Data Analysis Tip for Online Survey Results: Using Crosstabs to Gain Insights

aytm logo icon
Posted Oct 04, 2011
Kathryn Korostoff

As you look at the results to an online survey, it’s easy to get excited. Your data is in, and it is starting to tell you a story. But before you jump to conclusions, it is often a good idea to be thorough and look at your data two ways:

  1. Look at the data in aggregate. That’s when you look at how everyone who answered the questions responded. For every question, what is the distribution of answers? How many selected answer option A versus answer option B?
  2. Look at the data by subgroup. Sometimes you need to see if answers to a question vary by subgroup, such as gender, geography, or brand preference. This analysis is referred to as “banners” or “crosstabs.” Do men like that cool new feature idea more than women? Do people who own Brand X cell phones like this service idea more than those who own brand Y?

You can see that variations by subgroup can be very important. A big difference by gender, for example, might imply that you should be building brand awareness more with one gender than the other, or what marketing message will resonate more with one or the other. Conversely, you may be looking for a feature or marketing message that will appeal to both genders equally—so you want to make sure that neither is being turned off by one of your ideas.You have two options for looking at crosstabs using AYTM. You can export your data to a crosstab tool like Wincross or StatPac. Or you can look at basic crosstab results in graphical form using AYTM. The difference? A tool like Wincross or StatPac adds significance testing (a measure of how sure you can be that differences between subgroups are not due to random noise in your data), which may be of interest to you or may be overkill. But before you make a decision, let’s look at what you can do with AYTM to see if that will meet your crosstab needs.Try out some crosstabs yourself. If you have any questions, contact us via chat.