The scale construction is viewed as a specialized area of survey design. Its main purpose is designing a questionnaire, which provides a quantitative measurement of a hypothetical variable. However, not all surveys are scales, so before trying to apply the procedures to the questionnaire development, the researcher should decide whether it really is a scale.
Steps:
1. Determine clearly what it is to be measured
2. Generate an item pool
- Make the questions simple
- Make the items as simple and straightforward as possible
- Design the items so that they can be answered with very little instruction
- Always avoid double-barreled questions, where the item actually combines two different questions into one
- Avoid non-monotonic questions, where people could provide the same answer to a question for two different reasons.
- Make the questions clear
- Questions which are unclear can cause respondents to interpret the items in different ways; an item should be designed in such a way that every respondent interprets it in the same way.
- Avoid using any vague words or phrases in the items.
- Level of the language used in the questions should be appropriate to the intended target audience of the scale.
- Asking for respondents’ opinions about social groups or political structures should be taken care; these questions assume that the respondent has a single, uniform opinion about the entire entity, which may or may not be true. For example, the question “How do you feel about your parents?” would be difficult to answer for someone who has positive feelings about one parent but negative feelings about another.
- Avoid biased language
3. Determine the format for measurement (Nominal, Ordinal, Interval, Ratio)
4. Have initial item pool reviewed by the experts
5. Consider inclusion of validation of items
6. Administer items to a sample
7. Evaluate the items
8. Optimize the scale length