry Reed)
Today we have naming of stats. Yesterday
We had assumptions. And tomorrow morning
We shall have testing of assumptions. But to-day
Today we have naming of stats. Data
sparkles and flashes through all of the students’ phones.
And today we have naming of stats.
This is the rank-sum Wilcoxon test. And this
is the one-sample Wilcoxon test, whose use you will see
when you are given one sample. And this is Levene’s test
Which in your case you have not got. Near-supercomputers
idle in pockets and desks, waiting for questions
Which in our case we have not got.
This is the t-test, which is always performed
with assumptions of unequal variance. Do not let me
see anyone do it with equal variances. You can easily do it
with the formulas back of the book. Global temperatures
dance in rising spirals, not letting any one see them do it with equal variances.
And this you can see is the list. The purpose of this is to
teach to the test, as you see. We can keep it constant from year to year.
We say this provides transparency. And constant from year to year
Bored students stare out of the window. They see it provides transparency.
They see it provides transparency: you can easily do it
with the formulas back of the book: like the list, and the test,
and the context, which in our case we have not got;
and the temperatures rising and the data and science and questions
constant from year to year. For today we have naming of stats.