Foundations | Module 2 - Basic Data Type and Visualization Techniques (Mod. 2) Flashcards
Which attributes can be effectively displayed using a bubble chart?
* X-coordinate
* Shape
* Y-coordinate
* Bubble size
* Color
- X-coordinate
- Y-coordinate
- Bubble size
Which of the following visualisation techniques is best suited for displaying hierarchical data?
* Bubble charts
* Tree maps
* Scatter plots
* Scatter plots matrices
- Tree maps
What is a key benefit of using tree maps for data visualization?
Tree maps are excellent for visualizing part-to-whole relationships within hierarchical data. They represent hierarchical structures through nested rectangles, where the size of each rectangle is proportional to the value of the data it represents, making it easy to understand how individual parts contribute to the whole.
Which visualization technique would be most effective in showing correlations between multiple variables?
*Scatter plot matrices
*Bubble charts
*Tree maps
*Graph-based visualizations
*Scatter plot matrices
Which of the following are the limitations of bubble charts?
* Ineffective for displaying categorical data
* Limited to two variables
* Cannot show part-to-whole relationships
* Not suitable for hierarchical data
* Difficult to read with many bubbles
- Ineffective for displaying categorical data
- Cannot show part-to-whole relationships
- Not suitable for hierarchical data
- Difficult to read with many bubbles
Classify the variables from the dataset below into the three basic data types
- ID (A) - Ordinal
- Case (B) - Ordinal
- Species_No (C) - Nominal
- Species (D) - Nominal
- Organ (E) - Nominal
- Width (F) - Quantitative
- Lenght (G) - Quantitative
Taxonomy of data types
What are the three basic data types? Provide an example for each.
Taxonomy is a practice and science concerned with classification or categorization
1) Nominal: Non-order or non-numeric values.
Example: Categories like fruit types (apple, orange, pear) or colors (red, green, blue).
2) Ordinal: Ordered set of values, where the order matters but the differences between values are not uniform.
Example: Movie ratings (G, PG, PG-13, R) or rankings (1st, 2nd, 3rd).
3) Quantitative: Numeric values that can be measured and compared.
Subtypes:
3.1) Interval: Numeric values where the difference is meaningful, but there is no true zero.
Example: Temperature in Celsius.
3.2) Ratio: Numeric values with a true zero, allowing for meaningful comparisons and calculations.
Example: Height, weight, or age.
Explain the difference between nominal and ordinal data. Can you provide a real-world example for each?
Nominal: Non-order or non-numeric values.
Example: Categories like fruit types (apple, orange, pear) or colors (red, green, blue).
Ordinal: Ordered set of values, where the order matters but the differences between values are not uniform.
Example: Movie ratings (G, PG, PG-13, R) or rankings (1st, 2nd, 3rd).
Given a dataset with variables such as “Age,” “Fruit Preference,” and “Income,” classify each variable as nominal, ordinal, or quantitative.
- Age: Quantitative
- Fruit Preference: Nominal
- Income: Quantitative
Note:
While age can sometimes be treated as ordinal in specific contexts (like age groups: “0-18,” “19-35,” “36-50,” etc.), it is generally classified as a quantitative variable for the following reasons:
- Continuous Measurement: Age is typically measured on a continuous scale, allowing for precise calculations and comparisons.
- True Zero: Age has a true zero point (0 years), which allows for meaningful mathematical operations, such as calculating averages or differences.
- Mathematical Operations: You can perform various mathematical operations on age, such as addition and subtraction, which is characteristic of quantitative data.
It could be treated as ordinal, however, this is a transformation of the data rather than a reflection of its inherent nature.
What are examples of complex data types?
- 1D Linear: A single list of data items (e.g., a list of names).
- 2D: Data represented in two dimensions, such as maps.
- 3D: Volumetric data, like medical imaging (e.g., MRI scans).
- Temporal: Data that changes over time (e.g., stock prices over a year).
- Multidimensional: Data with multiple categories or dimensions (e.g., a dataset with various demographic factors).
- Hierarchical: Data organized in a tree-like structure (e.g., file directories).
- Network: Data represented as connections or relationships (e.g., social networks).
What is the difference between complex and basic data types?
Complex types expand on basic types to be able to represent different dimensions or relationships within the data.
Therefore, they often require more advanced visualisation techniques (scatter plot matrices, heatmaps, network diagrams, etc.)
For example, the name of employees within an organization can be viewed as basic nominal data. However, the relationships among them, e.g. who manages who or who reports to whom, expand on this, resulting in a more complex data type (hierarchical).
Data with various attributes (e.g., demographic data) is multidimensional, although individual attributes themselves fall into basic types.
Which of the following data visualization techniques is most effective for displaying trends over time, especially when tracking changes in data across a continuous time axis (e.g., days, months, years)?
Line chart
When designing a data dashboard, which practice is the most critical to ensuring that the dashboard is intuitive, effective, and user-friendly?
Minimize cognitive load
What is a key characteristic of ordinal data types in data visualization?
They have a meaningful order
Ordinal data types have a natural, meaningful order (e.g., rankings, satisfaction levels, educational degrees) but the intervals between these ordered values may not be equal. For example, the difference between “Excellent” and “Good” may not be the same as between “Good” and “Average.” This characteristic is important when choosing visualizations that emphasize ranking or order.
