Data unit test
A test on this unit alone, marked as a percentage and a letter grade — for the test your class is actually sitting, rather than for May. Answer everything, then submit once: seeing the answer to question 3 before attempting question 4 makes the final percentage meaningless.
Bias in a program
Why digital data is discrete
Sound as binary
Metadata
Personally identifiable information (PII)
Abstraction
Data cleaning
Open data
Images as binary
Why large datasets need programs
Number of values in n bits
Round-off error
Short answer 1. Define or explain: Bias in data collection
3 ptsShort answer 2. Define or explain: Overflow vs round-off
3 ptsShort answer 3. Define or explain: Text as binary
3 ptsShort answer 4. Define or explain: Analog vs digital data
3 ptsFree response
6 ptsA city transit agency collects a record for every trip taken on its buses. Each record contains the route number, the stop where the rider boarded, the time of boarding, and the fare category (adult, student, senior, reduced-fare). The agency wants to use this data to decide where to add service.
Identify one piece of information the agency could extract from this data that no single record contains, and describe the process used to extract it.
Explain the difference between the data itself and metadata, giving one example of metadata the agency might store alongside these records.
Explain one way the agency could use filtering to answer the question of which stops are busiest during the morning peak.
Explain why the agency should be cautious about concluding that a stop with few boardings has low demand.
Describe one specific privacy risk created by collecting these records, and one technique that reduces it.
Explain the difference between lossy and lossless compression, and state which would be appropriate if the agency needed to archive these records for later analysis.