Get in touch

AnswerMiner > Data science  > What everyone should know about survey
survey-answerminer

What everyone should know about survey

It is always a problem after we have a bunch of data from surveys that we can’t do anything with them. To fix this problem we give a cheat sheet with you can create an analyzable survey. We will write about online survey because nowadays it is the most popular and it is the easiest way to import data from. First, you have to have target group and a goal you want to reach with your survey. Now let’s say you have everything to start the project. You know your target group, goal, method etc. So the next step is creating the schema of your survey.

4 steps of questions

Start with a generic question and continuously dig deeper and in the end, you can ask for personal, sensitive data.

  • Questions about knowledge: “Do you know these brands?”
  • Questions about usage: “What kind of wine do you drink for a dinner?”
  • Questions about opinion or attitude: “What do you think about this brand?”
  • Statistical questions: “Data about the Interviewee with you can segment the data or quantitative data”
“Most of the people starts with sensitive, or statistical data like gender, salary, political affiliation, but this is one of the biggest mistake they could do”
knowledge-answerminer

6 Golden Rules

Remember to follow the following rules:

  1. Start with general parts
  2. Introduction of the survey affects the fillers, so write it well
  3. Smooth transition between the questions
  4. Questions have to be following each other in a logical way
  5. Place sensitive questions in the end of the survey
  6. Place personal questions in the very end of the survey, so even if they don’t want to answer them, you will have the rest of the answers

Question types

The literature distinguishes two types of questions. Open ended questions and close ended questions. In the case of open ended questions, the responder has the opportunity to write his/her own answer. In the case of the close ended questions, there are pre-set questions, and the responder chooses between them. If we dig deeper, there are 2 sub-segment in the close ended question: alternative and selective.

Examples:

  1. Open ended question – What is your opinion about global warming?
  2. Close ended question:
    • alternative: Do you believe in global warming?
      • a, yes
      • b, no
    • selective: Which brand or brands do you know from the following list?
      • Apple
      • Samsung
      • Huawei
      • Sony
      • Nokia

Any type of question can be good for your survey. It always depends on what kind of information do you want. However, it must be said that the answers from close ended questions are way easier to analyze and organize.

Viewpoint If YES, use open-ended If YES use close-ended
Goal We would like to collect quotes, and written opinions. We would like to have ordered/scaled/ organized data.
Characteristics of the jinter The responder are available and want to answer with their own words We prefer if the responders don’t use their own words.
The way of questioning We prefer only the open-ended questions because we don’t know the list of the possible answers We want the responders to choose from pre-set possible answers
Analyzing the results We have the ability to handle many different answers and notes We would like to have the count/sum of the answers
Reporting During the reporting, we will give personal or group information by words We are reporting statistical data

Check list

survey-check-list-answerminer

Summary

One of the biggest mistake is to analyze the answers only one by one. Therefore if you want a complex view about your survey then you have to look for connections between the answers. After it you can be sure that no important information is left hidden. Moreover you will find such connection between the answers that you have never thought it would be useful.

Survey tools like survey monkey or google survey have just limited analyzing functions which are may mislead you or just good for descriptive statistical analysis. Don’t waste your time with half solutions. If you really want to understand your data use a tool like AnswerMiner. Just easily drag and drop your spreadsheet and you are set. It works with semi dirty data 😉

No Comments

Leave a reply

Get special deals and up to date content.

Subcribe