Monday, May 10, 2010

Slider Scales Add Flash—and Improve Data Integrity—in Online Surveys

The traditional Likert scale—where survey participants specify their level of agreement with a statement (i.e., agree strongly, agree, neither agree nor disagree, disagree, disagree strongly)—is the most widely used scale in survey research. But does it provide the most accurate answers? And are there more engaging survey measures available?

Some experts believe the Likert scale is a rather imprecise instrument. A participant’s true opinion can lie in the spaces between the allowable answers and even beyond the traditional end points. Some suggest other scales may be better at enabling survey respondents to differentiate their opinions.

Adobe Flash, now widely adopted, gives researchers the opportunity to produce question and answer styles that incorporate a greater breadth of answers, as well as enable animation and interactivity. One such measure is the Slider. Sliders look engaging and offer a degree of interactivity beyond merely answering questions.

In an effort to determine how this Flash-based alternative compares to the standard 5-point Likert scale in terms of data collected, level of respondent engagement and respondent satisfaction with the instrument, Survey Sampling International (SSI) recently undertook a research experiment. The results are available in a new White Paper titled “Slider Scales in Online Surveys.”

SSI’s experiment dealt with two questions about the Likert scale:

  1. Equivalency of ratings: If item A is rated “agree slightly” and item B is also rated “agree slightly” does the respondent agree to both items to the same degree? Is the Likert Scale too blunt an instrument to detect the subtle differences between items?

  2. The spaces between: Is there some level of agreement between “agree slightly” and “agree strongly?” Is there some level of agreement below “agree slightly?” Do we force people to state something that is not their true opinion because we offer too few alternatives?

In SSI’s experiment, a random subset of respondents was presented with a 5-point Likert scale and four statements. After completing the exercise, respondents were asked to what extent the instrument allowed them to accurately give their opinions. Subsequently, respondents were presented with the items again and offered the opportunity to re-score each item using 5 points above or below the original stated answer. Interestingly, with this expanded scale, a large number of people elected to change several of their ratings.

From SSI’s results, it is clear that survey participants have a finer definition of agree and disagree than the Likert scale allows. The Slider allows researchers to collect a greater granularity of detail than they can with the Likert scale. Furthermore, respondents who used the Slider scale reported higher levels of satisfaction with this instrument as a means of capturing their true opinions.

In today’s sampling environment, researchers are increasingly vying for respondents’ attention, and data integrity is a constant concern. A move toward more engaging and interactive question and answer formats can help address these issues. Sliders are one Flash-based alternative to traditional Likert scales that is well worth considering.

For a copy of the white paper “Slider Scales in Online Surveys,” with full study results and to voice your opinions on question and answer formats, go to

About the Author: Pete Cape is Global Knowledge Director for Survey Sampling International. SSI provides access to more than 6 million research respondents in 72 countries. Sources include SSI proprietary panel communities in 27 countries and a portfolio of managed affiliates. SSI can potentially access anyone online to give their opinions via a network of relationships with websites, panels, communities and social media groups.
Reblog this post [with Zemanta]
iframe {max-width:100%;} .embed{ width: 100%; }