The use of surveys is one of the most important areas of measurement in applied social research. It covers any measurement procedure that involves asking questions of the sample. A survey can range from a short form to an intensive in-depth interview. Thus, there are several aspects to consider when conducting a survey. Here, a number of questions need to be considered including: the different types of questions; decisions on the content and wording of the question, response format and sequence in the instrument.
Building the Survey
Building a survey instrument is an art itself. There are numerous decisions to be made about content, writing, formatting, and placement which can have important consequences for the entire study. While there is no perfect way to accomplish this job, there are several tips that could increase the chances of developing a better end product.
There are several areas involved in writing a question:
- Determine question content, scope, and purpose
- Choose the response format you use to collect information from the respondent
- Find out how to ask the question to address the topic of interest
Finally, once you have the questions written, there is the question of how to best place them in the survey. According to Alvira (2011), although there are many aspects of the construction of surveys that are common sense, if you are not careful, you can make critical mistakes that have dramatic effects on the results.
The first set of considerations has to do with population and its accessibility. For some populations, you have a complete list of units to be sampled. For others, such a list is difficult or impossible to compile. For example, there are complete lists of registered voters or people with active driver's licenses. But no one maintains a complete list of homeless people. If you are doing a study that requires input from homeless people, chances are good that you need to go personally to find respondents. In such contexts, you can dismiss the idea of mail surveys or phone interviews.
Does the population know how to read and write?
Questionnaires require respondents to be able to read. While this may initially seem like a reasonable assumption for many adult populations, the adult illiteracy rate is high in some rural sectors. And, even if respondents can read, the questionnaire may contain difficult or technical vocabulary. Young children would not be good targets for quizzes.
Are there language problems?
We live in a multilingual world. Virtually all societies have members who speak a language other than the predominant one. Some countries like Canada are officially multilingual. And, our increasingly global economy requires us to do research covering different countries and language groups.
Will the population cooperate?
People who research on immigration issues have a difficult methodological problem. They often need to speak to undocumented immigrants or people who can identify others who are. Could we expect those respondents to cooperate? According to Sainz (1991), although the researcher may have good intentions, respondents may consider that they are at legal risk if the information reaches the authorities. The same can be said of any target group that engages in illegal activities.
What are the geographical restrictions?
Is the population of interest scattered over a geographic range too wide for you to feasibly study? You may be able to email the instrument to a national sample. Or even that you can conduct telephone interviews. But it is almost certainly less feasible to do research that requires interviewers to visit respondents directly if they are widely dispersed.
Questions to consider regarding the sample in the Survey
The sample is the real group that you will have to contact in some way. There are several important sampling issues to consider when doing a survey.
What data is available?
What information do you have about the sample? Do you know their current addresses? Your current phone numbers? Are your contact lists up to date?
Can respondents be found?
Can respondents be located? Some people are very busy. Some travel a lot. Some work the night shift. Even if you have an accurate phone or address, you may not be able to locate or contact your sample.
Who are the respondents?
Who are the respondents in the study? Suppose we have a sample of households in a small city. Do you want to interview a specific individual? Do you want to speak only to the "head of the family"? Are you willing to speak to someone else in the household? Will you speak to the first adult household member who opens the door? How will you manage multi-family homes? Similar problems arise when we talk about samples in companies. Can you survey any member of the organization? Or do you just want to speak to the Director of Human Resources? What if the person you would like to interview is unwilling or unable to participate?
Can samples be taken from all members of the population?
If you have an incomplete list of the population, you may not be able to sample each member of the population. The multi-group lists are extremely difficult to keep updated. People move or change their names. Even though they are on the sampling list, you may not be able to access them. And some may not even be on the list.
Are response rates likely to be a problem?
Even if you can solve all the other population and sampling problems, you still have to deal with the issue of response rates. According to Babbie (1988), there are several problems to consider. Some members of the sample will simply refuse to respond. Others have the best of intentions, but can't seem to find the time to submit the questionnaire before the due date. Others lose the instrument or forget the appointment for an interview. Low response rates are among the most difficult problems in survey research. They can ruin a well-designed survey effort.
Aspectos relacionados con las preguntas en la encuesta
Sometimes the nature of what you want to ask respondents will determine the type of survey you select.
What types of questions can be asked?
Are you going to ask personal questions? Are you going to need to get a lot of detail in the answers? Can you anticipate the most frequent or important types of answers and develop closed questions?
How complex will the questions be?
Sometimes it is a complex topic or theme. The questions can have multiple parts. You may need to ask sub-questions.
Are screening questions needed?
A screening question may be necessary to determine if the respondent is qualified to answer the survey. For example, you don't want to ask someone their opinion about a specific computer program without first evaluating whether they have any experience in computer software.
Can you control the sequence of questions?
Can a reasonable sequence of questions be constructed beforehand? Or are you doing an initial exploratory study in which you may need to ask many follow-up questions that you cannot easily anticipate?
Will there be long questions?
If the subject is complicated, you may need to provide the interviewee with some detailed background. Can you reasonably expect the interviewee to have enough time for the survey?
Will long answers be required?
If you are asking about the different computer equipment they use, you may need to have a long list of answers. Clearly, it can be difficult to ask about each of these in a short phone interview.
Tips to create your survey
Filter the sample of the target population
Who to contact? It is an important question that an investigator should answer and keep in mind when conducting research. The accuracy of the results may depend on who the members of a sample are and how useful their opinions are. The quality of the respondents in a sample is very important for the results received for the research and not the quantity. If a researcher seeks to understand if a product feature will work well with their target market, they can conduct a research survey with a group of market experts for that product or technology.
Choosing the Right Survey Design
It may be the key to getting the information you need to make crucial decisions for all of your research. It is very important to choose the right types of questions and to choose the corresponding design. If this is your first time creating a survey, it may seem like an intimidating task. For this you must have a group of experts to help you validate it.
What do you want to achieve with the survey? How will you measure it in a timely manner and what are the results you expect? Pick the right questions: Designing a survey can be a difficult task, but asking the right questions can help you get the answers you're looking for and make the analysis task easier. Therefore, always choose those specific, research-relevant questions.
Distribution of the Survey
Perform launch tests on all electronic devices if applicable. Once the survey is ready, it is time to share and distribute it to the correct audience. Make sure to store the results in a particular document or Excel sheet, with all the necessary categories mentioned, so you don't lose the data. This is the most crucial stage. Responses should be collected based on various categories, such as demographics, behavior, among others. This is because, as a researcher, you must know where the answers come from. It will help you analyze, predict decisions, and help write the summary report.
Preparation of the summary report
Now is the time to share the analysis. At this stage, you should mention all the responses obtained from a survey in a fixed format. Furthermore, the reader must be clear about the objective. Questions like: if the product or service has been used or not. Do the respondents prefer some other product to another? Any recommendation? Now is the time to prepare the final action plan, based on the stated objective, the responses collected and the conclusion made.
At Online-Tesis.com, we will help you solve all these obstacles. Whether you need to design the survey or want to apply it. Our experts will help you even with the validation of the instrument, which is one of the most sensitive aspects in terms of quantitative application.
Surveys are regularly used to make individual decisions, such as running a particular ad campaign or creating a new product or service, but they become even more powerful when repeated over time. A common phrase among researchers who use surveys is "the trend is your friend." After all, repeatedly asking the same question at different times offers a clear perspective on how things are changing. The US Census, a survey in itself (albeit a massive one), is particularly powerful in cataloging the main demographic changes in the country. And a company's performance indicator may not mean much on its own, but a significant drop in its second-quarter score would rightly send its executives looking for an explanation and solution.
Alvira, F. (2011). La encuesta: una perspectiva general metodológica. Madrid: Centro de Investigaciones Sociológicas. Cuadernos Metodológicos, 35
Babbie, E. R. (1988). Métodos de investigación por encuesta. México: Fondo de Cultura Económica.
Sainz, E. (1991). El cuestionario en los sondeos de opinión. En M. Latiesa, El pluralismo metodológico en la investigación social: ensayos típicos. Granada: Universidad de Granada, 291-309.