Big Data and Privacy
Waze uses data from thousands of drivers to identify traffic jams. This is an example of:
Crowdsourcing
What is the maximum decimal value that can be represented using 4 bits?
15
Which compression type is required for archiving a legal contract where every word must be preserved?
Lossless
You are looking at a spreadsheet of 10,000 students and want to see only those from 'New York'. This is called:
Filtering
Which visualization is most effective for showing a trend in data over a continuous period of time?
Line Graph
What does PII stand for?
Personally identifiable information.
Which error occurs when a program tries to store the number 257 in an 8-bit register?
Overflow error
What is the main trade-off when choosing Lossy compression over Lossless?
Smaller file size for lower quality.
What is the process of fixing incomplete or incorrectly formatted data in a dataset?
Data Cleaning
Why is a bar chart with a Y-axis starting at 100 instead of 0 often considered misleading?
It makes small differences between values look much larger
Why is 'Big Data' typically processed using parallel systems?
Because the data is too large for a single computer to handle efficiency.
Why might $0.1 + 0.2$ result in $0.30000000000000004$ in many programming languages?
Round-off Error
If you compress a 10MB photo using Lossless compression and then decompress it, what happens to the size?
It stays at 10 MB
Which of the following is an example of metadata for a digital photo?
Date and time the photo was taken.
What is the primary reason for creating a data visualization like a scatter plot?
It help human identify patterns or correlations that are hard to see in raw numbers.
What is 'Re-identification' in the context of data privacy?
Combining anonymous data with other datasets to uncover a person's identity.
How many distinct values can be represented by a single Byte?
256
Which of these file formats is a common example of Lossy compression?
JPEG
True or False: Metadata can be used to track a person's location even if the image content is hidden.
Which chart type is best for showing how a single budget is divided into different departmental percentages?
Pie chart.
What is 'Re-identification' in the context of data privacy?
It leads to data being skewed because certain groups are underrepresented.
In the hexadecimal color code #FF0000, what does the 'FF' represent?
Max Red
Why is Lossy compression unsuitable for executable software (.exe files)?
Software requires every bit to be exact to function correctly.
When you group a dataset of 5,000 individual sales into a single 'Total Monthly Revenue' figure, you are:
Aggregating.
If a survey about local internet quality is only posted on a high-speed fiber-optic forum, the results will likely have: