Regression analysis is another tool market research firms used on a daily basis with their clients to help brands understand survey data from customers.
The benefit of using a third-party market research firm is that you can leverage their expertise to tell you the “so what” of your customer survey data. Regression analysis helps you make sense of priority areas and what will have the most impact and influence on your customer relationships.
This article will help you understand the definition of regression analysis, how it is commonly used, and why it is used in market research.
What is regression?
Regression analysis is a common technique in market research which helps the analyst understand the relationship of independent variables to a dependent variable. More specifically it focuses on how the dependent variable changes in relation to changes in independent variables.
In a simple example, you want to find out how dependent variables A, B, and C impact the independent variable D.
If A increases will it have more of an impact on D than B or C? If C decreases will it have more of an impact on D than A or B? Etc.
How is regression analysis used in market research?
A common application of this in market research is understanding how the likelihood to recommend (dependent variable) is impacted by changes in wait time, price, quantity purchased (presumably independent variables).
Net promoter score (NPS) is one of the most popular metrics in market research. The calculation or score is based on a simple likelihood to recommend question. It is a 0 to 10 scale where “10” indicates very likely to recommend and “0” indicates not at all likely to recommend.
It groups your customers into 3 buckets:
- Promoters or those who rate your brand a 9 or 10
- Passives or those who rate your brand a 7 or 8
- Detractors or those who rate your brand a 0 to 6
The NPS is calculated as the difference between the percentage of promoters and the percentage of detractors (i.e., 75% promoters - 15% detractors = +60 NPS.)
The score is very telling to help your business understand how many raving fans your brand has in comparison to your key competitors and industry benchmarks.
While our market research company always recommends using an open-ended question after NPS to gather context to help understand the driving forces behind the score, sometimes it does not tell the whole story.
This is where regression analysis can help.
Customers are often not experts at expressing their emotions and feelings in a survey. If you were to ask a customer why they rated your restaurant a “10” on likelihood to recommend they may say something like “good prices” or “good food” in an open-ended comment.
But is that what is really driving your high NPS score?
Let’s say in the same survey after you asked the likelihood to recommend, you asked a series of satisfaction questions related to your customer experience at your restaurant.
You believe the price and food are good at your restaurant but you think there might be some underlying drivers really pushing your high NPS.
In this example, likelihood to recommend or NPS is your DEPENDENT VARIABLE A.
Your dependent variables become your more specific follow-up satisfaction questions.
You ask on a scale of 1 to 5 where “5” indicates very satisfied and “1” indicates not at all satisfied, how satisfied are you with the following?
- Cleanliness of the restaurant (INDEPENDENT VARIABLE B)
- Friendliness of the staff (INDEPENDENT VARIABLE C)
- Price of the food (INDEPENDENT VARIABLE D)
- Taste of the food (INDEPENDENT VARIABLE E)
- Speed of your order (INDEPENDENT VARIABLE F)
- Check-out process (INDEPENDENT VARIABLE G)
Through your regression analysis, you find out that INDEPENDENT VARIABLE C (friendliness of the staff) has the most significant effect on NPS. This means how the customer rates the friendliness of the staff members will have the largest overall impact on how likely they would be to recommend your restaurant.
This is much different than what customers said in the open-ended comment around price and food.
This is likely driven by subconscious undertones of the customer experience and customers not understanding how they impact their overall experience.
However, as regression analysis proves, staff friendliness is essential.
If this facet of your business can be improved so all customers rate your staff a “5” on the satisfaction it is significantly more likely your NPS score will push higher than +60.
Why is regression analysis used in market research?
Regression analysis is a great tool for predictive analytics and forecasting in market research.
It helps businesses and organizations prioritize efforts to improve measures like overall satisfaction, likelihood to recommend, or net promoter score (NPS).
By using regression analysis in quantitative research it provides the opportunity to take corrective actions on the items that will most positively improve overall satisfaction.
Regression analysis has many other applications in market research and analysis.
At a former manufacturing company I worked at, I used regression analysis to understand the impact that key index scores from the markets had on sales projections.
In more detail, how would our revenue be impacted by the ups and downs of oil prices, the consumer price index (CPI), gross domestic product (GDP), etc?
We used reports and analysts forecasts on those key independent variable statistics (oil price, CPI, etc.) to understand how our revenue might be impacted in future quarters.
Obviously, the further in the future you predict, the less reliable the data will be using a wider margin of error.
Interested in exploring regression analysis for your customer satisfaction survey? Need a quote or proposal for the work? Contact us below.
- Message us on our website
- Email us at firstname.lastname@example.org
- Call us at 888-725-DATA
- Text us at 315-303-2040
George is the Owner & President of Drive Research. He has consulted for hundreds of regional, national, and global organizations over the past 15 years. He is a CX certified VoC professional with a focus on innovation and new product management.
Learn more about George, here.