Data Dive 2.2

Can the city check its own rat numbers?

The city counts rat calls, and it also sends inspectors. Do the two agree?

You will need paper and a pencil, and a browser for step 3

2.20 / 6Leave

Step 1 of 5 · Your guess

What do you think?

Last time, New York's rat numbers turned out to count phone calls, not rats.

Someone has a fix. The city also sends inspectors to look for rats. Compare the inspections with the calls, they say, and you will know the truth.

Write it down before you lookWill comparing inspections with calls tell you where the rats are? Write yes or no, and one reason.

2.2 · Can the city check its own rat numbers?1 / 6Leave

Step 2 of 5 · Look

Inspectors sent for every call

New York City, 2024. One bar is one borough.

How to read it. Each bar is one borough. Its length is how many inspections the city sent for every rat call it got.

Find out

Which borough gets the most inspections per call? Which gets the fewest?
Why does the city send an inspector in the first place?

2.2 · Can the city check its own rat numbers?2 / 6Leave

Step 3 of 5 · Try it

Now you try it, on the same data

This opens the pool, the site's chart tool. The words in bold below are buttons and menus you will see on the screen.

Do these five things

Open the pool on this file: data.sfhsbta.com/thepool?file=two_instruments_nyc_rats.csv&mark=point

Under across, pick complaints. Under up, pick inspections. You get five dots, one per borough. Hover each dot and write down both numbers.
The dots almost make a straight line. Why? Which number caused the other?
Under up, pick failed_for_rat_activity. That is how many inspections actually found rats. Which boroughs change places?
Which borough stays near the bottom no matter what you pick? Why might that be?
Name one way to count rats that does not start with a phone call.

2.2 · Can the city check its own rat numbers?3 / 6Leave

Step 4 of 5 · Say it

Your answer, in one sentence

I think comparing inspections with calls <works or does not work> because <what the chart shows> and I checked it by <what you did to the chart>.

The last part matters most. It shows you did not just look at the chart, you tested it.

Here is one exampleI think comparing inspections with calls does not work, because the city only sends an inspector after someone calls. I checked by putting confirmed rats on the side, and Staten Island was still near the bottom, because few calls means few inspections.

2.2 · Can the city check its own rat numbers?4 / 6Leave

Step 5 of 5 · What you found

Check your numbers

8.0

inspections per call in the Bronx, the most

1.4

inspections per call on Staten Island, the fewest

Queens and Bronx

swap places between calls and confirmed rats

The big idea: numbers that cannot check each otherTwo numbers can only check each other if one did not cause the other. Here the calls cause the inspections, so of course they line up. That proves nothing about rats. Before you use one number to check another, ask where each one came from.

One more thing to think aboutIs there any count of rats that does not depend on someone calling? Who could collect it, and how?

2.2 · Can the city check its own rat numbers?5 / 6Leave

After the dive

The charts you used today

the bar

Bar length is the value, so it only means anything measured from zero. Start the axis anywhere else and the lengths stop matching the numbers.

What it leaves outOrder is a choice. Sorted by size it is a ranking; sorted by name it is a lookup; and the same bars say different things in each.

the scatter

Each dot is one thing measured twice. A tight cloud along a line means the two move together.

What it leaves outTwo things moving together is not one causing the other, and a third thing neither axis shows may be moving both.

library · ladder · dives · the pool · this dive’s worksheet

2.26 / 6Leave