{"id":484,"date":"2018-08-15T03:45:45","date_gmt":"2018-08-15T03:45:45","guid":{"rendered":"http:\/\/measuringu.com\/rating-scales\/"},"modified":"2022-03-21T17:49:30","modified_gmt":"2022-03-21T23:49:30","slug":"rating-scales","status":"publish","type":"post","link":"https:\/\/measuringu.com\/rating-scales\/","title":{"rendered":"15 Common Rating Scales Explained"},"content":{"rendered":"

In surveys, questions can be broadly classified as open-ended (free responses) or closed-ended. Closed-ended questions themselves can be classified into multiple choice questions or rating scales.<\/p>\n

Multiple choice questions (e.g. age, education level, or electronic devices owned) are usually more straightforward for researchers with little survey experience. When properly written, they\u2019re also straightforward to the respondents as they usually involve concrete selections.<\/p>\n

Rating scales however usually involve asking participants to rate abstract concepts, such as satisfaction, ease, or likelihood to recommend. The item selection can have a big impact on both the responses and interpretation.<\/p>\n

There are different ways of classifying rating scales and slight variations can result in different looking rating scales, even though they\u2019re variations on the same scale. For example, our MUIQ platform<\/a> offers over 30 question types but I\u2019ve identified 15 distinct ones.<\/p>\n

I\u2019ve adapted a classification scheme based on our experience at MeasuringU and from the classic text on survey research by Alreck and Settle<\/a>. Here are 15 scales, in roughly the order of most to least commonly used.<\/p>\n

<\/p>\n

1. Linear Numeric Scale<\/h2>\n
In a linear numeric scale, participants provide some numeric response to a question or statement. This can include things like satisfaction<\/a>, ease, brand favorability<\/a>, feature importance, or likelihood to recommend. The Single Ease Question (SEQ)<\/a> and likelihood to recommend item used in the NPS<\/a> are examples of linear numeric scales. Linear numeric scales usually have at least the endpoints labeled. (Labeling, neutral points, and number of response options<\/a> are the topics of other articles.)<\/p>\n
$\"\"$ <\/a><\/p>\n

2. Likert<\/h2>\n
The classic Likert scale<\/a> has participants agree or disagree (or approve\/disapprove) to multiple statements. When numbers are associated with each response option, the Likert item can be seen as a special case of the linear numeric scale. The classic Likert item uses a 5-point response scale, but you can use 7, 9, or other points, too. (Although someone will have a strong opinion about the \u201cright\u201d number of steps.<\/a>) Because the response scale is about agreement, be sure items are phrases participants can agree or disagree to. The System Usability Scale (SUS)<\/a>, SUPR-Q<\/a>, and UMUX-Lite<\/a> use a Likert scale with numbered values<\/a>.<\/p>\n
$\"Likert\"$ <\/a><\/p>\n

3. Multiple Rating Matrix<\/h2>\n
The matrix question is a compact way of presenting multiple linear numeric items and is the typical method for displaying Likert items, too. It\u2019s probably not technically different from a linear numeric scale but I\u2019ve separated it out because they\u2019re so popular for online surveys. For example, when having participants rate their brand attitude, it\u2019s common to use a matrix<\/a> similar to the following one.<\/p>\n
$\"Multiple$ <\/a>Try not to use too many of these in a survey as it can be overwhelming to respondents<\/a>.<\/p>\n

4. Frequency Scales<\/h2>\n
Understanding how often people perform (or think they perform) actions helps when product planning as in the example below. When listing the frequency of actions, consider both specific number of times (e.g. every day) as well as more general timeframes (sometimes, always, never\u2014referred to as a verbal frequency scale). Also, be sure the frequencies are sequentially ordered and well understood. For example, is occasional more frequent than sometimes?<\/p>\n