the scatterplot matrix

Every pair of measures plotted against every other, so you can spot which ones move together.

What it leaves outPlot enough pairs and some will line up by chance alone. The more panels there are, the more likely a false one looks real.

4 · data science · cartesian · rung 4 · what isn’t there

weakest citation of its group · shipped on the platform · repeat: row/column -- no shape yet

Three worked examples

Sixteen small charts. Which one is worth a big chart?

Before you lookWrite down the pair of measures you would put on a full-size scatter.

civictwo_instruments_nyc_rats.csv · 5 rows · 5 columns

four rat measures, every pair plotted against every other

What to look atSixteen small scatters. Scan for the panels with a clear slope — those are the pairs worth a real chart.

This example draws itself with a small script. With scripting off you can still read every word on this page, and the file itself is at data/two_instruments_nyc_rats.csv.

earth and spacecorrelation_co2_temperature_exoplanets.csv · 33 rows · 4 columns

carbon dioxide, temperature and planet discoveries

What to look atCarbon and temperature move together. So do carbon and planet discoveries, and that one is nonsense — both just go up over time.

This example draws itself with a small script. With scripting off you can still read every word on this page, and the file itself is at data/correlation_co2_temperature_exoplanets.csv.

teen healthnhis_teen_group_profiles.csv · 29 rows · 12 columns

the same ten measures, every pair drawn as its own small scatter

What to look atScan for the panels with a clear slope. Anxiety and depression is the obvious one; find a second that surprises you, then check it in the table.

This example draws itself with a small script. With scripting off you can still read every word on this page, and the file itself is at data/nhis_teen_group_profiles.csv.

the pool

Now build one yourself.

The pool opens with this file and this shape already drawn, so your first move is to change something rather than to start from nothing. Bring your own CSV if you have one. Nothing is uploaded anywhere — the chart is drawn in your browser, your work saves there, and it downloads as a picture or as a project file you can open again.

Open the pool → the scatterplot matrix · two_instruments_nyc_rats.csv