Chapter 3 - Data Types Flashcards
Explain the differences in these structured data types:
- Categorical data
- Numerical data
Categorical data
Classifies data into groups - Usually described with words
(certain categories can be numbers like invoice #)
Numerical data
Meaningful numbers that can be summated to create meaningful data
What is this type of categorical data:
Nominal data
- Give some examples.
- How is it summarized?
Categorical data that cannot be ranked
Examples: Gender and transaction types
Summarized using counting and grouping.
What is this type of categorical data:
Ordinal data
- Give some examples
- How can it be summarized?
Categorical data with natural “order” or rank
Examples: Letter grades or rank
Summarized with counting, proportion, and ranking
What is this subcategory of numerical data:
Interval data
- Give an example
- How can this data be summarized?
Numerical data with equal intervals or distance between each observation but not definitive zero
Example: Temperature/SAT score
Can be summarized using:
- Counting/grouping
- Proportion
- Summing
- Averaging
What is this subcategory of numerical data:
Ratio Data
Give some examples
Numerical data with an equal and definitive interval between each data and has definitive zero
Examples: Salary, Sales
Note: may allow for negative numbers (like returns)
This is different from interval data.
What are these data types:
String/text/alphanumeric
String of characters (numbers and letters) that are interpreted as number of characters used.
What are these data types as interpreted by Tableau:
- Dimension
- Measure
Dimension
Any data point that is determined to be categorical (by Tableau)
Measure
Any data point that is determined to be numerical (by Tableau)
Why is receiving data “raw” the best?
Raw data is free of calculations.
Without an understanding of the fiels in a dataset, you would not know about the calculation.
What type of data are product reviews (1-5 stars)?
Categorical:
Ordinal
