+ Reply to Thread
Results 1 to 2 of 2

Thread: Experimental design help: powering clinical study

  1. #1
    Points: 40, Level: 1
    Level completed: 80%, Points required for next Level: 10

    Thanked 0 Times in 0 Posts

    Experimental design help: powering clinical study


    I am applying for an IRB to evaluate the effect of lidocaine (local anesthetic) dilution on pain and duration of intradermal anesthesia.

    I need to figure out how many volunteer subjects we need to power the study and the best way to analyze the data.

    Procedure: each subject will have a circle of the same size drawn on each arm and a different dilution of the same volume of lidocaine will be injected into each arm at that site. During each injection patients will report pain of injection on a pain scale (either 1-5 or 1-10) for each arm. Then for the next hour the subject will be pricked with a needle every 10 minutes in each arm to see if they are still numb (yes or no) in order to make a duration calculation for each dilution.

    I would greatly appreciate if someone could share their expertise with me regarding the best test to analyze this data. Thank you so much in advance.

    Randy Gunther

  2. #2
    TS Contributor
    Points: 21,765, Level: 92
    Level completed: 42%, Points required for next Level: 585

    Thanked 7 Times in 7 Posts

    Re: Experimental design help: powering clinical study

    I don't understand the difference between the two arms, is there any difference or you simply makes two samples out of each patient. If you give different treatments in each arm, then it's a paired design. If it is identical, it is a repeated measures design. Big difference.

    You need to build up a question of interest, or in clinical trials language, an endpoint, what do you want to show / test ? After you do that, you can easily calculate the sample size required for this trial.

+ Reply to Thread


Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts

Advertise on Talk Stats