You are on page 1of 17

Basic Data Types

MSBA 325

Fouad Zablith, PhD


Objectives

We will cover in this part the following data measurement levels:


- Nominal Data
- Ordinal Data
- Interval Data
- Ratio Data
We will also discuss:
- Discrete vs. Continuous Data
Objectives

- Data Variable vs. Data Type


- Categorical Data
- Qualitative vs. Quantitative Data
Nominal Data

- Unordered
- Consist of named categories
- Can be counted and used to calculate percentages
Levels of Measurement

- Cannot be averaged

Ex: What section of a store an item came from.

Dichotomous data: when there are only 2 categories available.


Ex: The answers to yes/no questions.
Nominal Data

Nominal data as percentages:


Levels of Measurement
Ordinal Data

- Have a natural ordering to the categories


- Can be counted
- Can be used to compute percentages
Levels of Measurement

Note: some fields discourage averaging ordinal data, whereas others consider it
common practice.
Ordinal Data

Numbering Ordinal Categories: Any set of numbers can be assigned to ordinal


categories as long as they are kept in order.
Levels of Measurement
Interval Data

- Numeric
- Zero doesn’t indicate absence
- Intervals between consecutive points of measurement are equal
Levels of Measurement

Examples of interval data: time of day, calendar years, temperature.


Ratio Data

- Numeric
- Very similar to interval data,
- But zero indicates absence of the thing being measured
Levels of Measurement

Examples of ratio data: height, weight, age, money.

• “11:30 to 11:45” is interval data, whereas “15 minutes” of waiting is ratio data.
Levels of Measurement Summary
Example
Can you identify which pieces of information are measured at each level (nominal,
ordinal, interval, and ratio) ?
Date: 06/01/2014 Time: 11:32am
Item Section Aisle Quantity Cost (US$) Level of
Freshness (1-3)
2
Levels of Measurement

Oranges-Lbs Produce 4 2 2.58


Apples-Lbs Produce 4 1 1.29 2
Mozzarella-Lbs Dairy 7 1 3.49 3
Milk-Skim-Gallon Dairy 8 1 4.29 3
Peas-Bag Frozen 15 1 0.99 1
Green Beans-Bag Frozen 15 3 1.77 1
Tomatoes Canned 2 4 3.92 1
Potatoes Canned 3 2 2.38 1
Mushrooms Canned 2 5 2.95 1
Discrete vs. Continuous Data

Discrete data can take specific values (typically integers) and no values in between (for
example: you can’t have 4.5 people)
Levels of Measurement

Continuous data can be any value along a certain scale. (for example: you can buy 1.5
KGs of tomato)

Interval and ratio data can be either discrete or continuous.


Variable Type vs. Data Type

Many variables can belong to more than one data type depending on the collection
method.
Variable Type vs. Data Type

Example: Age can be collected as ratio data and ordinal data.

General rule: you can go down in level of measurement but not up (during both
collection and analysis of data)
Variable Type vs. Data Type

• If you can collect the variable as interval or ratio data, you can also collect it as
Variable Type vs. Data Type

nominal or ordinal data.

• If the variable is essentially nominal in nature, it cannot be collected as ordinal,


interval, or ratio.
Variable Type vs. Data Type

Many variables that get captured as ordinal have a similar variable that can be
captured as interval or ratio.
Variable Type vs. Data Type

Ordinal Level Type Corresponding Interval/Ratio Example


Level Measure

Ranking Measurement that ranking is based Record runners’ marathon


on times instead of what place
they finish
Grouped scale Measurement itself Record exact age instead of
age category
Substitute scale Original measurement the scale Record exact test score
was created from instead of letter grade
Categorical Data

• Some texts consider both nominal and ordinal data to be types of categorical data.
Nominal: unordered categorical data
Other Important Terms

Ordinal: ordered categorical data

• Other texts consider only nominal data to be categorical, and ordinal data to be a
separate group.
Qualitative and Quantitative Data

• Qualitative data are non-numeric, whereas quantitative data are numeric and
quantifiable.
Other Important Terms

• Certain data are always considered qualitative (ex: transcripts of interviews)

• Interval and ratio data are always considered quantitative


Qualitative and Quantitative Data

• Some consider nominal and ordinal data to be qualitative since they are descriptive.
Other Important Terms

• Others consider them to be quantitative since they can be counted and used to
calculate percentages.

You might also like