When creating surveys or questionnaires, researchers sometimes rephrase “positive” questions in a “negative” way to make sure that individuals are giving consistent responses.
For example, consider the following two questions:
1. When working on new projects, I prefer to work alone rather than in a small group.
- Strongly Agree
- Agree
- Neither Agree Nor Disagree
- Disagree
- Strongly Disagree
2. Given the choice, I prefer to work with a small group rather than by myself on new projects.
- Strongly Agree
- Agree
- Neither Agree Nor Disagree
- Disagree
- Strongly Disagree
For question 1, “Strongly Agree” corresponds to introversion. However, in question 2, “Strongly Agree” corresponds to extroversion.
We say that question 2 is reverse-coded.
Both questions seek to measure the level of introversion and extroversion of individuals, but they use opposite wording.
When assigning a composite score to individuals to determine their level of introversion or extroversion, it’s important to make sure the reverse-coded questions are reverse-scored as well.
The following example shows how to reverse the scores on reverse-coded questions.
Example: How to Reverse Code Questions
Suppose researchers use the previous two questions to assign an “introversion” score to individuals. Higher scores indicate higher levels of introversion.
Suppose researchers assign a value of 5 to “Strongly Agree”, 4 to “Agree”, 3 to “Neither Agree Nor Disagree”, “2 to “Disagree”, and 1 to “Strongly Disagree.”
Then consider the overall average score of someone who answered “Strongly Agree” to the first question and “Strongly Disagree” to the second question:
1. When working on new projects, I prefer to work alone rather than in a small group.
- Strongly Agree (5)
- Agree (4)
- Neither Agree Nor Disagree (3)
- Disagree (2)
- Strongly Disagree (1)
2. Given the choice, I prefer to work with a small group rather than by myself on new projects.
- Strongly Agree (5)
- Agree (4)
- Neither Agree Nor Disagree (3)
- Disagree (2)
- Strongly Disagree (1)
Their average score would be calculated as: (5 + 1) / 2 = 3. This would make them seem perfectly in the middle of being introverted and extroverted.
However, if you read the individual questions you can see that they prefer to work alone in both scenarios. They should receive a much higher score for introversion.
We must reverse score the second question since it’s reverse-coded.
The easiest way to do this is to take the max possible score (5) and add one. Then subtract the original scores to get the reverse scored value.
For example:
- “Strongly Agree” becomes 6 – 5 = 1.
- “Agree” becomes 6 – 4 = 2.
- “Neither Agree Nor Disagree” becomes 6 – 3 = 3.
- “Disagree” becomes 6 – 2 = 4.
- “Strongly Disagree” becomes 6 – 1 = 5.
Then consider the overall average score of someone who answered “Strongly Agree” to the first question and “Strongly Disagree” to the second question:
1. When working on new projects, I prefer to work alone rather than in a small group.
- Strongly Agree (5)
- Agree (4)
- Neither Agree Nor Disagree (3)
- Disagree (2)
- Strongly Disagree (1)
2. Given the choice, I prefer to work with a small group rather than by myself on new projects.
- Strongly Agree (1)
- Agree (2)
- Neither Agree Nor Disagree (3)
- Disagree (4)
- Strongly Disagree (5)
Their average score would be calculated as: (5 + 5) / 2 = 5. This means they received the maximum introversion score. This makes sense given their responses to the questions.
Note 1: In practice, most surveys will have far more than two questions but for simplicity sake we only used two questions in this example.
Note 2: In this example we manually reverse scored the questions, but most statistical software has the ability to reverse code questions for you.
Additional Resources
The following tutorials explain other commonly used terms in questionnaires and surveys:
What is Face Validity?
What is Predictive Validity?
What is Concurrent Validity?
What is Content Validity?