Tips for Setting up Your Online Survey to Collect Quantitative Data

Posted March 22, 2017

Using online surveys has become one of the most common methods of collecting quantitative data for doctoral research. Online surveys are often more convenient than paper and pencil surveys for both the researcher to administer and for the participants to complete. Additionally, most online survey services offer features that can help prevent errors in data collection and make your data management more efficient. The key is knowing how to use these features properly in order to take advantage of them. Below are a few tips to consider when setting up your online survey.

Control your survey flow using question logic: Most online survey services allow you to control the flow of your survey so that respondents who answer a question in a particular way can skip certain questions or be screened out of the survey. This is useful if you have specific inclusion criteria for your study and you wish to screen out participants who do not meet your criteria. For example, if your participants are required to be between the ages of 20 and 30, you can include a question that asks for the respondent’s age. If their answer falls outside of that age range, they can automatically be disqualified from the survey without having to answer further questions. This is also the easiest way to handle informed consent in online surveys. You can put the informed consent information on the very first page of your survey and include a survey item that asks respondents if they agree or do not agree to participate. If they answer “do not agree” they can be automatically disqualified.

Use response validation: If you have questions in your survey in which respondents will type numbers into a text box (e.g., for “age” or “income” questions), it is crucial to use response validation to make sure respondents’ answers are in the correct format. Response validation allows you to control what respondents are able to type into the text box. For instance, you can limit responses to whole numbers, or only allow numbers that fall within a set range (e.g., between 1 and 100). This will prevent respondents from entering nonsensical numbers (such as “500” for age). This will also keep the format of the responses consistent, which can help you avoid headaches cleaning the data later. For example, say you have a question that asks for the respondent’s annual income. If you do not use response validation, some people might type in 50000, but others might type answers such as $50,000, 50K, Fifty-thousand, etc. If the format of the responses is all over the place like this, it will make the data impossible to analyze without meticulous david

Use forced response: Finally, the easiest thing you can do to make sure you get the most complete data possible is to use forced response. This is a feature that you can add to any question that forces the respondent to provide an answer. If the respondent attempts to continue the survey without answering the question, they will be given a notification informing them that the question requires an answer. Using this will greatly reduce the amount of missing data you have in your final dataset. However, just make sure you keep ethical considerations in mind when using this feature. If your survey contains questions about sensitive subject matter, it may not be ethical to require answers to those questions. If you are unsure if you should require respondents to provide an answer to certain sensitive questions, it is always best to ask a representative from your school’s Institutional Review Board (IRB).

Pin It on Pinterest

Share This