Select Page

## Definition of Quantitative Data

Before we begin, what even is quantitative data?

Well without complicating it, quantitative data can be defined as the value of data in the form of numbers, put into a category for the ease of making sense.

Okay, it still sounds complicated, but we use this in our everyday lives, and it honestly is much simpler than you would think.

Some everyday examples of quantitative data and how they may be categorized are:

• How much does that man weigh? (kilograms)
• How tall is that tower? (meters)
• How good is a product? (# of stars given)
• How viral is my content? (# of likes and shares)

See? Simple, with an everyday use. But why does it seem so complicated?

Well, the complications of quantitative data comes from its usage in making sense of things in a large quantity.

As we will see later on, some examples of large amounts of quantitative data can come from:

• surveys
• polls
• questionnaires

From these sources, you could receive 1 to 1000 to even more than 10 000 points of quantitative data, which can help you make a decision.

An easy example: “750 customers out of 1000 enjoyed their stay at hotel X.”

So we can see that 75% of customers were satisfied with hotel X, so if you had thoughts on staying at hotel X, there’s a good chance that you’re going to enjoy your stay too!

Now that we understand quantitative data a little bit more, let’s go into more depth by discussing the types of quantitative data, their collection methods, their analysis methods, what’s needed to conduct quantitative analysis, and the advantages and disadvantages of quantitative data.

## Examples of Quantitative Data

Some common types of quantitative data are:

• Counter: Number data which represents the number of entities. I.e. number of downloads of an application represents the number of users/customers who have downloaded the application.
• Physical Measurements: The measurements of physical objects. I.e. the dimension of a standard office is 10′ x 15′ (150SF).
• Sensory calculation: Specialized mechanisms to convert information into measurable parameters for a reliable and understandable source of information. I.e. the Richter magnitude scale is a scale to measure the strength of earthquakes.
• Projection of data: Using algorithms and formulas to project future data based on current or past data (predictive analysis). I.e. Google Flu Trends (GFT) was a tool created by Google to predict the next flu outbreak based on search queries.
• Quantification of qualitative entities: Putting a number to an otherwise qualitative source of data. I.e. Asking participants to rate their happiness on a scale of 1-10, where 1 is “feeling sad” and 10 is “feeling very happy”.

It definitely feels like a lot of information to take in, but it helps to keep in mind that depending on what your needs are, you will only need to use a few of these types of quantitative data, rather than all of them.

## How to Collect Quantitative Data

Quantitative data is concrete, as it is based on logic and mathematics. As such, you can usually establish conclusive results based on the data.

Two ways to collect quantitative data are through:

Surveys: From the time of pencil and paper to today’s online mediums, surveys are a tried and tested method to gather quantitative data. An effective quantitative survey would use mostly closed-ended questions as yes and no data, and data on a Likert scale can easily be understood.

The usage of surveys is key in collecting feedback. They are easily shared and allows you to gauge the perspective of your audience.

One-on-one Interviews: Another traditional method to collect quantitative data, that has moved to both telephone and online platforms.

Interviews offer you the chance to gather extensive data from participants, which surveys find difficult due to participant fatigue.

The common mediums to conduct an interview are via:

• Face-to-face Interviews
• Telephone/Online Interviews
• Computer Interviews

If you decide to use interviews for data collection, an additional benefit is the collection of qualitative data to pair with your quantitative data.

The trade-off is that due to it being more time intensive compared to the survey method, interviews are mostly used for quality data, rather than quantity.

### Analysis Methods for Quantitative Data

You’ve collected your data! Now what? Well, its time to analyze it.

Data alone doesn’t mean anything until you look at it and give it meaning. Some methods of analyzing data are:

• Cross-tabulation: This is the most popular method when analyzing quantitative data. Cross-tabulation, as the name implies, analyzes multiple variables and tries to find correlations between them. This helps establish relationships and discriminates between variables.
• Trend analysis: When you’re looking at data over a period of time to help you predict future data, then you’re analyzing trends. Using this method can help you collect feedback regarding data that changes or remains the same, over time to help you predict
• Gap analysis: Using a gap analysis will help you determine how you and your company are doing vs the potential performance. Through this, you will find areas that are not optimized and/or can be improved on.
• SWOT analysis: A well-known analysis, the Strengths, Weaknesses Opportunities and Threats (or SWOT) analysis is similar to the gap analysis in finding out your company’s performance and potential. However, this analysis goes into further detail, which will help in creating business strategies.
• Text Analysis:  Raw survey data starts unstructured but has to be made into something that makes sense. Text analysis helps by using intelligent tools to do structure the data, and help you understand it.

## Understanding How To Conduct A Quantitative Data Analysis

To be blunt, raw data means nothing. This is why you need to conduct an analysis; to make sense of it so you can make use of that data.

There are four criteria that you need to understand before conducting an analysis.

### Relating Measurement Scales and Variables

There are four types of scales to categorize your data in. The four scales are:

• Nominal – A label for your data. I.e. hair color, place of birth, a genre of music, cuisine of food, the material of cloth.
• Ordinal – Data that comes in a specific order. I.e. Rankings of badminton players, top 10 Japanese restaurants, movie ratings.
• Interval – A numerical scale with no true 0 (has negative integers). I.e. temperature (Celcius & Fahrenheit), income, any value on a Likert scale.
• Ratio – A numerical scale with a true 0 (does not have negative integers). I.e. height, weight, volume, number of donuts.

### Using Descriptive Statistics for Data

To further understand your raw data, you should use descriptive statistics. With descriptive statistics, you should find it easier to see patterns within your data.

Descriptive statistics that are often used are:

• Mean- The average value of specific variables.
• Mode – The most common value in a variable.
• Median – The numerical middle point of a variable.
• Frequency – How many times a specific value is observed on a scale.
• Minimum and Maximum Values- The lowest and highest values on a scale.
• Percentages – A format to express the scores of variables.

Okay, simple to understand. But! You need to put your scales of measurements together with your descriptive stats to fully understand your data!

### Deciding Which Measurement Scale To Use

You will have to decide on the measurement scale to use so you can choose a descriptive statistic for your variable.

An example, you can never use a nominal variable score with means or medians, as a label doesn’t have an average or midpoint. As such, your descriptive statistics will be based on your chosen scale for your variable.

Some extra information, descriptive statistics are used to help describe raw data from a sample size, and cannot be applied to a population.

### Tabulate and Analyze Your Data

Finally, after you decide which measurement scale and descriptive statistics work best, use tables to represent your data.

Once your data is tabulated, it can be analyzed using the cross-tabulation technique.

So you’ve learned about what quantitative data is, how to collect it and how to analyze it. But how does quantitative data help you, and how doesn’t it help you?

Well the advantages of quantitative data are:

• Detailed Research: As quantitative data is numerical and statistical in nature, the research you conduct with it can lead to many inferences.
• Minimal Bias: Assuming the data isn’t tampered with, quantitative data will tell you information as it is. Number’s don’t discriminate, but humans may accidentally do so, which could lead to incorrect results.
• Accurate Results: Numbers don’t lie. Quantitative data presented to you is objective by nature and won’t try to trick you (which is why proper analysis is important!)

Quantitative data is great! But it isn’t perfect. There are limits to what quantitative data can do for you.

The disadvantages of quantitative data are:

• Limited Information: Quantitative data gives you numbers, but what do these numbers mean? Yes, your customer gave you a 7 for satisfaction, but why did they do so? To gain true insight, quantitative data cannot be the only option of data collection.
• Question Bias: Numbers don’t lie, but the intentions behind them may skew your data. To ensure that you’re getting the correct data, you should consider the nature of your questions, and their measurement scale, and analyses while making them.