Small Scales, Big Scales - Getting A Clear Picture

aytm logo icon
Posted Apr 05, 2012
Kathryn Korostoff

One of the first things a new student of photography learns is the trade-offs of resolution. Large format cameras take high resolution pictures, but they are expensive, heavy and awkward, and high-res images are slow to transmit electronically. Digital has changed much in the art, but the trade-offs are still there. And believe it or not, similar trade-off’s face a market researcher designing an online survey. “Resolution”, in our case, is measured in points on a scale.

5 or 7 points: More Points, More Resolution

It’s a common question in survey design: How many points in a scaled question is “enough”? You've seen online surveys, and you've probably noticed that they often have five points. For example, “Please rate your satisfaction on a scale from 1 to 5, with one representing ‘not at all satisfied’ and five representing ‘extremely satisfied’. Sometimes you may see a 7-point scale instead of 5. Is 7 points better than 5? In other words, is higher resolution better? The answer is, “that depends”.

The goal is balance

If you ask two different researchers you’ll get two different opinions, but ideally we want to strike a balance between keeping it simple for our survey takers and getting accurate data for ourselves. If we’re talking about a topic where we expect to see a lot of variability in responses, a 7 point scale allows our respondents to be more precise, and that gives us better data than a 5 point scale. For example, we tend to use larger scales for satisfaction studies because different customers tend to have different experiences with—and thus different feedback about—your brand.

Plan for future online surveys

If online surveys are something you plan to be doing for a while, consider picking a scale and sticking with it. Whether it's an even scale of 4 or 6 points or an odd scale like 5 or 7 points, pick a scale and standardize on it so that you have a benchmark and some consistency across your studies. Eventually, you will want to easily compare results from one study to another over time, and being consistent allows that.If you’ve thought it through and still can’t decide what scale you need, err on the side of a larger scale. Just like resolution in photographs, you can always collapse the scale when you're doing your data analysis, but you can never expand it (increase the resolution) once you've captured the data. Pick a scale and stick with it.

Define your survey goals and choose

Ultimately, the choice isn’t that complex. On the plus side, larger scales allow a greater degree of potential accuracy, but require a bit more thinking by participants. As a researcher, you need to make these trade-off’s carefully, so that your research delivers gallery-worthy results.

Featured Stories

New posts in your inbox