How do you deal with non-response bias when surveying sensitive topics?

1 Choose an appropriate mode

The mode of your survey refers to how you deliver and collect your questions, such as online, phone, mail, or face-to-face. Different modes have different advantages and disadvantages in terms of cost, convenience, coverage, and response rate. When surveying sensitive topics, you should consider the mode that best suits your target population, your research objectives, and your ethical obligations. For example, online surveys may offer more anonymity and privacy than phone or face-to-face surveys, but they may also exclude some groups who have less access to the internet or are less comfortable with technology.

2 Design clear and respectful questions

The wording and format of your questions can influence how people respond to your survey, especially when they are sensitive or personal. You should design your questions to be clear, concise, relevant, and respectful. Avoid using jargon, slang, or ambiguous terms that may confuse or offend your respondents. Use simple and direct language that is easy to understand and answer. Provide clear instructions and examples if needed. Use closed-ended questions with predefined response options when possible, as they are easier to answer and analyze than open-ended questions. However, you should also provide an option for "prefer not to answer" or "don't know" for sensitive questions, to respect your respondents' right to withhold information.

3 Establish trust and rapport

One of the main reasons why people do not respond to surveys or skip sensitive questions is because they do not trust the surveyor or the survey purpose. They may fear that their answers will be used against them, shared with others, or exposed to public scrutiny. To overcome this barrier, you should establish trust and rapport with your respondents before and during your survey. You should explain the purpose and importance of your survey, how you will use and protect their data, and what benefits or incentives they will receive for participating. You should also thank them for their time and cooperation, and assure them that their answers are confidential and voluntary.

4 Follow up and remind

Another reason why people do not respond to surveys or drop out halfway is because they forget, lose interest, or encounter technical difficulties. To prevent this from happening, you should follow up and remind your respondents about your survey. You should send them multiple invitations and reminders through different channels, such as email, text, or phone, depending on the mode of your survey. You should also monitor your response rate and track your non-respondents, so that you can target them with tailored messages or incentives. However, you should also respect your respondents' preferences and opt-out requests, and avoid spamming or harassing them.

5 Analyze and adjust

Even if you follow all the tips above, you may still encounter some non-response bias in your survey results. Therefore, you should analyze and adjust your data accordingly, to account for the potential differences between respondents and non-respondents. You can use various methods to do this, such as weighting, imputation, or post-stratification. These methods involve using additional information, such as demographics, previous surveys, or external sources, to estimate the missing values or correct the sample distribution. However, you should also be aware of the limitations and assumptions of these methods, and report them transparently in your findings.

6 Here’s what else to consider

This is a space to share examples, stories, or insights that don’t fit into any of the previous sections. What else would you like to add?