Introduction to Types of Data
Welcome to the first step of your statistical journey! Before we can draw charts or calculate averages, we need to understand what "data" actually is. Think of data as the raw ingredients for a recipe. Just as you wouldn't use a whisk to cut a tomato, you shouldn't use the wrong statistical method for the wrong type of data. In this chapter, we will learn how to identify different types of data and understand how they are collected.
Quick Note: Raw data is the term we use for information that has been collected but not yet processed or organized in any way.
1. Qualitative vs. Quantitative Data
The first big split in statistics is between Qualitative and Quantitative data. This is all about whether the data is made of words or numbers.
Qualitative Data (Categorical)
Qualitative data is descriptive. It describes qualities or characteristics that cannot be measured with numbers. We often call this categorical data because it puts things into "categories."
Examples: Eye color, car brands, types of pets, or your favorite pizza topping.
Quantitative Data (Numerical)
Quantitative data is numerical. It deals with quantities and things you can count or measure. If you can do meaningful math with it (like finding an average), it’s usually quantitative.
Examples: Shoe size, weight, temperature, or the number of students in a class.
Memory Trick: Qualitative is about Qualities (words). Quantitative is about Quantities (numbers).
2. Breaking Down Quantitative Data
Numerical data comes in two distinct flavors: Discrete and Continuous. Understanding the difference is vital for choosing the right graph later on!
Discrete Data
Discrete data can only take specific values. These are often "counted" things. You can’t have "half" of a value in many discrete sets.
Examples: The number of siblings you have (you can’t have \(2.4\) siblings) or shoe sizes (you can be a size \(6\) or \(6.5\), but not a \(6.217\)).
Continuous Data
Continuous data can take any value within a range. These are usually "measured" things. The accuracy just depends on how good your measuring tool is.
Examples: Your height (\(1.652...\) meters), the time it takes to run a race, or the weight of an apple.
Quick Review: If you count it, it’s usually discrete. If you measure it with a ruler, scale, or stopwatch, it’s continuous.
3. Ordinal Data
Sometimes, categorical data has a specific order. We call this Ordinal data. While it is still qualitative (words), the order matters.
Example: A survey asking if a movie was "Poor," "Average," "Good," or "Excellent." You can't say "Excellent" is twice as good as "Average," but you definitely know "Excellent" is higher than "Average."
4. Ungrouped and Grouped Data
When we collect lots of numerical data, it can look messy. We have two ways to organize it:
Ungrouped Data
This is a list of every individual score or measurement. It is very accurate because you know every single value.
Grouped Data
To make large sets of data easier to read, we put them into class intervals (groups).
Example: Instead of listing \(50\) different heights, we might group them into \(150 \le h < 160\), \(160 \le h < 170\), etc.
Important Point: When we group data, we suffer a loss of accuracy. Once data is grouped, you no longer know the exact original values—you only know they fall somewhere within that interval. This is a common exam question!
5. Bivariate and Multivariate Data
This section looks at how many "things" we are measuring at the same time.
Bivariate Data
Bivariate data involves pairs of variables to see if there is a relationship between them. We usually plot this on a scatter diagram.
Example: Comparing a person's height (\(x\)) with their arm span (\(y\)).
Multivariate Data (Higher Tier Only)
Multivariate data involves more than two variables for each subject. It helps us understand complex situations where many factors are at play.
Example: If you were studying health, you might look at a person’s weight, age, and heart rate simultaneously.
6. Explanatory and Response Variables
When looking at bivariate data, we often think one variable might "explain" the change in another.
1. Explanatory Variable (Independent): This is the variable that we think might be causing a change. By convention, this goes on the horizontal \(x\)-axis.
2. Response Variable (Dependent): This is the variable we are measuring to see how it reacts. This goes on the vertical \(y\)-axis.
Example: If you are studying how much sunlight a plant gets and how tall it grows, Sunlight is the Explanatory variable (\(x\)) and Height is the Response variable (\(y\)).
7. Primary vs. Secondary Data
This is all about where you got your data from.
Primary Data
Data you (or your team) collect yourself for your specific investigation.
Advantages: You know exactly how it was collected; it’s up-to-date; it’s specific to your needs.
Disadvantages: Can be very expensive and time-consuming.
Secondary Data
Data that has already been collected by someone else (e.g., the internet, newspapers, or government census records).
Advantages: Usually very quick and cheap (or free) to get; allows you to access huge amounts of data you couldn't collect yourself.
Disadvantages: It might be out of date; it might be biased; it might not be in the exact format you need.
Did you know? Using the internet for research is the most common form of secondary data collection today!
Summary Table: Key Takeaways
Qualitative: Describing categories (words).
Quantitative: Measuring or counting (numbers).
Discrete: Fixed values (e.g., number of pets).
Continuous: Any value in a range (e.g., time).
Grouped Data: Easier to handle, but loses accuracy.
Primary Data: Collected by you (Accurate but slow).
Secondary Data: Collected by others (Fast but maybe biased).