Getting a lot of people applying for a quantitative research job? Want a fast way to weed out those that lack basic quant knowledge? Here are ten interview questions you can use to quickly, and even by phone, weed out quantitative research fakers:
- Using examples, what’s the difference between ranking and rating questions?
- In questionnaire design, what is randomization and why do we use it?
- What’s the difference between branching and piping?
- What is an example of nominal data?
- Using an example, what’s the difference between median and mode?
- Why might you use both unaided and aided questions in a questionnaire?
- What is weighting?
- Consider this scenario: You have just completed data collection for a survey about vacation trends. Your client wants to know how vacation interests vary by gender. How might you accomplish this?
- Consider this scenario: A colleague has done a survey of 50 people to measure satisfaction with auto leasing terms. He reports that overall satisfaction is 2.375. What questions or concerns might you have?
- Consider this scenario: You have collected survey data from 500 people to learn about their frozen pizza shopping behaviors. Your want to see what combination of demographic variables predict higher frozen pizza purchase volume. What type of data analysis might you use?
If they get all 10 correct, your job candidate has some solid quantitative research knowledge and just may be a research rock star. You may still want to test them for hands-on data analysis (if that is required). But at minimum, you know they have appropriate knowledge and will be able to hold their own when working with colleagues, clients, and data analysis partners.
If they get items 1 to 7 correct, they likely have a strong grasp of questionnaire design, and some light data analysis skills. For some positions, this may be adequate—especially if your research team includes dedicated data analysts.
If they only get items 1 to 3 correct, this is a person qualified for a junior-level position. This job candidate has some quantitative research knowledge but is not yet able to manage an entire project. They will likely be able to contribute to questionnaire design and programming, but they will need data analysis support.
If they get none of these questions correct, hirer beware. This may be a candidate aspiring to be a quant researcher, but they will need significant training and support to get them there.
[Did any of these questions stump you? Would they stump your team members? Then maybe it’s time to brush up on quant skills. Try our Intro to Quantitative Data Analysis or our 10 Point Checklist for Questionnaire Design.]