AP CSP topic 2.3
Extracting Information from Data
Data becomes useful information when we find patterns in it. Large data sets can reveal trends that no single record shows, but they may need cleaning to fix missing, duplicate, or inconsistent values first. Metadata is data about data, such as the date and location a photo was taken. Correlation in data does not prove that one thing causes another, and a data set may be biased if it does not represent everyone it claims to.
Extracting Information from Data vocabulary
- Information: The patterns and meaning people get from analyzing data.
- Metadata: Data that describes other data, such as a file's size, author, or creation date.
- Data cleaning: Fixing or removing incorrect, missing, or inconsistent data before analysis.
- Correlation: A relationship where two values tend to change together; it does not prove cause.
AP-style practice questions
Try each one, then open the answer. To save your progress, take this quiz in the interactive course.
A digital photo file includes the image itself plus the date taken, the camera model, and GPS coordinates.
1. Which of the following is metadata for this photo?
- (A) The colors of the pixels
- (B) The GPS coordinates of where it was taken
- (C) The objects shown in the image
- (D) The brightness of the image
Show answer
(B) The GPS coordinates of where it was taken Metadata describes the data, such as when and where a photo was taken.
A city finds that neighborhoods with more ice cream sales also have more sunburn cases.
2. Which of the following conclusions is best supported by this data?
- (A) Ice cream causes sunburn
- (B) Sunburn causes people to buy ice cream
- (C) The two values are correlated, but this data does not show that one causes the other
- (D) The data is too small to show anything
Show answer
(C) The two values are correlated, but this data does not show that one causes the other Correlation does not prove cause. Hot sunny weather likely increases both.
A survey form lets students type their grade level. Responses include "10", "tenth", "10th", and "Grade 10".
3. Which of the following should be done before counting how many students are in grade 10?
- (A) Delete all responses
- (B) Clean the data so every grade level uses the same format
- (C) Compress the data with lossy compression
- (D) Encrypt the responses
Show answer
(B) Clean the data so every grade level uses the same format Data cleaning makes inconsistent entries uniform so counts are accurate.
4. An app collects data only from users who own the newest phones, then claims the results describe all teenagers. Which of the following is the biggest problem?
- (A) The data set is too large
- (B) The data may be biased because it does not represent all teenagers
- (C) The data was not compressed
- (D) The data has no metadata
Show answer
(B) The data may be biased because it does not represent all teenagers A sample that leaves out groups can lead to biased conclusions.