← Back to course
Statistics 9-12 / Week 05 / Wednesday
3/6
Week 05 · Correlation and Causation

Wednesday

Data Lab: r from pure chance
// How tight is the cloud, and what it does not prove
⏱ about 20 min

Wednesday: Data Lab, r From Pure Chance

"Ten tokens, numbered 1 to 10," Comet says, shaking the cloth bag. "Draw one for x, put it back, draw one for y."

"Eight points, no reason for any pattern," Wren says. He draws. "3 and 7." Again. "8 and 2."

Eight pairs later Nova plots the cloud. "Would you like a hint? Guess r before you look."

"Zero," Comet says. "Pure chance." Nova glows the number: -0.21.

"Not zero," Wren says. "Small, but not zero. What do you notice? Eight random points still make a little tilt."

They reshuffle and draw eight more. This time r is 0.05. "Different tilt, still small," Comet says.

"So a small r can happen by chance alone," Wren says. "A big r is much harder to get from a bag."

What you need

  • A cloth bag or cup with ten tokens or paper scraps numbered 1 to 10.
  • Graph paper, a pencil, a calculator or spreadsheet that finds r, and your Run Log.
  • A partner to record, and a grown-up who knows where you are.
Safety first
The lab stays at the table. Tokens and paper scraps are kept away from small children.
Cut paper scraps with scissors on paper. Nothing heavy is lifted alone.
Any running or walking this week is on the park loop or a safe path, never a road. A grown-up is aware and water is at hand.

Run the lab

  1. Shake the bag. Draw a token for x and write it down. Put it back and shake.
  2. Draw a token for y and write it down. Put it back. That is one point.
  3. Repeat until you have eight points. Plot them on graph paper, x across and y up.
  4. Guess r from the look of the cloud. Then find r with a calculator or spreadsheet.
  5. Shake, draw eight new points, and find r again. Repeat a third time if you have time.
  6. Write all your r values in a row. Most should be small. Notice how they differ.

The crew's lab log

Here are the crew's own two rounds from Nova's Run Log. Yours will differ, and that is the point.

RoundPoints (x, y)r
1(3, 7) (8, 2) (5, 5) (1, 9) (6, 4) (9, 8) (2, 3) (7, 6)-0.21
2(3, 2) (8, 7) (5, 9) (1, 5) (6, 3) (9, 6) (2, 8) (7, 4)0.05
Round 1 of the token lab: eight random points spread over the grid with no line, r about -0.21.
Round 2 of the token lab: eight new random points spread with no pattern, r about 0.05.

Random pairs have nothing linking x to y, yet r is rarely exactly 0. Chance alone makes a small tilt.

That is why the crew calls a size under 0.3 "little or none". It is the range chance can reach with a few points.

A size like 0.98 is far outside what the bag produced. Something real links practice and laps.

READ THE LAB
  • Read the question.
  • Tap your answer.
A scatter plot, Two tokens from the bag, first token across and second token up, with 8 points.Round 1 of the token lab gave r = -0.21. How would you describe the linear relationship?
A scatter plot, Two tokens from the bag, first token across and second token up, with 8 points.Round 1 points: (3, 7), (8, 2), (5, 5), (1, 9), (6, 4), (9, 8), (2, 3), (7, 6). What is r? (Round to 2 places.)
The crew's two random rounds gave two different small values of r. What does that show?
Practice and laps gave r = 0.98. Compared with the token lab, what does that suggest?
How many tokens are in the lab bag? Type the number.
WHY THIS EXERCISEEach token is equally likely, so x and y have no reason to move together.
StatementTrue or false?
Random pairs from a bag give r exactly 0 every time.?
A size of r under 0.3 is within the range chance often produces with a few points.?
8 + 8 = 16?
Putting the token back before the second draw keeps every draw the same.?
WHY THIS EXERCISESeeing chance produce a small r is what makes a large r mean something.
Draw your first round of eight random points. Write your guessed r and the real r beside the plot.

Good lab work. Tomorrow the formula for r, step by step, and the big question: does a strong r prove a cause?

← Tuesday