How JustAnswer Works:
  • Ask an Expert
    Experts are full of valuable knowledge and are ready to help with any question. Credentials confirmed by a Fortune 500 verification firm.
  • Get a Professional Answer
    Via email, text message, or notification as you wait on our site.
    Ask follow up questions if you need to.
  • 100% Satisfaction Guarantee
    Rate the answer you receive.
Ask Ryan Your Own Question
Ryan, Engineer
Category: Calculus and Above
Satisfied Customers: 9022
Experience:  B.S. in Civil Engineering
Type Your Calculus and Above Question Here...
Ryan is online now
A new question is answered every 9 seconds

Doing a statistical analysis / T-Test. I used a 5 point

Customer Question

Doing a statistical analysis / T-Test. I used a 5 point likert scale. I am looking at a "comfort level" for people. 1-very uncomfortable to 5-very comfortable. When analyzing the data, do I exclude those respondents that PRE intervention were a 5 "very comfortable" as they already were at the top, so therefore cannot show that they improved with the intervention?
Submitted: 1 year ago.
Category: Calculus and Above
Expert:  Ryan replied 1 year ago.


Thank you for using the site.

I think this would depend on the specific situation. If it is possible for a respondent's rating to decrease due to the intervention, then no, respondents who had a pre-intervention rating of 5 should not be removed.

If, somehow, it is only possible for ratings to improve with the intervention, then you might want to exclude those who indicate from the outset that the intervention cannot help them.

In this latter case, it becomes a matter of selecting a sample that represents the target population. For example, if you were testing the efficacy of a cancer treatment, you wouldn't include people who didn't have cancer, as they wouldn't be getting the treatment anyway once it was tested and available. In the case of this 'intervention', the question for you to consider is whether people who already rate themselves a "5", would even be seeking or receiving this intervention.

Either way, you would want to be open and honest about your decisions when explaining your methodology. As long as those who are reviewing your results know exactly what was done and how the study was performed, there will be little room for any accusations of data manipulation, or other shady practices. The worst that could happen would be that your methodology is criticized by those who disagree with whatever you have done. But that would be much better than having your credibility impugned by accusations of data manipulation.

I hope this helps.



Related Calculus and Above Questions