Extracting Information from Data FRQ Practice

Responses receive AI feedback against a rubric after submission. Scores are practice estimates.

Question 1 of 5

Use the track table.

Athlete Practice days Race time_s Coach note
Lina 4 58 late start
Omar 6 55
Priya 5 56 new shoes
Quin 3 61
Rae 6 54

(a) List athletes with race time under 57 seconds. (b) Is "Priya is the unique fastest athlete" supported? (c) Compute the mean practice days for athletes who ran under 57 seconds. Show work.

Question 2 of 5

Shop data show that months with more umbrella sales also have more traffic accidents.

(a) State a correlation claim that fits the data wording. (b) Explain a lurking factor that could influence both variables. (c) Explain why selling umbrellas should not be assumed to cause accidents from this table alone.

Question 3 of 5

A research team keeps lake water samples (primary measurements) and a catalog listing sample IDs, collection GPS, and storage freezer ID.

(a) Which parts are metadata? (b) If a freezer ID is updated after moving a vial, do the chemical concentration values in the sample record change as a necessary result? (c) How can GPS metadata improve use of the dataset?

Question 4 of 5

Raw ratings: 5, five, 4, 04, 3, three.

(a) Describe cleaning to numeric ratings 1-5. (b) After cleaning to 5,5,4,4,3,3, what average rating is supported? (c) Explain one claim that unclean data would fail to support cleanly.

Question 5 of 5

A journalist has (1) a table of factory PM2.5 emissions by company and (2) a table of neighborhood asthma rates, with no shared geographic key.

(a) Why can't the journalist yet support "Company Z's emissions cause Neighborhood Y's asthma rate"? (b) What additional data would help test association geographically? (c) Even with a geographic link, why is causation still not automatic?