Getting Ready

Getting Ready

Our goal is for consultation sessions to be as valuable and effective as we can make them. Based on our experience, we have several suggestions to help you get the most out of the experience.

  • Be ready to teach us. We've got a lot of experience and expertise. But, you've been thinking about your problem longer than we have. We don't know the idiosyncrasies of your situation, data, and approach. We'll have questions that you'll have to answer. They might seem obvious to you, but it is part of the process.
  • Be ready to learn. We want to solve your problem. But we also want you to be able to solve it in a month or two when it happens again.
  • Find the right consultant. Everyone on our team uses different tools and has different skills. We share that information with you so you can find the right match.
  • Open your code and data. We'll be able to spend more time talking about your problem if you are ready to jump in.
  • Get your environment ready. If you are using a laptop, we want to help you solve the problem on that same laptop. To help us do that, you should make sure you have any required software installed and that you can reproduce the problem you are having.
  • Ask yourself questions. Just like doctors, nurses, and other health care providers we ask questions to get a quick understanding of the symptoms you are experiencing, we use diagnostics to pinpoint a cause, and we make recommendations or prescriptions for you to take. You can get into that mindset if you start by asking yourself some questions before you come.

Questions to ask yourself

  1. What type of question do you think you have?
    • Is it conceptual and software agnostic?
    • Is it specific to a particular tool or program?
    • Is it about finding resources (e.g., tutorial, datasets)?
  2. What is your specific goal for this session (don't worry, it's okay to use multiple sessions)? How would you briefly explain your goal while waiting for a coffee at a coffee shop?
  3. Are there examples of research (published or unpublished) that use the kinds of tools and techniques you are using?
  4. Are there examples of people with the same problem? What worked in those cases (you might look at StackOverflow or CrossValidated)? Why doesn't it work for me?

Have a question?

Send us an email at statlab@yale.edu and we'll get back to you.