How to use descriptive statistics for market analysis
Franco Brutti
Have you ever made a decision to change something in your company based purely on intuition? If so, we hope it worked out well for you.
But what if we told you that you can turn to statistics for this? That's right, today we want to talk to you about descriptive statistics and their usefulness in market analysis.
Don't worry, you don't have to be scared, you won't have to deal with too many numbers, but rather with data, so calm down, take a breath and read on to find out more.
Let's define descriptive statistics
Descriptive statistics, as you may have figured out from its name, focuses on description, and is able to show and summarize the basic characteristics of a data set found in a given study, presented in a summary that describes the data sample and its measurements.
We can say that it helps analysts to better understand the data, since descriptive statistics represent the available data sample and do not include theories, inferences, probabilities or conclusions.
This is a job for inferential statistics, but we will talk about that in another article that you may be interested in.
Let's get back on topic, descriptive statistics are useful when dealing with populations that are too large and extensive for specific and detailed measurements.
Remember that statistics are crucial for drawing general conclusions related to a data set from a sample of data.
Examples of descriptive statistics
If you want a good example of what descriptive statistics are, you need look no further than a student's grade point average. Why? It's simple...
A GPA collects data points created across a large selection of grades, classes, and exams, then averages them and presents an overall picture of a student's average academic performance.
Note that the GPA does not predict future performance or present any conclusions. Instead, it provides a straightforward summary of the academic success of students or, in this example, a student, based on values extracted from the data.
Perhaps that sounded a bit confusing, let's look at an even simpler example. Suppose a data set of 2, 3, 4, 5, and 6 equals a sum of 20. The average of the data set is 4, which is arrived at by dividing the sum by the number of values (20 divided by 5 equals 4). This is simple mathematics.
Analysts often use tables and graphs to present descriptive statistics, but let's look at another example.
If you stand outside a movie theater and ask 50 audience members if they liked the movie they saw and then put your findings on a pie chart, that would be descriptive statistics.
In this example, descriptive statistics measure the number of yes and no responses and show how many people in this specific theater did or did not like the movie.
If you tried to draw other conclusions, we would be wandering in the territory of inferential statistics, well, it seems that we cannot forget about them, we will give them their space.
Finally, the political survey is considered a descriptive statistic, as long as it only presents hard facts, such as respondents' answers, without drawing any conclusions.
Polls are fairly straightforward: "Who did you vote for president in the recent election?"
What types of descriptive statistics are there?
Although this territory might be a bit more…problematic? It should be mentioned. And the fact is that there are different types of descriptive statistics, although experts on the subject do not agree with each other, since while some claim that there are 4, others simplify them to 2.
It can be somewhat complicated, yes, but it is worth mentioning the most recognized ones:
1. Frequency distribution.
This type of descriptive statistics is used to obtain qualitative and quantitative data since it allows the presentation of the frequency and/or the count of various results according to a group of samples.
They can be represented in a simple way through a table or a graph. Each entry in the graph will be shown next to the count or frequency of the values presented, giving a specific range, interval, or group.
Since these frequencies present a summary of the grouped data, this allows the data to be grouped in a more organized manner. The most common graphing methods are bar charts, histograms, pie charts, and line graphs.
2. Central tendency
When we speak of central tendency in descriptive statistics we refer to a set of data that is used as a single value and that reflects the center of distribution of the other data.
They are also known as "measures of central location" and it’s here when we talk about "The mean", "the median" and "the mode", since they are considered measures of central tendency.
The mean: is the most popular central tendency, the average or common value of the data obtained.
The median: is the midpoint of the data sets obtained in ascending order.
The mode: it is the most frequent score of all data sets.
3. Variability
To finish with the types of descriptive statistics, we have variability, which reflects the level of dispersion that a sample has. These are determined around the distance with the data points shown with respect to the center of the graph.
Both dispersion and variability refer to and show the range and amplitude of how the values of the data sets are distributed.
It uses range, standard deviation, and variance to represent the components and aspects of dispersion.
Range: the degree of dispersion between the highest and lowest values of the data sets.
Standard deviation: is used in order to determine the average variance over the data set, which allows one to have a perspective of the distance of the data set and the mean value.
Variance: reflects the level of dispersion and is the mean of deviations in the table.
What is the main purpose of descriptive statistics?
If we had to summarize the usefulness of descriptive statistics, we could do it according to 2 aspects:
To provide basic information about the variables in a data set.
To highlight possible relationships between variables.
Graphical and/or pictorial methods are measures of the three most common descriptive statistics that can be displayed graphically or pictorially and are used to summarize data.
Descriptive statistics only make statements about the data set used to calculate them; they never go beyond the information you have.
Therefore, we can say that the main purpose is to convey information quickly to businesses.
Suppose you are an entrepreneur and you receive the information. You may not have the time or the skills to analyze that data.
That's one reason why data analysts take complex information and reduce it to something more digestible for managers or decision-making groups.
A management team can take descriptive statistics into account when considering changes in a company's strategy.
These statistics allow managers to understand whether the current plan is meeting objectives and whether course corrections are needed to improve and/or enhance it.
Investors often use descriptive statistics to get a sense of a company's financials, performance, value, and growth potential. Researchers can use descriptive statistics to understand and communicate the details of the data set they are using.
Importance of descriptive statistics
Descriptive statistics facilitate data visualization by allowing data to be presented in a meaningful and understandable way, which, in turn, allows a simplified interpretation of the data set in question.
Raw data would be difficult to analyze, and determining trends and patterns can be even more difficult to perform. In addition, raw data makes it difficult to visualize what the data shows.
Let's look at an example:
Suppose there are 100 students enrolled for a particular module. To find out the overall performance of the students taking the module and the distribution of marks, you should use descriptive statistics.
Since it allows you to obtain the marks as raw data, it would show that determining the overall performance and distribution of marks would be challenging.
In addition, descriptive statistics allow you to summarize and present a set of data through a combination of tabular and graphical descriptions, plus a discussion of the results found.
In summary, descriptive statistics can be used to summarize complex quantitative data, which facilitates the interpretation and analysis of the data, but this becomes the task of inferential statistics.
What is the difference between descriptive and inferential statistics?
We were late in arriving... And the fact is that in order to take the next step when you have already collected all the data, you have to apply inferential statistics.
If we had to define it simply, it would be as follows: While descriptive statistics describe a set of data; inferential statistics infer what the data says.
Imagine you have a Ford Mustang car on the starting line of a drag race. Descriptive statistics, as the name implies, describe it: color, and characteristics such as engine and horsepower.
Now, it’s possible to make inferences about such a car, but from looks you can't see yet. Since it’s a racing car, we could infer that it’s fast, otherwise, it would not be in the competition, would it?
The difference between descriptive and inferential statistics is quite similar, but you have to look at it with an example related to the world of work.
Suppose you have a company that will bring out a new line of toys, but before you launch it to the country's market, you want to do a test, so you decide to do it in one state first.
After a few months, you gather sales, acceptance, and popularity data to graph. In the event that it has been a success, you could, based on the data obtained from 10,000 units sold, make a guess as to how it would do on a larger scale.
Inferential statistics help provide information about the probability that a descriptive statistic represents the population being estimated. Inferential statistics are important in research studies when scientists conduct hypothesis testing.
Descriptive statistics as a business strategy
As you can see, descriptive statistics can help you to carry out a market analysis later on, so it’s a strategy that you should take into account to carry out studies about your target customers.
And you can know the data of a group of the population you want to satisfy, to know if you will have a better result, but remember, for this you must also resort to inferential statistics.
Would you be willing to give a chance to these types of statistics to see the results you can achieve in your business?
Don't hesitate to tell us the details in the comments!
Looking for something specific?
